WorksPhysics and Astronomy
Quantum machine learning geospatial time-series by seasonal encoding
Abstract
Quantum data reuploading models can increase the expressive capacity of variational quantum models, but do not necessarily improve predictive performance. In the present work, we investigate this behavior for seasonal time series forecasting and show that data encoding determines how well temporal structures are represented as circuit depth increases. We develop a fidelity-based quantum geometric description in which repeated encodings contribute to an effective input generator, so that reuploading depth changes the quantum geometry through which approximately recurrent inputs are distinguished. We construct fixed and adaptive seasonal encodings that represent observation magnitude and seasonal phase in distinct Bloch-sphere coordinates. We evaluate these encodings for monthly precipitation derived from ERA5-Land, a global reanalysis dataset, from a representative semi-arid, drought-prone tropical region in East Africa, using a 14-month lag window and reuploading depths = 1-6. We find that in ideal simulations, standard value-based encodings degrade markedly with depth, whereas adaptive seasonal encodings preserve temporal correlation, spectral structure, and forecasting accuracy. Noisy simulations show that this encoding hierarchy persists at shallow and intermediate depths, while larger depths are limited by circuit noise and optimization difficulty. The seasonal quantum models remain competitive with established classical forecasting methods (ARIMA, random forests, and LSTMs). These results identify structure-aware quantum data encoding as a general strategy for building deeper quantum reuploading models.
Introduction
Remote sensing is now central to observing environmental changes across spatial and temporal scales. Optical, radar, thermal, and LiDAR sensors provide repeated measurements of, for instance, land cover and land-use change, forest structure, surface temperature, water availability, and precipitation [1, 2, 3]. These measurements are important not only for characterizing the present state of the Earth’s environment, but also for understanding how it evolves. Precipitation time-series data are especially critical for understanding agricultural productivity, water resource availability, drought and flood conditions, and food security monitoring [4, 5, 6]. However, the diversity of data modalities is growing and the resulting data volumes are increasing. Thus, developing novel methods for the extraction and forecasting of meaningful spatio-temporal patterns is an increasingly important problem in geospatial analysis.
Time series forecasting differs fundamentally from analyzing unordered observations, since predictive information is encoded not only in the values themselves, but also in their temporal organization. Environmental signals often exhibit recurring seasonal patterns, trends, and correlations across time scales, yet they are generally not perfectly periodic. Classical methods, from autoregressive models to random forests to recurrent neural networks, exploit these dependencies in different ways. Across these methods, performance depends on model capacity as well as on whether the representation preserves the relevant temporal relationships. As environmental forecasting problems become increasingly multivariate and spatiotemporal, the relevant predictive structure can involve correlations across time, and also across variables, spatial locations, and observational modalities. Therefore, a central challenge and opportunity is to determine whether new computational paradigms can offer representations that better preserve these predictive structures.
Quantum machine learning (QML) provides a novel framework for constructing such representations by embedding classical data into quantum states and processing them with trainable quantum circuits [7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17]. The ability of quantum feature maps and entangling operations to construct correlated representations makes QML particularly interesting for learning problems in which multiple interacting sources of structure must be represented simultaneously. Whether this representational flexibility translates into useful predictive performance remains an open question and should first be established in controlled settings where the relevant structure can be identified and interpreted. In variational quantum models, the choice of data encoding determines how relationships in the classical input space are translated into the geometry of Hilbert space and can therefore strongly influence what the model is able to learn [18, 19, 20, 21, 22]. Data reuploading architectures extend this idea by repeatedly inserting the classical input between trainable variational transformations, allowing increasingly rich nonlinear functions to be represented as the number of reuploading layers grows [23, 24, 25]. Increasing reuploading depth, however, does not necessarily lead to improved predictive performance and can be accompanied by challenges optimizing the model as the behavior of the objective function varies significantly [26, 27, 28, 29]. Since the input is repeatedly re-encoded after successive quantum transformations, increasing depth also changes how the circuit represents relationships between different inputs.
Understanding this depth-dependent representation is therefore particularly important for structured data such as time series, where predictive information depends on preserving meaningful relationships between temporally related observations. Before extending such models to multivariate and spatiotemporal settings, though, it is essential to establish how they behave in a controlled forecasting problem where the relevant temporal organization can be isolated. A univariate seasonal time series provides such a setting: the dominant recurrence seasonal structure can be identified directly, the effect of quantum data representation can be examined independently of cross-variable interactions, and forecasting performance can be compared against classical approaches.
Most commonly used quantum angle encodings map numerical input features directly through their magnitude into single-qubit rotations [20, 30, 31, 32, 33, 34] while carrying no explicit information about where that observation occurs within a recurring temporal cycle. For a seasonal signal, these two pieces of information are qualitatively distinct. Similar precipitation values observed at different times of the year can have different temporal meanings, while observations separated by one annual cycle can occupy corresponding seasonal positions even when their magnitudes differ. A value-based encoding therefore requires the variational circuit to infer this organization indirectly from the repeated sequence of observations. This distinction becomes especially relevant in data reuploading models where repeated encodings inserted between variational layers are known to modify the function classes accessible to a variational quantum model [23, 25]. Recent work in quantum machine learning has emphasized the value of incorporating known structure directly into quantum representations rather than relying only on unconstrained model capacity [35, 36, 37]. This motivates a broader design question for quantum time series learning: when a physically or statistically meaningful temporal structure is already known, should that structure be incorporated directly into the quantum data encoding, or left for the variational circuit to infer?
In this work, we address this question by directly linking temporal recurrence to the geometry induced by a quantum data reuploading circuit. We consider input windows separated by a characteristic recurrence period and use their quantum-state fidelity to quantify how closely recurring observations are represented as reuploading depth increases. A local geometric analysis relates the distinguishability of these inputs to a Fubini-Study metric [38, 39, 40, 41] generated by contributions from each reuploading layer, showing explicitly that circuit depth changes the geometry through which pre-existing temporal differences in the data are resolved. As a result, we construct season-aware quantum encodings that represent observation magnitude and seasonal phase via separate coordinates on the Bloch sphere. Precipitation magnitude determines the polar coordinate, while position within the annual cycle or calendar month determines the azimuthal coordinate. We consider a fixed seasonal representation and its adaptive variants in which this reference geometry can be deformed during training, allowing the model to learn from the data without discarding the known temporal organization of the signal.
We demonstrate these ideas using monthly precipitation forecasting for Napak, Uganda, with a hybrid quantum data reuploading model across reuploading depths . To this end, we compare conventional value-based angle encodings with the fixed and adaptive seasonal encodings in ideal simulations, and subsequently examine the seasonal models under noisy simulations. We further benchmark the resulting forecasts against classical statistical and machine learning approaches: ARIMA (autoregressive integrated moving average) [42], random forest [43], and LSTM (long short-term memory) [44].
As a main result we find that in ideal simulations, the value-based encodings progressively lose forecasting performance and temporal structure as reuploading depth increases, whereas the adaptive seasonal encodings remain substantially more stable across depth. This hierarchy is also retained in noisy simulations at shallow and intermediate depths, but circuit noise and optimization difficulty begin to dominate at larger . Taken together, these results show that increasing circuit depth alone is insufficient to improve quantum time-series learning. Rather, the structure by which the data is encoded can play a central role in determining whether predictive temporal information remains accessible as the model deepens.
Hybrid quantum-classical machine learning
We begin by describing the hybrid quantum-classical forecasting model used throughout this work. Given a temporally ordered sequence of observations, the forecasting task is formulated as a one-step-ahead prediction from a lag window. We implement this map using a quantum data reuploading architecture in which the same input is repeatedly encoded between variational circuit blocks [20, 25, 46, 48] [47]. This construction allows us to vary the reuploading depth while keeping the underlying forecasting task and readout architecture fixed.
Consider a univariate time series . To predict the observation at time , we construct a lag window containing the preceding observations
and learn the one-step forecasting map
where is the prediction of the subsequent observation and denotes the complete set of trainable parameters of the hybrid quantum-classical model. We realize this map using a quantum data reuploading architecture. Each component of the lag window is associated with one qubit, resulting in a -qubit register initialized in . We separate these parameters according to their role: . Here, contains parameters of a trainable encoding block, contains the parameters of the variational block, and contains the parameters of the classical output head.
The quantum circuit consists of successive data reuploading layers, cf. Figure 1 for a sketch. At layer , the input window is first mapped onto the quantum register via a data encoding block followed by a trainable variational circuit block . For our present purposes, we implement using a hardware-efficient variational ansatz consisting of a trainable three-parameter rotation on every qubit followed by a nearest-neighbor ring of CNOT gates, where the three rotation angles on each qubit are independently trainable. The raw data values are suitably transformed via classical pre-processing such that they can be encoded into . One complete reuploading block is, therefore,
Figure 1. The hybrid quantum-classical machine learning model for time-series forecasting. Within each reupload layer, classically preprocessed data enters the quantum circuit through a data encoding block, followed by a variational block. This is repeated times followed by Pauli- measurement on all qubits, which is then passed onto a classical output head to obtain the prediction after classical post-processing. This circuit includes trainable parameters in the encoding step (), which parameter is omitted in some of the encodings. Figure generated using [45].
and the depth- circuit becomes
Throughout this work, the reuploading depth denotes the number of complete encoding-variational blocks. For fixed data encodings, contains no trainable encoding parameters, whereas for adaptive encodings, the parameters are optimized jointly with the variational circuit.
The quantum state representing the lag window after reuploading layers then reads
where the dependence on trainable parameters has been suppressed for ease of notation. The quantum state is converted into a finite-dimensional classical vector by performing a Pauli- measurement on all qubits , which is the output of the quantum model,
These measurements are passed to a classical output head,
where denotes the forecast in the transformed target space, which is then transformed back into raw data units using classical post-processing. The forecasting model is trained by minimizing the empirical prediction loss over the training windows.
With the forecasting architecture established, we now turn to the precipitation time series on which it is evaluated. The temporal structure present in the data will provide the basis for examining how recurrent information is represented by the quantum model.
Dataset – precipation time-series
We study a monthly precipitation time series for Napak, Uganda (, ), spanning January 1981 through November 2025. Napak is located in the drought-vulnerable Karamoja sub-region, an agro-pastoral area characterized by high climate variability and frequent, acute rainfall deficits [49]. Demonstrating the efficacy of quantum machine learning algorithms in a challenging region with such acute environmental dynamics establishes a robust baseline for extending the proposed architecture to similar climate-vulnerable regions globally. The monthly precipitation record was extracted from the ECMWF ERA5-Land Monthly Aggregated dataset (ECMWF/ERA5_LAND/MONTHLY_AGGR) via Google Earth Engine [6]. We retrieved the accumulated monthly precipitation (total_precipitation_sum) and converted the values from meters to millimeters.
The resulting record contains 539 consecutive monthly precipitation observations. We use a lag window of length months to predict precipitation in the subsequent month. Thus, each supervised example consists of 14 consecutive monthly observations followed by a one-month-ahead target. Figure 2(a) shows the complete time series chronologically divided into 350 training targets spanning March 1982–April 2011, 70 validation targets spanning May 2011–February 2017 and 105 test targets spanning March 2017–November 2025. This chronological split preserves the temporal ordering of the forecasting problem while preventing leakage from future intervals into model training.

Figure 2. Dataset and seasonal structure (a) Monthly precipitation time series for Napak, partitioned chronologically into training, validation, and test intervals. (b) Normalized Fourier power of the training data only, computed after mean subtraction. The Fourier spectrum has a peak at approximately 12 months, indicating annual recurrence of the seasonal dataset.
The signal exhibits substantial month-to-month and year-to-year variability while retaining a recurrent annual structure. To characterize this recurrence, we compute the Fourier spectrum from the training data after subtracting the mean. As shown in Figure 2(b), the data exhibits a dominant annual frequency corresponding to a period of approximately 12 months. The data, however, is not perfectly periodic; lag windows separated by one annual cycle are generally similar but not identical. This motivates the central question considered next: how does a quantum data reuploading circuit distinguish such approximately recurrent input windows, and how does that distinction change as the reuploading depth increases?
Theory – ideal quantum circuit
Having shown that the time series has a characteristic recurrence period months and is approximately periodic, we ask how the quantum model represents two lag windows separated by one such period, and . This comparison isolates the effect of repeated data encoding on temporally related inputs and provides the basis for analyzing how depth modifies the representation of seasonal structure.
The similarity between two such inputs is measured by the fidelity,
with . A value corresponds to identical quantum states up to a global phase, whereas smaller values indicate greater distinguishability in the quantum representation. Suppose that the time series is perfectly periodic with period , that is, . Every component of the lag vector then repeats . Since the trained circuit is a deterministic function of the input and trained parameters, for arbitrary reuploading depth and arbitrary variational parameters. Consequently,
Thus, repeated reuploading of the same data cannot distinguish two identical windows. Any depth-dependent change in the representation of seasonally related inputs must therefore originate from the fact that real seasonal signals are only approximately recurrent.
We describe this imperfect recurrence by writing
where contains the cycle-to-cycle differences between corresponding components of the lag window. The displacement is a property of the time series and exists before any input is processed by the quantum model. The role of the quantum circuit is therefore not to create this seasonal mismatch, but to determine how strongly this mismatch is represented in Hilbert space.
To make this explicit, consider sufficiently small . The state associated with the displaced window can be expanded around as
The local distinguishability of two seasonally related windows is therefore controlled by the derivatives of the depth quantum state with respect to the input coordinates. Determining these derivatives requires accounting for the contribution of every reupload and the circuit transformations that precede it. Assume that the encoding is differentiable with respect to the chosen continuous input coordinates. For the component of the lag window at reuploading layer , we define the encoding generator as
so that
This generator describes the sensitivity of a single encoding layer to a change in input coordinate . In a data-reuploading circuit, however, the same coordinate enters at every encoding layer, so the derivative of the complete circuit contains one contribution from each reupload. Define the partial circuits
so that contains all operations applied before the reupload. The resulting effective generator is
A straightforward calculation using Eq. (11) and Eq. (15) shows that the corresponding fidelity admits the local expansion
where is the Fubini-Study metric [38, 40] induced by the trained depth- circuit in input space. The metric can be written as the symmetrized covariance
where and . The structure is particularly transparent when projected directly onto the seasonal displacement . Define
Equation (16) becomes
where equality is understood to leading quadratic order in . Equation (16) separates two conceptually different contributions. The displacement is a property of the data and exists before the quantum model is applied. The metric , in contrast, describes how strongly the trained depth- circuit resolves that displacement. The details of the derivation are presented in the Supplemental Material.
The role of encoding is particularly transparent at a single reuploading layer. At the fidelity becomes
The single reupload layer fidelity is therefore determined entirely by the encoding map. Consequently, reflects the imperfect recurrence already present in the data in the Hilbert space. At higher depths, intermediate variational blocks occur between repeated encoding operations and rotate the layerwise generators appearing in Eq. (15), thereby changing the geometry of the temporal representation.
For , implies that the effective generator, which is transformed by all preceding encoding and variational layers through , leads to degradation in the temporal representation in the quantum circuit. However, in general, multiple reupload depth may suppress, amplify, or redirect the pre-existing differences in the real time series. Importantly, Eqs. (19) and (16) do not imply that larger fidelity leads to better forecasting. A useful predictor must remain sensitive to genuine changes that contain predictive information. The result instead establishes that reuploading depth changes the geometry with which the circuit distinguishes temporally related inputs. Whether this change is beneficial depends on its alignment with the data’s predictive structure.
This observation provides the central motivation for the encoding strategies considered in this work. An encoding based only on the instantaneous value of an observation has no explicit information about where the observation occurs within a recurring temporal cycle. This suggests a general design principle for the quantum time series models: when a known temporal structure is predictive, it can be advantageous to encode the structure explicitly rather than requiring the variational circuit to infer it solely from repeated value-based reuploads. In the following sections, we apply this idea to construct quantum encodings that progressively incorporate and adapt to its seasonal organization.
Quantum data encodings
The analysis in Sec. IV showed that the geometry of approximately recurring inputs depends on the data encoding map, while Sec. III identified a dominant annual frequency with months. Therefore, we will compare a sequence of quantum encodings that progressively incorporate this temporal structure.
The first two encodings depend only on precipitation magnitude and serve as value-based baselines. The remaining three encodings explicitly account for the position of each observation within the annual cycle, with the last two allowing this seasonal geometry to adapt during training. In all five cases, the lag windows, variational circuit, quantum readout, and classical prediction head are kept fixed, so that the differences between models arise from data representation itself.
For an input window qubit represents the observation at the index
Since the time series has a characteristic period , we associate each observation with the seasonal index
This implies that
Thus, identifies the observation within the full time series, whereas identifies its position within the recurring annual cycle.
At reuploading layer , the complete encoding operation is constructed from single-qubit operations as
The dependence of is absent for value-based encodings introduced below and becomes explicit only for seasonal encodings.
Value based encodings
We first consider two fixed encodings that depend only on the precipitation magnitude. Let denote the linearly scaled precipitation value corresponding to the physical observation . Define the associated rotation angle . Since these encodings contain no trainable encoding parameters and are identical at every reuploading layer, we suppress the layer index .
Ry encoding
The simplest encoding maps each scaled precipitation value to a rotation about the axis. The complete window encoder is, therefore,
The encoded state is restricted to a single great circle around the Bloch sphere or, in other words, on a single Bloch sphere meridian as shown in Figure 3(a). The magnitude of precipitation determines the position along this one-dimensional trajectory and contains no information about the seasonal position of the observation.

Figure 3. Bloch-sphere geometry of the quantum data encodings Each point represents one of the 364 monthly observations in the training set (or equivalently, 350 training targets) and is colored according to calendar month. (a) The encoding maps the scaled precipitation values onto a single meridian. (b) The encoding applies the same data-dependent angle about all three rotation axes, producing a more intricate trajectory over the sphere. (c) The fixed seasonal encoding maps the empirical training data’s cumulative distribution to the polar coordinate and assigns the calendar month to the azimuthal coordinate. Overall, it maps the data onto 12 equally spaced seasonal meridians on the Bloch sphere. (d) The learned polar encoding starts from the fixed seasonal encoding as the reference but later introduces month- and layer-dependent deformations of the polar mapping while retaining the fixed seasonal azimuths. (e) The learned polar + azimuthal encoding additionally permits bounded, month- and layer-dependent azimuthal adaptations in addition to the trainable polar coordinate. It also starts from the fixed seasonal encoding as the reference. For (d)(e), the embeddings shown here are representative of a single layer from a single trained reuploading model; the learned polar mapping generally changes from layer to layer and from model to model.
RxRyRz encoding
The second encoding applies the same data-dependent angle about all three rotation axes. The corresponding encoding operator is
This construction generates a more intricate trajectory than the encoding, but the same scalar controls all three rotations as shown in Figure 3(b). This keeps the representation one-dimensional with respect to the information supplied by each observation.
Fixed seasonal CDF encoding
The and encodings introduced above distinguish observations only through their precipitation magnitude. To incorporate seasonal recurrence, we construct a two-dimensional representation in which the precipitation magnitude and the seasonal phase control two independent angular coordinates on the Bloch sphere. We first map precipitation magnitude using the empirical cumulative distribution function derived from the training data. Let the empirical training CDF (cumulative distribution function) be denoted by as defined in Eq. (74) in the Supplemental Material. For the observation encoded on qubit , define
where . The corresponding polar angle is
The polar coordinate is determined by the relative position of the precipitation value within the training distribution rather than by its absolute magnitude. The seasonal coordinate is determined by the position of the same observation within the annual cycle.
Using the seasonal index defined above, we assign the fixed azimuthal angle,
For , the annual cycle is therefore partitioned into 12 equally spaced azimuthal directions, or in other words, the data are encoded on 12 seasonal Bloch sphere meridians as shown in Figure 3(c). Correspondingly, the encoding operator becomes
The precipitation controls the polar coordinate, while the calendar month controls the azimuthal coordinate. This construction embeds the known annual structure into the quantum representation before any variational transformation is applied. In contrast to and encodings, two observations with similar precipitation magnitude but different calendar months are no longer represented identically, and observations occurring at the same calendar month in different years lie on the same seasonal Bloch sphere meridians even when their magnitudes differ.
Adaptive seasonal encodings
The fixed seasonal CDF encoding imposes a physically interpretable geometry in which precipitation magnitude determines the polar coordinate and calendar month determines the azimuthal angle. Next, we allow this geometry to adapt during training while retaining the annual recurrence structure as the reference configuration. In both adaptive encodings, the trainable encoding parameters depend on the seasonal index and on the reuploading layer , so that different phases of the annual cycle may be represented differently at different reupload depths.
Learned polar seasonal encoding
First, we allow the polar coordinate to vary while keeping the seasonal azimuthal coordinate fixed. The CDF derived reference polar angle is transformed through a month and layer dependent map where denotes a trainable deformation of the polar coordinate. The seasonal azimuthal angle remains fixed as so that the seasonal information is preserved.
The encoding at reuploading layer is, therefore,
The trainable map is initialized to the identity, so it reduces to the fixed seasonal CDF encoding before training. Optimization subsequently allows the model to reshape the precipitation-dependent polar coordinate independently for each seasonal phase and reuploading layer, while preserving the fixed cyclic organization in azimuthal coordinate as shown in Figure 3(d).
Learned polar + azimuthal seasonal encoding
The final encoding also allows the azimuthal coordinate to adapt by a trainable month- and layer-dependent map . The polar coordinate is adapted the same way as in the learned polar seasonal encoding. The corresponding encoding operator is
The azimuthal displacement is bounded so that the model can locally adjust the seasonal phase associated with each month without arbitrarily destroying the cyclic ordering of calendar months as shown in Figure 3(e). The trainable map is initialized such that the encoding reduces exactly to the fixed seasonal CDF encoding. The three encodings consequently form a nested family. The fixed seasonal CDF encoding imposes the reference geometry.
The value-based encodings in Figure 3(a),(Figure 3b) map the time-series data exclusively according to their precipitation magnitude and completely ignore their seasonal structure. The seasonal encodings in Figure 3(c),(Figure 3d),(Figure 3e) take the seasonality into account and map the data onto 12 different meridians on the Bloch sphere. The adaptive variants deform this seasonal geometry through their learned encoding parameters. In both adaptive encodings, the encoding parameters are optimized jointly with other trainable parameters of the forecasting model. The details of the various encoding schemes are presented in the Supplemental Material.
Results
We evaluate the five encodings within the same 14-qubit data reuploading forecasting architecture, varying the number of reuploading layers over . For each encoding and depth, five independent models are trained, and model selection is performed exclusively on the validation set. The checkpoint with the lowest validation loss is retained for each run and evaluated once on the test set.
Forecasting performance is assessed using four complementary quantities: the test root mean squared error (RMSE) (Eq. (100)), which measures absolute prediction error in millimeters, the Pearson correlation (Eq. (106)), which measures temporal alignment between the observed and predicted series, the Fourier power cosine similarity (Eq. (105)), which compares their normalized frequency domain structure; and the Amplitude variance ratio (Eq. (107)), which measures recovery of the observed forecast amplitude. The detailed definitions of these metrics are given in the Supplemental Material.
Ideal simulations
The ideal simulations were performed using the default.qubit state-vector simulator and automatic differentiation framework by PennyLane [50]. The complete hybrid quantum-classical learning pipeline was implemented using PyTorch [51].
Representation of seasonal recurrence with depth
We first examine how the different encodings represent inputs separated by the dominant seasonal period. This tests the quantum geometric picture developed in Sec. IV before considering forecasting performance.
For a depth- circuit, we define the mean seasonal fidelity over all valid test set window pairs separated by as
where is the number of valid pairs in the test data. For our time series, months. Thus, measures the average similarity between quantum representations of lag windows separated by one annual cycle.
Figure 4(a) shows that the mean seasonal fidelity decreases with reuploading depth for all five encodings. The rate and scale of this decrease, however, depend strongly on how the data are represented. The and encodings begin with relatively small seasonal overlaps and decrease rapidly with depth. By contrast, the three seasonal encodings produce substantially larger overlaps at shallow depth but also exhibit a pronounced decline with .

Figure 4. Same-season quantum fidelity as a function of reuploading depth . (a) Mean seasonal fidelity measures the similarity between two quantum representations of two lag windows separated by 12 months, averaged over all possible pairs of lag windows in the test set. (b) The same fidelity normalized by expected fidelity between Haar-random states, highlighting similarity compared to a random state reference. Curves show the mean across five independently trained seeds, with shaded region indicating standard deviation.
The single-layer behavior is consistent with the geometric analysis of Sec. IV. For fixed encodings, the variational block cancels exactly from the fidelity at , so that the overlap is determined entirely by the encoding map. Correspondingly, the fixed seasonal CDF representation gives a substantially larger single-layer seasonal overlap than either value-based encoding. The adaptive encodings are initialized from the same seasonal geometry but subsequently optimize their encoding parameters during training, allowing the learned representation itself to change.
To interpret the magnitude of these fidelities in context, we compare them with the characteristic fidelity of two independent Haar-random pure states [52, 53] in a Hilbert space of dimension . For such states, . We consider the normalized quantity shown in Figure 4(b). At , the and encodings have decreased to the scale. The fixed seasonal CDF representation remains above , better than the value-based encodings. In contrast, the two adaptive seasonal encodings remain roughly two orders of magnitude above the Haar reference even at . These results show that repeated data reuploading progressively separates the quantum representations of input windows related to different years, but the extent of this separation depends strongly on the encoding geometry.
Importantly, is a diagnostic of representation geometry rather than a forecasting metric. A reduction in fidelity does not by itself imply a loss of predictive information, since the seasonal differences between and may themselves be informative. We therefore next examine whether the depth-dependent changes in quantum geometry are accompanied by corresponding changes in forecasting performance.
Forecasting performance
Figure 5 summarizes the test data predictions as a function of reploading depth . Figure 5(a) shows a clear separation between the seasonal and value-based encodings in terms of prediction error. The and encodings attain their lowest RMSE at shallow depth and generally deteriorate as additional reuploading layers are introduced. The fixed seasonal CDF encoding substantially improves upon these baselines at small depth, but its error also increases progressively with . In contrast, both learned seasonal encodings remain comparatively stable across the full depth range. The lowest test error is obtained by the learned polar encoding at , Test RMSE mm, whereas the best value-based encodings remain near 63 mm.
A similar hierarchy appears in the frequency-domain results of Figure 5(b). The learned seasonal encodings preserve an almost unchanged spectral structure across the complete depth range, with –. The fixed seasonal CDF encoding also retains strong spectral agreement at shallow and intermediate depth, although its similarity decreases at the largest . By comparison, both value-based encodings exhibit substantially stronger depth-dependent fluctuations and ultimately lose much of their agreement with the observed spectrum.

Figure 5. Forecasting metrics shown as a function of reuploading depth across the five different encodings. (a) Test root mean square error (RMSE) measures the magnitude of pointwise forecast error in precipitation units (mm). Lower values indicate better predictive accuracy. (b) Fourier cosine similarity measures the similarity between the normalized Fourier power spectra of the predicted and observed time series, thereby probing how well the forecast preserves dominant temporal frequencies. (c) Pearson correlation measures the linear correlation between the predicted and observed time series and captures whether temporal fluctuations are tracked correctly, independent of the absolute scale. (d) Amplitude variance ratio assesses whether the forecast reproduces the observed variability in amplitude. A value of 1 indicates matched variance. Curves denote the mean over five independently trained seeds, and shaded regions indicate standard deviation.
The Pearson correlations in Figure 5(c) show an even clearer difference in depth dependence. Both learned seasonal encodings maintain strong and comparatively stable temporal alignment throughout the entire range of depths. The learned polar encodings reach their largest correlation at , and remain close to this level at larger depths. The learned polar + azimuthal encoding exhibits a similar trend. The fixed seasonal encoding shows a more gradual loss of correlation with depth, whereas the value-based encodings deteriorate much more strongly and approach negligible temporal correlation by . Both learnable seasonal models show a slight increase in performance at that is not seen in any other model. This highlights the distinction between predictive model performance and the seasonal fidelity of Eq. (33) and indicates that the optimization is able to effectively utilize some of the enhanced expressive capacity from data reuploading.
The amplitude variance ratios in Figure 5(d) reveal a complementary limitation. All five models underestimate the amplitude of the observed precipitation fluctuations throughout the depth range. The learned seasonal models nevertheless retain substantially more variability than the value-based encodings and exhibit much weaker amplitude collapse as the circuit becomes deeper. The largest amplitude recovery occurs for the learned polar model at .
Taken together, the four metrics show that the learned seasonal encodings are not only distinguished by a lower pointwise error, but also preserve temporal correlation, normalized spectral structure, and forecast amplitude much more consistently as reuploading depth increases. The fixed seasonal CDF representation captures a substantial fraction of this improvement at shallow depth, but its performance degrades more strongly with , indicating that explicitly encoding the annual cycle is beneficial while allowing the corresponding geometry to adapt provides additional robustness.

Figure 6. Observed monthly precipitation is compared with the mean forecast across five independently trained seeds for the , fixed seasonal, and learned polar encodings over the first 36 months of the test data. (a) Shallow reuploading circuit with . (b) Deepest reuploading circuit with . At , the learned polar encoding continues to retain good forecasts, the fixed seasonal encoding performs slightly better, and the encoding shows the poorest forecast quality.
The comparison with the fidelity results further shows that forecasting performance cannot be identified with preservation of seasonal recurrence alone. The seasonal fidelity of the learned encodings decreases substantially with depth, yet their Pearson correlation and Fourier similarity remain nearly unchanged. The learned seasonal representations therefore continue to retain forecast-relevant temporal structure even as annually separated input windows become increasingly distinguishable in Hilbert space. By contrast, for the value-based encodings, the reduction in seasonal fidelity is accompanied by a significant loss of temporal and spectral forecasting structure.
Finally, allowing the azimuthal coordinate to become trainable does not produce a consistent improvement over adapting the polar coordinate alone. The learned polar and learned polar + azimuthal encodings exhibit very similar behavior across all four forecasting metrics, while the learned polar encoding attains the overall minimum RMSE and maximum Pearson correlation. For this time series, the additional azimuthal degrees of freedom therefore provide no predictive advantage beyond the learned polar representation and that the evenly-spaced seasonal encoding is near optimal.
Noisy Simulations
The ideal simulations show that the seasonal encodings remain comparatively robust as the number of reuploading layers increases. They further establish a clear hierarchy among the seasonal encodings, with the learned seasonal models generally outperforming the fixed seasonal CDF representation and remaining substantially more robust as reuploading depth increases. We next examine if this behavior persists in the presence of noise. For the noisy simulations, we evaluated the three seasonal encoding strategies: Fixed seasonal CDF, learned polar, and learned polar + azimuthal across .
Noisy circuit evaluations were performed with Qiskit Aer using the IBM FakeAachen noise model [54]. Circuit executions used 512 measurement shots. The logical circuits were compiled onto a fixed 14-qubit physical layout as shown in Figure 7. The entire forecasting model was trained using a hybrid optimization procedure in which quantum circuit parameters were updated using simultaneous perturbation stochastic approximation (SPSA) [55], while classical parameters were optimized with Adam [56]. To make the noisy simulations computationally tractable, the circuit evaluations were parallelized across multiple CPU cores on an HPC cluster. The details of the exact implementation are presented in the Supplemental Material.

Figure 7. Topology of IBM FakeAachen used for noisy simulations. The 14-qubit subset selected for implementing the quantum reuploading circuit is highlighted, while the remaining qubits and couplings are shown in gray.
Figure 8 compares the noisy simulations with their ideal counterparts over reuploading depths . A central observation is that, at shallow and intermediate depths , the hierarchy of encodings established in the ideal simulations is preserved under noise. In particular, the adaptive seasonal encodings retain their advantage over the fixed seasonal CDF encoding across all the forecasting metrics. Thus, the benefit of learning the seasonal encoding geometry is not restricted to ideal state-vector simulations, but is also retained in the presence of hardware-derived noise. At these depths, hardware noise degrades the absolute forecasting performance relative to the ideal case, but it does not immediately erase the relative advantage produced by the encoding choice.

Figure 8. Comparison of ideal and noisy quantum simulations across reuploading depth for the three seasonal encoding schemes. Both regimes are shown for a single matched initialization, rather than as an ensemble average across seeds. Solid lines with filled markers denote ideal simulations, while dashed lines with open markers denote simulations using the IBM FakeAachen noise model.
The situation changes as additional reuploading layers are introduced. We again observe that all adaptive seasonal encoding models perform optimally at , an observation that is not true of the fixed seasonal encodings. Beyond , the forecasting metrics deteriorate substantially for all three encodings and the differences between them become progressively compressed. The test RMSE increases and eventually enters a similar high-error regime for the three seasonal models, while the Pearson correlation and forecast amplitude decrease more strongly with depth. By the deepest circuits, the predictions retain little temporal correlation with the observed precipitation series and exhibit severe amplitude suppression and spectral dissimilarity in the Fourier domain. These trends indicate that the advantages associated with the different seasonal geometries become increasingly difficult to exploit as the depth and noise grow.
The degradation in performance at higher depths should also be interpreted in the context of the hybrid optimization procedure. During the noisy simulations, we find that convergence is sensitive to the SPSA hyperparameters, particularly the parameter controlling the gradient updates [57]. This sensitivity becomes increasingly relevant as the circuit depth grows and the stochastic optimization landscape becomes more difficult to navigate. Consequently, the deterioration observed at large need not arise solely from the accumulation of hardware noise; it may also reflect the increasing difficulty of jointly optimizing the noisy quantum circuit and classical prediction head. The performance of the noisy models could also potentially be improved through error mitigation strategies [58, 59, 60]. We therefore leave a combined systematic study of the encoding design, depth-dependent optimizer tuning, and error mitigation as an important direction for future work.
Classical Baselines
Having established that the seasonal quantum encodings substantially outperform the standard encodings as reuploading depth increases and this robustness persists under noise, we finally compare the resulting quantum models with conventional classical forecasting approaches. We consider three complementary baselines: a random forest (RF), representing a nonlinear machine learning model; an autoregressive integrated moving average model, ARIMA(7,0,6), representing a statistical time series model; and a stacked long short-term memory (LSTM), representing a recurrent neural network with a comparable notion of depth. All classical models are trained and evaluated over the same chronological training, validation, and test data splits used on the same chronological training, validation, and test data splits as the quantum models. The implementation details are presented in the Supplemental Material.
The RF and ARIMA models provide depth-independent reference points for the forecasting task. For a more controlled comparison with the depth-dependent quantum models, we constructed stacked LSTMs with recurrent depth and hidden dimension . The LSTM architecture was intentionally not chosen as a high-capacity, state-of-the-art forecasting model. Instead, its parameters were chosen so that it could serve as a classically comparable model to our learned quantum models, with a parameter count that grows approximately in step with that of the quantum model with equivalent reuploading depth.
Compared with these classical baseline models, the learned polar seasonal-encoding quantum model occupies the same overall forecasting regime, as shown in Figure 9. In ideal simulations, the learnable polar achieved best test RMSEs of . For comparison, the RF achieved mm, ARIMA(7,0,6) achieved mm, and the best mean LSTM result was 52.84 ± 0.82 mm. The same overall picture is reflected in the correlation amplitude and spectral metrics: no classical baseline uniformly dominates across all forecast metrics, and the learned polar quantum model achieves the same performance. In the presence of noise, the performance of quantum model decreased, but still achieved an RMSE of 56.54 mm and retained strong temporal and spectral structure. Together, these results show that the robustness introduced by seasonal quantum encoding is not at the expense of forecasting accuracy; rather, the resulting models remain competitive with established statistical and machine learning methods.

Figure 9. Comparison of the Learned Polar quantum data reuploading model with classical forecasting baselines across depth . For the quantum model, denotes the number of repeated data-encoding and variational-circuit layers; for the LSTM, it denotes the number of stacked recurrent layers. The learned polar quantum model and LSTM are shown as depth-dependent trajectories, whereas random forest and ARIMA serve as depth-independent reference baselines. Shaded regions indicate standard deviation across five independent realizations for the learned polar quantum model, LSTM, and ARIMA.
Discussion
In this work, we have demonstrated that the choice of encoding classical data into a quantum circuit can play a central role in determining how a data reuploading model behaves as circuit depth increases. For the rainfall time series considered here, standard value-based encodings progressively lose both seasonal structure and forecasting performance as additional reuploading layers are introduced. Explicitly incorporating the known seasonal recurrence pattern into the quantum feature map substantially changes this behavior. The fixed seasonal encoding shows improved performance at shallow depth, while the adaptive seasonal encodings remain far more robust across the full depth range. All adaptive seasonal encoding showed modest performance improvents at a depth of before declining at larger depths. These results suggest that increasing circuit depth alone is not sufficient to improve a quantum time series model (in many cases it is detrimental to performance); the geometry through which temporally structured data are repeatedly presented to the circuit is equally (or more) important.
The geometric analysis provides a framework for interpreting this behavior. Two input windows separated by one seasonal period differ by a small displacement that is already present in the underlying time series, which prevents the time series from being perfectly periodic. The quantum circuit does not create this displacement but determines how strongly it is resolved by the input-space geometry induced by the model. Locally, this relation is captured by the Fubini-Study metric generated by the complete data reuploading circuit via a quantum geometric fidelity analysis. Since the effective input generators receive contributions from every reuploading layer, increasing depth can alter how the same underlying temporal differences are represented. However, preservation of seasonal fidelity should not be interpreted as the forecasting objective itself. Rather, the useful representation is one that preserves alignment of the quantumly encoded data with known seasonal structure. In this sense, the fidelity analysis provides a diagnostic of how temporal relationships are represented, rather than a direct measure of prediction quality. These observations suggest a broader design principle for quantum learning of structured time series. When a physically or statistically meaningful temporal organization is already known, it can be advantageous to incorporate that structure directly into the quantum data encoding rather than requiring the variational circuit to infer it solely through repeated value-based encodings. In the present construction, precipitation magnitude determines the polar coordinate of the encoded qubit state while seasonal phase or calendar month determines the azimuthal coordinate, providing an explicit geometric representation of the annual cycle. The adaptive variants then deform this structured reference geometry during training. The fact that learning the polar deformation provides most of the observed improvement, while additional azimuthal flexibility gives no consistent advantage, further suggests that useful learning need not require unconstrained modification of every geometric degree of freedom. More generally, analogous constructions could incorporate other known temporal periods, phase variables, spatial coordinates, or physical symmetries into quantum representations.
The noisy simulations further show that the benefit of structured encoding is not limited to ideal state-vector evolution. At shallow and intermediate reuploading depths, the ordering established in the ideal simulations is retained under the IBM FakeAachen noise model, with the adaptive seasonal encodings continuing to outperform the fixed seasonal representation. At larger depths, however, the performance of all three seasonal models deteriorates, and their differences become increasingly compressed. This behavior highlights a practical trade-off among representational depth, hardware noise, and the increasing difficulty of hybrid SPSA optimization in a noisy landscape. A systematic separation of these effects, together with noise-aware optimization and error mitigation strategies, remains an important direction for future work.
In the presence of noise, the quantum performance decreases but remains close to the classical reference models at the best shallow and intermediate depths. These results demonstrate that the improved depth robustness achieved through structured quantum encoding can coexist with forecasting performance comparable to that of conventional classical approaches.
Finally, the classical benchmarks place the quantum results in the context of established forecasting methods. Random forests, ARIMA, and LSTM represent complementary standard statistical and machine learning approaches to the same prediction task. The best ideal seasonal quantum models achieve forecasting errors in family with these classical baselines. While it remains an open question whether QML methods can exhibit any quantum advantage, it is generally expected that quantum methods might be superior in analyzing correlated data sets [9]. The present comparison of the quantum algorithm with classical methods gives reason to be cautiously optimistic about the realizability of more intricate quantum machine learning protocols. Thus, an important next step is to extend our paradigm beyond univariate forecasting to multivariate time series, where temporal structure coexists with intervariable dependencies [61, 62]. In this setting, structure-aware quantum encodings could be used to investigate how temporal and cross-variable relationships are jointly represented, and how entangling operations provide useful representational structure [63, 64, 65, 66].
A complementary direction is to evaluate these models on real quantum hardware [67, 68, 69, 70, 71, 72] and to develop more closely matched classical baselines that enable controlled comparisons with the corresponding quantum architectures [73]. Together, these extensions would test how broadly the encoding principles identified here apply as quantum time-series models move toward richer data and experimentally realized circuits.
Data Availability
The code for numerical simulations is available can be found at [74].
Acknowledgments
S.D. acknowledges support from the John Templeton Foundation under Grant No. 63626. During the course of the project, OpenAI’s ChatGPT models were used to help understand Pennylane with PyTorch and Qiskit, to optimize code for HPCs and to orchestrate the project workflow. They were also used to help writing the plotting scripts for the figures.
References
Derivation of the local fidelity geometry
Here, we present the details of the derivation for Eq. (19) in the main text: the relation between the fidelity of two approximately recurrent input windows and the effective generators of a depth data reuploading circuit. Consider two lag windows separated by the characteristic period of the time series,
where quantifies the displacement between the two windows. Throughout the derivation, all derivatives are taken with respect to the continuous input coordinates entering the encoding operation, while the trained circuit parameters are held fixed. For compactness, we write and evaluate all derivatives at unless otherwise stated. For sufficiently small , the state associated with the displaced window has the Taylor expansion
where .
Local expansion of the fidelity
The fidelity between the two approximately recurrent windows is
The corresponding overlap amplitude is
For notational convenience, define , . Then,
The fidelity is obtained from . Keeping terms up to second order gives
Using , we can write or equivalently . Thus, the fidelity contains no term linear in . Differentiating the normalization condition twice yields
Taking the real part gives
Substituting these identities into Eq. (37), and using the symmetry of under interchange of and , gives
We therefore identify the input-space Fubini–Study metric induced by the reuploading depth- circuit as
Then Eq. (40) becomes
or equivalently,
Equation (A10) separates the cycle-to-cycle displacement of the data, , from the local geometry induced by the quantum model, . We next express this metric directly in terms of the generators of the data-reuploading circuit.
Effective input generator of a reuploading circuit
The depth- circuit is where each reuploading block is . The dependence on the trained circuit parameters is suppressed here for notational clarity. The variational operation does not depend explicitly on the input coordinates. For each input coordinate and encoding layer , define the local encoding generator
Since is unitary, . Differentiating this identity gives
which shows that is anti-Hermitian. Hence, defined in Eq. (44) is Hermitian. Multiplying Eq. (44) by from the left gives . Because is independent of ,
The same input coordinate is present in every reuploading layer. Therefore,
Substituting Eq. (46) gives
We now define the effective generator of the complete depth- circuit,
To evaluate it, define the partial circuit , . Using , the contribution from reuploading layer becomes
Summing over all reuploading layers gives
Thus, each reupload contributes a generator associated with the same input coordinate, but the contribution from layer is conjugated by all circuit operations that precede that layer. Equation (A16) also implies
The depth- state is , and therefore,
Fubini-Study metric as a generator covariance
We can now substitute Eq. (A20) directly into the Fubini-Study metric of Eq. (A8). First,
Similarly, and hence,
where . It follows that,
Since the effective generators are Hermitian,
Defining the centered generators the metric takes the symmetrized covariance form
Substituting Eq. (A25) into Eq. (A10) gives
To expose the structure along the actual seasonal displacement, define the directional bare generator at layer ,
Similarly, define the effective generator along ,
Using Eq. (A18),
Because is real, Eq. (59) can now be contracted directly:
The leading deviation from unit fidelity is therefore
Quantum data encodings
This Appendix gives the explicit parameterizations used for the five quantum data encodings considered in § 1.4 of the main text. All encodings act independently on the components of the lag window before the variational block at each data-reuploading layer. The value-based encodings depend solely on precipitation magnitude, whereas the three seasonal encodings additionally depend on the position of each observation within the annual cycle. For a lag window
the observation encoded on qubit has source index
For the present data set, . The seasonal index associated with the same observation is
with seasonal period . For the two value-based encodings, precipitation is linearly mapped from the physical interval mm to
The corresponding rotation angle is . At reuploading layer , the complete encoding operation has the product form
where the single-qubit map depends on the encoding strategy described below.
encoding
The simplest encoding uses the scaled precipitation value as a rotation angle about the axis,
The complete encoding layer is, therefore,
This encoding contains no trainable parameters and is identical at every reuploading layer . Each observation is represented along a single Bloch sphere meridian.
Same-scalar encoding
The second value-based encoding applies the same scalar angle to rotations about all three axes. For a single observation,
Thus,
Although this map generates a more intricate Bloch sphere trajectory than the encoding, the same value controls all three rotations. Consequently, the information supplied by each observation contains no explicit seasonal coordinate.
Fixed seasonal CDF encoding
Precipitation magnitude is first transformed using the empirical cumulative distribution function constructed exclusively from the raw training observations. The training reference contains the 364 observations with indices , and the right-continuous empirical CDF is
The empirical rank is mapped to the interval as
and subsequently to the polar angle
For the observation on qubit , . The seasonal phase is assigned to the azimuthal coordinate,
The resulting single-qubit encoding is
and the complete encoding layer is
This encoding is fixed and therefore does not depend explicitly on . The corresponding single-qubit Bloch vector is
Thus, empirical precipitation rank controls the polar coordinate, whereas the location within the annual cycle or calendar month controls the azimuthal coordinate.
Learned polar seasonal CDF encoding
The fixed seasonal encoder applies the same encoding at every reuploading layer. To allow the representation to adapt to both seasonal phase and circuit depth, the learned polar encoding introduces two trainable parameters for every month-layer pair ,
The first parameter determines a bounded multiplicative strength,
while the second determines a bounded polar displacement,
For the observation encoded on qubit , the resulting month- and layer-dependent polar angle is
The fixed seasonal azimuthal coordinate is retained
The single qubit encoding at layer is, therefore,
and the complete layer is
All raw encoding parameters are initialized at zero, . Consequently, , , and Eq. (84) reduces exactly to
The learned-polar model therefore begins from the fixed seasonal CDF geometry and subsequently learns month- and layer-dependent deformations of its polar coordinate.
Learned polar + azimuthal seasonal CDF encoding
The final encoding extends the learned-polar model by also allowing the seasonal azimuthal coordinate to adapt during training. The polar angle is identical to Eq. (84). In addition, each month-layer pair is assigned a third raw trainable parameter which determines a bounded azimuthal displacement,
The month- and layer-dependent azimuthal coordinate is
The corresponding single-qubit encoding is
Adjacent fixed seasonal sectors are separated by . Since the learned displacement satisfies , its maximum magnitude is half the angular separation between adjacent month sectors. The azimuthal coordinate can therefore adapt locally while remaining bounded around the corresponding fixed seasonal direction.
All three raw encoding parameters are initialized at zero, , which gives , , . Thus, the learned polar + azimuthal model also reduces exactly to the fixed seasonal CDF encoding at initialization.
Noisy Simulation Details
The finite-shot noisy simulations are carried out with the IBM FakeAachen through the PennyLane-Qiskit interface. Each expectation value is estimated from measurement shots.
All circuits are transpiled to the native FakeAachen basis using transpiler optimization level 1 and SABRE routing. This implementation uses the fixed physical qubit layout
The closing logical ring CNOT interaction is therefore routed through the available physical connectivity whenever the corresponding physical qubits are not directly coupled. Simulator truncation is enabled so that inactive physical qubits do not contribute to the simulated state space.
Hybrid SPSA-Adam optimization
Let denote the complete set of trainable quantum parameters. This vector contains the variational circuit parameters and, for the adaptive encodings, the trainable encoding parameters. We denote the parameters of the classical prediction head by . The quantum parameters are optimized using simultaneous perturbation stochastic approximation (SPSA), while the classical prediction head is optimized using Adam. At SPSA iteration , the learning rate and perturbation schedules are
with
At each iteration, a perturbation vector is drawn with independent Rademacher components. Two perturbed quantum-parameter vectors are then constructed,
For a mini-batch , the noisy quantum circuit is evaluated once at each perturbed parameter vector. The corresponding losses are
where denotes the finite-shot vector of quantum features after measurement, is the classical prediction head, and denotes the scaled/transformed target used during training. The SPSA estimator of the quantum gradient is
where the inverse is componentwise. Because each component of is either or , . The quantum parameters are then updated as
The classical-head loss is defined as the symmetric average of the two perturbed losses,
The quantum features are detached from the PyTorch computational graph before the classical backward pass, so automatic differentiation acts only on . The classical parameters are updated with Adam using learning rate , and the norm of the classical gradient is clipped to 1.0 before each update.
Both the SPSA estimator and the Adam gradient are constructed from the same two quantum evaluations at and . The complete training procedure is summarized below.
Algorithm: Finite-shot hybrid SPSA-Adam training
Require: Training set
Require: Initial quantum parameters
Require: Initial classical head parameters
Require: SPSA constants
Require: Adam learning rate
for do
Shuffle the training windows
for each mini-batch do
Sample
Evaluate for all
Evaluate for all
Compute and using Eq. (96)
Detach the quantum features from the PyTorch graph
Compute by automatic differentiation
Clip to 1.0
Update from using Adam
Compute using Eq. (97)
Increment
end for
if , , or is a multiple of 5 then
Evaluate the center-point validation loss
if the validation loss has improved then
Save the current model as the best checkpoint
end if
end if
Save the resumable training checkpoint
end for
Restore the checkpoint with the lowest validation loss
Evaluate the restored model once on the test set
Finite-shot quantum evaluations are distributed across worker processes. Each worker constructs and retains its own PennyLane QNode and Qiskit Aer backend. For a mini batch of 16 training windows, the positive and negative SPSA perturbations require quantum circuit evaluations. These evaluations are submitted concurrently to the 32 CPU workers. The transpiler seed is identical across workers, ensuring that all workers use the same compiled logical circuit. In contrast, the simulator seed assigned to worker is , 0, , , which provides independent finite-shot and noise realizations across workers. With 350 training windows and mini batch size 16, each epoch contains SPSA updates. Because each update evaluates two perturbed quantum circuits, training requires 700 quantum evaluations per epoch and 70 000 training evaluations over 100 epochs for each independent run.
| Category | Parameter | Value or specification |
| Data | Time-series length | 539 monthly observations |
| Data | Lag-window length | |
| Data | Training windows | 350 |
| Data | Validation windows | 70 |
| Data | Test windows | 105 |
| Data | Target range used for scaling | [0, 350] mm |
| Data | Scaled target range | [, 1] |
| Data | Forecast horizon | One month |
| Quantum model | Number of logical qubits | 14 |
| Quantum model | Reuploading depths | |
| Quantum model | Ansatz layers per reupload | 1 |
| Quantum model | Single-qubit ansatz | on every qubit |
| Quantum model | Entangling pattern | Nearest-neighbor CNOT chain with closing interaction CNOT |
| Quantum model | Measurement | Individual Pauli-Z expectation values on all 14 qubits |
| Quantum model | Classical head | Linear(14, 1) followed by tanh |
| Quantum model | Variational initialization | Independent zero-centered initialization with scale 0.01 |
| Quantum model | Learned-encoding initialization | Raw strength, polar-shift, and azimuth-shift parameters initialized to zero |
| Quantum model | Quantum parameters | for fixed encoding, for learned polar, and for learned polar plus azimuth |
| Quantum model | Classical parameters | 15 |
| Noisy simulation | Backend mode | Qiskit Aer finite-shot noisy simulation |
| Noisy simulation | Noise source | IBM FakeAachen |
| Noisy simulation | Physical backend size | 156 qubits |
| Noisy simulation | Physical layout | [33, 32, 31, 18, 11, 10, 9, 8, 7, 17, 27, 28, 29, 38] |
| Noisy simulation | Routing method | SABRE |
| Noisy simulation | Transpiler optimization level | 1 |
| Noisy simulation | Shots | 512 per expectation-value estimate |
| Noisy simulation | Aer method | automatic |
| Noisy simulation | Simulator truncation | Enabled |
| Training | Independent seeds | 42 |
| Training | Epochs | 100 |
| Training | Mini-batch size | 16 |
| Training | Updates per epoch | 22 |
| Training | SPSA updates per run | 2200 |
| Training | Loss | Mean-squared error |
| Training | Quantum optimizer | SPSA |
| Training | SPSA coefficient | 0.40 |
| Training | SPSA perturbation coefficient | 0.05 |
| Training | SPSA stability constant | 50 |
| Training | SPSA decay exponent | 0.602 |
| Training | SPSA perturbation exponent | 0.101 |
| Training | Classical optimizer | Adam |
| Training | Adam learning rate | 0.005 |
| Training | Classical gradient clipping | Maximum Euclidean norm 1.0 |
| Training | Validation schedule | Epoch 1, every fifth epoch, and the final epoch |
| Training | Validation repeats | 1 |
| Training | Validation batch size | 32 |
| Training | Checkpoint interval | Every epoch |
| Training | Model selection | Lowest validation mean-squared error |
Table I. Noisy Simulation Details
Forecasting metrics
Forecasting performance was evaluated on the test set using four complementary metrics. Let and denote the observed and predicted precipitation, respectively, for , where . The test root-mean-square error is defined as
RMSE was computed after restoring model predictions to the original precipitation scale and is therefore reported in millimeters.
To quantify similarity in frequency domain structure, the observed and predicted test sequences were first centered independently by subtracting their respective means,
Their discrete Fourier transforms were computed as
The corresponding Fourier power spectra are
The Fourier cosine similarity was evaluated over the non-zero positive frequency bins ,
Since the Fourier power is nonnegative, , with indicating identical normalized spectral shapes. This quantity therefore measures whether the forecast reproduces the relative distribution of power across temporal frequencies. Because it is a cosine similarity, it is insensitive to an overall multiplicative rescaling of the predicted power spectrum. This means that high spectral similarity does not by itself imply agreement in forecast amplitude.
Temporal alignment between the observed and predicted sequences was quantified using the Pearson correlation coefficient,
The coefficient satisfies , with corresponding to perfect positive linear alignment between the observed and predicted temporal fluctuations. Because the means and overall scales of the two sequences are removed in the correlation calculation, primarily measures whether the forecast tracks the temporal variation of the observations rather than their absolute magnitude.
Finally, recovery of the observed forecast amplitude was quantified using the amplitude variance ratio,
where the variances were evaluated over the complete test interval using and analogously for . The ideal value is . Values below 1 indicate suppression of the observed variability and therefore forecasts with reduced amplitude, whereas values above unity indicate variability larger than that of the observed precipitation series.
These four metrics probe distinct aspects of forecast quality: Test RMSE measures absolute pointwise error, measures normalized frequency-domain structure, measures temporal alignment, and measures recovery of the observed variation in amplitude.
Classical forecasting baselines
To compare the performance of our quantum models, we evaluated three complementary classical baselines: random forest (RF), autoregressive integrated moving average (ARIMA), and long short-term memory (LSTM). The classical models were evaluated over the same chronological training, validation, and test splits used for the quantum models. No test observations were used for hyperparameter or model selection. For the random forest and LSTM models, the precipitation series was represented using the same supervised lag window construction as the quantum models. Each input contained the preceding monthly precipitation observations,
with the subsequent observation used as the one-month-ahead target. This resulted in 350 training, 70 validation, and 105 test forecasting examples.
Precipitation values were transformed to the interval according to
where is measured in millimeters. Predictions were transformed back to physical units using . Random forest and LSTM are stochastic models and were evaluated over five independent runs using random seeds 42, 43, 44, 45, and 46. The source of stochasticity is model-dependent: for the LSTM, the random state determines the initialization of the trainable parameters and the shuffled mini-batch sequence during training. For the random forest, it determines the stochastic bootstrap of the tree ensemble. The ARIMA model is deterministic for a fixed model specification and was consequently evaluated using a single fit. All classical models were evaluated using the same set of forecasting metrics used for the quantum models.
Random forest
The random-forest baseline was implemented using the RandomForestRegressor in scikit-learn. Each 14-month lag window was supplied to the model as a 14-dimensional feature vector. Individual regression trees used the squared-error criterion and bootstrap sampling. Model hyperparameters were selected using a grid search over the validation set, with the parameter search including
where denotes the number of trees, the maximum tree depth, the minimum number of samples in a terminal leaf, and the fraction of input features available when determining a split. The complete grid therefore contained 576 hyperparameter configurations. Each configuration was trained independently for the five random states 42, . . . ,46. The selected configuration, according to the mean validation mean-squared error, was
LSTM
Each 14 month input window was represented as a sequence of length 14 with one scalar feature per time step, so that the input to the recurrent network had shape 14 × 1. The input dimension and hidden dimension were fixed to , , while the number of stacked recurrent layers was varied over . All LSTMs were unidirectional and used no dropout. After processing the complete 14 month sequence, the final hidden state was passed to a linear output layer, followed by a tanh activation to produce the forecast in the scaled target space. The models were trained by minimizing mean squared error using Adam with learning rate . For every depth , five independent runs were performed using random states . The best model was chosen using minimum validation loss during training.
| Depth | LSTM | Fixed Seasonal | Learned Polar | Learned Polar + Azimuthal |
| 1 | 76 | 57 | 81 | 93 |
| 2 | 172 | 99 | 147 | 171 |
| 3 | 268 | 141 | 213 | 249 |
| 4 | 364 | 183 | 279 | 327 |
| 5 | 460 | 225 | 345 | 405 |
| 6 | 556 | 267 | 411 | 483 |
Table II. Total trainable parameter counts for the LSTM and the three seasonal encoding models across model depth. The LSTM hidden dimension was fixed at . LSTM depth and quantum reuploading depth are not architecturally equivalent and are aligned here only for a scaling comparison of parameter counts.
The hidden size was intentionally chosen to provide a comparable recurrent baseline whose parameter count increases with recurrent depth on a scale comparable to the quantum models.
ARIMA
The ARIMA baseline was applied directly to the chronologically ordered precipitation series rather than to fixed 14 month input windows. Model order was selected using the training and validation periods while preserving their temporal ordering. We considered the grid
Stationarity and invertibility constraints were enforced during fitting. Models were estimated using the state space implementation in statsmodels, with a maximum of 500 optimizer iterations. For each model in the grid search, the model was initially fit using the training portion of the raw precipitation record, comprising observations with indices . Validation performance was then evaluated over the subsequent 70 observations using rolling one-step-ahead forecasts. After each forecast, the corresponding observed precipitation value was incorporated into the ARIMA state before forecasting the next month, while the fitted model coefficients remained fixed. Models were ranked according to their validation RMSE.
This procedure selected ARIMA(7, 0, 6). After model-order selection, the selected ARIMA specification was refit using all 434 observations preceding the test interval. Test predictions were then generated sequentially over indices 434, , 538 using the same rolling one-step-ahead procedure. Following each test forecast, the corresponding observed precipitation value was incorporated into the model state without re-estimating the ARIMA coefficients.
Consequently, the ARIMA baseline differs from the fixed-window models in that each prediction can use the complete observed history available up to the forecast time, rather than only the preceding 14 months. No seasonal ARIMA terms were included.
| Model | Parameter | Value |
| Random forest | Trees | 500 |
| Maximum depth | 5 | |
| Minimum samples per leaf | 2 | |
| Maximum feature fraction | 1.0 | |
| Split criterion | Squared error | |
| Bootstrap sampling | Yes | |
| Independent runs | 5 | |
| ARIMA | Selected order | (7, 0, 6) |
| Candidate orders | 182 | |
| Seasonal terms | None | |
| Forecasting protocol | Rolling one-step | |
| Final fit observations | 434 | |
| LSTM | Input sequence | |
| Hidden dimension | 3 | |
| Recurrent depth | ||
| Optimizer | Adam | |
| Learning rate | 0.005 | |
| Batch size | 16 | |
| Epochs | 100 | |
| Gradient clipping | 1.0 | |
| Independent runs | 5 |
Table III. Summary of the classical baseline configurations.
References
- [1]M. C. Hansen, P. V. Potapov, R. Moore, M. Hancher, S. a. Turubanova, A. Tyukavina, D. Thau, S. V. Stehman, S. J. Goetz, T. R. Loveland, A. Kommareddy, A. Egorov, L. Chini, C. O. Justice, and J. R. G. Townshend, High-resolution global maps of 21st-century forest cover change., Science 342, 850 (2013).
- [2]Z. Wan, P. Wang, and X. Li, Using MODIS Land Surface Temperature and Normalized Difference Vegetation Index products for monitoring drought in the southern Great Plains, USA, Int. J. Remote Sens. 25, 61 (2004).DOI
- [3]R. Dubayah, J. B. Blair, S. Goetz, L. Fatoyinbo, M. Hansen, S. Healey, M. Hofton, G. Hurtt, J. Kellner, and S. Luthcke, The global ecosystem dynamics investigation: High-resolution laser ranging of the Earth’s forests and topography, Sci. Remote Sens. 1, 100002 (2020).DOI
- [4]A. D. Adebayo and C. Nakalembe, Sub-seasonal forecasting of cropland productivity anomalies using satellite soil moisture in water-limited environments, Remote Sens. Environ. 347, 115645 (2026).DOI
- [5]S. Shukla, G. Husak, W. Turner, F. Davenport, C. Funk, L. Harrison, and N. Krell, A slow rainy season onset is a reliable harbinger of drought in most food insecure regions in Sub-Saharan Africa, PLoS ONE 16, 1 (2021).DOI
- [6]J. Muñoz-Sabater, E. Dutra, A. Agustí-Panareda, C. Albergel, G. Arduini, G. Balsamo, S. Boussetta, M. Choulga, S. Harrigan, H. Hersbach, B. Martens, D. G. Miralles, M. Piles, N. J. Rodríguez-Fernández, E. Zsoter, C. Buontempo, and J.-N. Thépaut, ERA5-Land: A state-of-the-art global reanalysis dataset for land applications, Earth Syst. Sci. Data 13, 4349 (2021).
- [7]M. Schuld and N. Killoran, Quantum machine learning in feature Hilbert spaces, Phys. Rev. Lett. 122, 040504 (2019).DOI
- [8]M. Benedetti, E. Lloyd, S. Sack, and M. Fiorentini, Parameterized quantum circuits as machine learning models, Quantum Sci. Technol. 4, 043001 (2019).DOI
- [9]M. Schuld and N. Killoran, Is quantum advantage the right goal for quantum machine learning?, PRX Quantum 3, 030101 (2022).DOI
- [10]N. Schetakis, D. Aghamalyan, P. Griffin, and M. Boguslavsky, Review of some existing QML frameworks and novel hybrid classical-quantum neural networks realising binary classification for the noisy datasets, Sci. Rep. 12, 11927 (2022).DOI
- [11]S. H. Kim, J. Mei, C. Girotto, M. Yamada, and M. Roetteler, Quantum large language model fine-tuning (2025), arXiv:2504.08732 [quant-ph].arxiv.org/abs/2504.08732
- [12]J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe, and S. Lloyd, Quantum machine learning, Nature 549, 195 (2017).DOI
- [13]H.-Y. Huang, M. Broughton, M. Mohseni, R. Babbush, S. Boixo, H. Neven, and J. R. McClean, Power of data in quantum machine learning, Nat. Commun. 12, 2631 (2021).
- [14]W. Guan, G. Perdue, A. Pesah, M. Schuld, K. Terashi, S. Vallecorsa, and J.-R. Vlimant, Quantum machine learning in high energy physics, Mach. Learn.: Sci. Technol. 2, 011003 (2021).DOI
- [15]M. Larocca, F. Sauvage, F. M. Sbahi, G. Verdon, P. J. Coles, and M. Cerezo, Group-invariant quantum machine learning, PRX Quantum 3, 030341 (2022).DOI
- [16]M. C. Caro, H.-Y. Huang, M. Cerezo, K. Sharma, A. Sornborger, L. Cincio, and P. J. Coles, Generalization in quantum machine learning from few training data, Nat. Commun. 13, 4919 (2022).DOI
- [17]P. Bermejo, P. Braccia, M. S. Rudolph, Z. Holmes, L. Cincio, and M. Cerezo, Quantum convolutional neural networks are effectively classically simulable, PRX Quantum 7, 020304 (2026).arxiv.org/abs/2408.12739
- [18]V. Havlíček, A. D. Córcoles, K. Temme, A. W. Harrow, A. Kandala, J. M. Chow, and J. M. Gambetta, Supervised learning with quantum-enhanced feature spaces, Nature 567, 209–212 (2019).DOI
- [19]M. Cerezo, G. Verdon, H.-Y. Huang, L. Cincio, and P. J. Coles, Challenges and opportunities in quantum machine learning, Nat. Comput. Sci. 2, 567–576 (2022).DOI
- [20]N. Schetakis, P. Bonfini, N. Alisoltani, K. Blazakis, S. I. Tsintzos, A. Askitopoulos, D. Aghamalyan, P. Fafoutellis, and E. I. Vlahogianni, Quantum neural networks with data re-uploading for urban traffic time series forecasting, Sci. Rep. 15, 19400 (2025).DOI
- [21]T. Hubregtsen, D. Wierichs, E. Gil-Fuster, P.-J. H. S. Derks, P. K. Faehrmann, and J. J. Meyer, Training quantum embedding kernels on near-term quantum computers, Phys. Rev. A 106, 042431 (2022).DOI
- [22]J. Jäger, P. Elsässer, and E. Torabian, Quantum feature-map learning with reduced resource overhead, Phys. Rev. Res. 8, 023247 (2026).DOI
- [23]M. Schuld, R. Sweke, and J. J. Meyer, The effect of data encoding on the expressive power of variational quantum machine learning models, Phys. Rev. A 103, 032430 (2021).DOI
- [24]A. Pérez-Salinas, D. López-Núñez, A. García-Sáez, P. Forn-Díaz, and J. I. Latorre, One qubit as a universal approximant, Phys. Rev. A 104, 012405 (2021).
- [25]A. Pérez-Salinas, A. Cervera-Lierta, E. Gil-Fuster, and J. I. Latorre, Data re-uploading for a universal quantum classifier, Quantum 4, 226 (2020).
- [26]J. R. McClean, S. Boixo, V. N. Smelyanskiy, R. Babbush, and H. Neven, Barren plateaus in quantum neural network training landscapes, Nat. Commun. 9, 4812 (2018).
- [27]M. Cerezo, A. Sone, T. Volkovich, L. Cincio, and P. J. Coles, Cost function dependent barren plateaus in shallow parametrized quantum circuits, Nat. Commun. 12, 1791 (2021).DOI
- [28]S. Sim, P. D. Johnson, and A. Aspuru-Guzik, Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms, Adv. Quantum Technol. 2, 1900070 (2019).DOI
- [29]Y. Du, T. Huang, S. You, M.-H. Hsieh, and D. Tao, Quantum circuit architecture search for variational quantum algorithms, npj Quantum Inf. 8, 62 (2022).DOI
- [30]S. Y.-C. Chen, S. Yoo, and Y.-L. L. Fang, Quantum long short-term memory (2020), arXiv:2009.01783 [quant-ph].arxiv.org/abs/2009.01783
- [31]S. Z. Khan, N. Muzammil, S. Ghafoor, H. Khan, S. M. H. Zaidi, A. J. Aljohani, and I. Aziz, Quantum long short-term memory (QLSTM) vs. classical LSTM in time series forecasting: a comparative study in solar power forecasting, Front. Phys. 12, 1439180 (2024).DOI
- [32]K.-H. Moon, S.-G. Jeong, and W.-J. Hwang, QSegRNN: Quantum segment recurrent neural network for time series forecasting, EPJ Quantum Technol. 12, 32 (2025).
- [33]S. Cao, W. Zhang, J. Tilly, A. Agarwal, M. Bakr, G. Campanaro, S. D Facciati, J. Wills, B. Shteynas, V. Chambarama, P. Leek, and I. Rungger, Encoding optimization for quantum machine learning demonstrated on a superconducting transmon qutrit, Quantum Sci. Technol. 9, 045037 (2024).arxiv.org/abs/2309.13036
- [34]Z. Yu, Q. Chen, Y. Jiao, Y. Li, X. Lu, X. Wang, and J. Z. Yang, Non-asymptotic approximation error bounds of parameterized quantum circuits, in Advances in Neural Information Processing Systems, Vol. 37, edited by A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang (Curran Associates, Inc., 2024) pp. 99089–99127.arxiv.org/abs/2310.07528
- [35]M. T. West, J. Heredge, M. Sevior, and M. Usman, Provably trainable rotationally equivariant quantum machine learning, PRX Quantum 5, 030202 (2024).DOI
- [36]Z. Li, L. Nagano, and K. Terashi, Enforcing exact permutation and rotational symmetries in the application of quantum neural networks on point cloud datasets, Phys. Rev. Res. 6, 043028 (2024).arxiv.org/abs/2405.11150
- [37]J. Heredge, C. Hill, L. Hollenberg, and M. Sevior, Permutation invariant encodings for quantum machine learning with point cloud data, Quantum Mach. Intell. 6, 25 (2024).DOI
- [38]S. L. Braunstein and C. M. Caves, Statistical distance and the geometry of quantum states, Phys. Rev. Lett. 72, 3439 (1994).pubmed.ncbi.nlm.nih.gov/10056200
- [39]J. Stokes, J. Izaac, K. Killoran, and G. Carleo, Quantum natural gradient, Quantum 4, 269 (2020).DOI
- [40]D. Spehner, Bures geodesics and quantum metrology, Quantum 9, 1715 (2025).DOI
- [41]J. P. Provost and G. Vallee, Riemannian structure on manifolds of quantum states, Commun. Math. Phys. 76, 289 (1980).DOI
- [42]G. Box and G. Jenkins, Time Series Analysis: Forecasting and Control (Holden-Day, 1970).
- [43]L. Breiman, Random forests, Mach. Learn. 45, 5 (2001).
- [44]S. Hochreiter and J. Schmidhuber, Long short-term memory, Neural Comput. 9, 1735 (1997).
- [45]T. Draper and S. Kutin, 〈qpic〉: Quantum circuit diagrams in LaTeX. (2016), accessed October 2026.
- [46]N. L. Wach, M. S. Rudolph, F. Jendrejewski, and S. Schmitt, Data re-uploading with a single qudit, X. Wang, H.-X. Tao, and R.-B. Wu, Predictive performance of deep quantum data re-uploading models (2025), arXiv:2505.20337 [quant-ph].
- [48]A. Barthe and A. Pérez-Salinas, Gradients and frequency profiles of quantum re-uploading models, Quantum 8, 1523 (2024).DOI
- [49]C. Nakalembe, Characterizing agricultural drought in the Karamoja subregion of Uganda with meteorological and satellite-based indices, Nat. Hazards 91, 837 (2018).DOI
- [50]V. Bergholm, J. Izaac, M. S. Schuld, C. Gogolin, S. Ahmed, V. Ajith, M. S. Alam, G. Alonso-Linaje, B. AkashNarayanan, A. Asadi, J. M. Arrazola, U. Azad, S. Ban n ing, C. Blank, T. R. Bromley, B. A. Cordier, J. Ceroni, A. Delgado, O. D. Matteo, A. Dusko, T. Garg, D. Guala, A. Hayes, R. Hill, A. Ijaz, T. Isacsson, D. Ittah, S. Jahangiri, P. Jain, E. Jiang, A. Khandelwal, K. Kottmann, R. A. Lang, C. Lee, T. Loke, A. Lowe, K. McKiernan, J. J. Meyer, J. A. Montañez-Barrera, R. Moyard, Z. Niu, L. J. O’Riordan, S. Oud, A. Panigrahi, C.-Y. Park, D. Polatajko, N. Quesada, C. Roberts, N. Sá, I. Schoch, B. Shi, S. Shu, S. Sim, A. Singh, I. Strandberg, J. Soni, A. Száva, S. Thabet, R. A. Vargas-Hernández, T. Vincent, N. Vitucci, M. Weber, D. Wierichs, R. Wiersema, M. Willmann, V. Wong, S. Zhang, and N. Killoran, PennyLane: Automatic differentiation of hybrid quantum-classical computations (2022), arXiv:1811.04968 [quant-ph].
- [51]A. Paszke, S. Gross, F. Massa, A. Ler er, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, PyTorch: An imperative style, high-performance deep learning library, in Advances in Neural Information Processing Systems, Vol. 32, edited by H. Wallach, H. Larochelle, A. Beygelzimer, F. d’Alché-Buc, E. Fox, and R. Garnett (Curran Associates, Inc., 2019).arxiv.org/abs/1912.01703
- [52]K. Życzkowski and H.-J. Sommers, Average fidelity between random quantum states, Phys. Rev. A 71, 032313 (2005).DOI
- [53]S. Sim, P. D. Johnson, and A. Aspuru-Guzik, Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms, Adv. Quantum Technol. 2, 12 (2019).DOI
- [54]A. Javadi-Abhari, M. Treinish, K. Krsulich, C. J. Wood, J. Lishman, J. Gacon, S. Martiel, P. D. Nation, L. S. Bishop, A. W. Cross, B. R. Johnson, and J. M. Gambetta, Quantum computing with Qiskit (2024), arXiv:2405.08810 [quant-ph].
- [55]J. Spall, Multivariate stochastic approximation using a simultaneous perturbation gradient approximation, IEEE Trans. Autom. Control 37, 332 (1992).DOI
- [56]D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, in International Conference on Learning Representations (2015).arxiv.org/abs/1412.6980
- [57]J. Spall, Implementation of the simultaneous perturbation algorithm for stochastic optimization, IEEE Trans. Aerosp. Electron. Syst. 34, 817 (1998).DOI
- [58]K. Temme, S. Bravyi, and J. M. Gambetta, Error mitigation for short-depth quantum circuits, Phys. Rev. Lett. 119, 180509 (2017).DOI
- [59]Y. Li and S. C. Benjamin, Efficient variational quantum simulator incorporating active error minimization, Phys. Rev X 7, 021050 (2017).DOI
- [60]Z. Cai, R. Babbu sh, S. C. Benjamin, S. Endo, W. J. Huggins, Y. Li, J. R. McClean, and T. E. O’Brien, Quantum error mitigation, Rev. Mod. Phys. 95, 045005 (2023).DOI
- [61]C. Sharma and S. K. Sood, Variational quantum reservoir networks for multivariate time-series prediction, Nonlinear Dyn. 114, 818 (2026).DOI
- [62]S. Ranilla-Cortina, D. A. Aranda, J. Ballesteros, J. Bonilla, N. Monr io, and E. F. Combarro, Quantum-enhanced architectures for multivariate time-series forecasting, J. Supercomput. 82, 155 (2026).
- [63]M. R. Laskar and R. Goel, Shallow entangled circuits for quantum time series prediction on IBM devices, Sci. Rep. 15, 43727 (2025).DOI
- [64]I. Panadero, Y. Ban, H. Espinós, R. Puebla, J. Casanova, and E. Torrontegui, Regressions on quantum neural networks at maximal expressivity, Sci. Rep. 14, 31669 (2024).DOI
- [65]A. Kutvonen, K. Fujii, and T. Sagawa, Optimizing a quantum reservoir computer for time series prediction, Sci. Rep. 10, 14687 (2020).DOI
- [66]K. Kobayashi, K. Fujii, and N. Yamamoto, Feedback-driven quantum reservoir computing for time-series analysis, PRX Quantum 5, 040325 (2024).DOI
- [67]Y. Hou, J. Hua, Z. Wu, W. Xia, Y. Chen, X. Li, Z. Li, X. Peng, and J. Du, High-accuracy temporal prediction via experimental quantum reservoir computing in correlated spins, Phys. Rev. Lett. 136, 120602 (2026).DOI
- [68]O. Ahmed, F. Tennie, and L. Magri, Optimal training of finitely sampled quantum reservoir computers for forecasting of chaotic dynamics, Quantum Mach. Intell. 7, 31 (2025).arxiv.org/abs/2409.01394
- [69]A. Kandala, A. Mezzacapo, K. Temme, M. Takita, M. Brink, J. M. Chow, and J. M. Gambetta, Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets, Nature 549, 242 (2017).DOI
- [70]L. Candelori, S. Majumder, A. Mezzacapo, J. R. Moreno, K. Musaeilan, S. Nagarajan, S. Pinnamaneni, K. Sharma, and D. Villani, Shallow-circuit supervised learning on a quantum processor (2026), arXiv:2601.03235 [quant-ph].arxiv.org/abs/2601.03235
- [71]N. Mathur, P. K. Barkoutsos, M. Yamada, M. Roetteler, and I. Kerenidis, Scalable on-hardware training of quantum neural networks and application to clinical data imputation (2026), arXiv:2606.03517 [quant-ph].arxiv.org/abs/2606.03517
- [72]M. Kornjača, H.-Y. Hu, C. Zhao, J. Wurtz, P. Weinberg, M. Hamdan, A. Zhdanov, S. H. Cantu, H. Zhou, R. A. Bravo, K. Bagnall, J. I. Basham, J. Campo, A. Choukri, R. DeAngelo, P. Frederick, D. Haines, J. Hammett, N. Hsu, M.-G. Hu, F. Huber, P. N. Jepsen, N. Jia, T. Karol yshyn, M. Kwon, J. Long, J. Lopatin, A. Lukin, T. Macri, O. Marković, L. A. Martínez-Martínez, X. Meng, E. Ostroumov, D. Paquette, J. Robinson, P. S. Rodriguez, A. Singh, N. Sinha, H. Thoreen, N. Wan, D. Waxman-Lenz, T. Wong, K.-H. Wu, P. L. S. Lopes, Y. Boger, N. Gemelke, T. Kitagawa, A. Keesling, X. Gao, A. Bylinskii, S. F. Yelin, F. Liu, and S.-T. Wang, Large-scale quantum reservoir learning with an analog quantum computer (2024), arXiv:2407.02553 [quant-ph].arxiv.org/abs/2407.02553
- [73]O. Knitter, J. Mei, S. H. Kim, C. Chen, M. Yamada, and M. Roetteler, Neural fourier surrogates for data reuploading quantum neural networks (2026), arXiv:2610.00841 [quant-ph].arxiv.org/abs/2610.00841
- [74]D. Tripathy, R. Robertson, J. Stevens, C. L. Nakalembe, and S. Deffner, GitHub Repo: Quantum Learning for Geospatial Time Series (2026), accessed October 2026.
