Machine Learning · arXiv:2611.16322 v1 · submitted 12 Nov 2026 · 50 references
Climate Temporal Temperature Prediction via an Adaptive Stacked Bidirectional Residual Mamba Network
The paper says
“Accurate temperatures forecasting relies on traditional meteorological parameters that are essential for monitoring weather informatics and guiding forecasting efforts.”
more of the abstract
This study presents Deep DualMamba, a novel deep learning framework for temporal temperature prediction, built upon an enhanced variant of the recently proposed Mamba network. Unlike conventional Transformer-based architectures, which dominate foundation models but suffer from computational inefficiencies on long sequences, Deep DualMamba leverages selective structured state space models (SSMs) to achieve both scalability and performance. We identify a core limitation of prior subquadratic-time models-namely, their inability to perform long-term and robust forecasting and introduce two key innovations. First, we propose an adaptive bidirectional Mamba as encoders to learn complex and efficient features. Second, we develop a hardware-aware, parallel recurrent algorithm to compensate for the loss of convolutional efficiency, ensuring practical viability at scale. Last, the Deep DualMamba's approximation ability and convergence is theoretical analyzed. These design choices culminate in a simplified, attention- and MLP-free neural architecture that exhibits linear complexity with sequence length and significantly improved inference throughput. To demonstrate its applicability in climate informatics, we implement a full forecasting pipeline using historical meteorological data from UK monitoring stations.
from the abstract
Pith says
Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded · not checked by a person
It can be wrong. Challenge this review or reply to it.
Does not hold up as stated. The paper's central empirical claim is contradicted by its own Table IV, and the theoretical analysis is generic and unverified. The bidirectional Mamba idea is not new. This is not ready for peer review. This line is wrong
6 major objections · 6 minor
How often objections from reviews like this one are right: not yet measured
Not checked: figures, code, what the 50 references say.
The paper says, at Section V.C, Table IV, contributions bullet (p. 3)
The review did not quote this passage.
Pith says: Objection 1 of 6 · major
The central empirical claim is contradicted by the paper's own results. In Table IV, the test RMSE of DualMamba-4 is 0.0292 versus 0.0278 for Mamba-4, and DualMamba-3 gives 0.0314 versus 0.0308 for Mamba-3; the only metric on which DualMamba-4 beats Mamba-4 is training RMSE (0.0257 vs 0.0281), which is irrelevant to generalization.
more of objection 1
The statement in Section V.C that "compared to villa-Mamba, our proposed DualMamba also achieves better forecasting performance" is therefore not supported by the table it cites. The contribution bullet claiming "14.2% lower RMSE" cannot be traced to any entry of Table IV, and the abstract's "32%" error-reduction figure is inconsistent with the 14.2% figure. These numbers must be re-derived from the reported tables or the claims must be corrected before any accuracy statement can be evaluated.
This review says the paper's mathematics is wrong. Pith did not check that against the paper's source.
The paper says, at Table IV and Table V
The review did not quote this passage.
Pith says: Objection 2 of 6 · major
Table IV shows data-integrity problems. First, the GRU-3 row is a verbatim duplicate of the MLP-3 row (MSE 0.0487/0.0507/0.0579, RMSE 0.2208/0.2251/0.2406, MAE 0.1672/0.0738/0.0076, MAPE 27.96/28.52/28.91), which is implausible for two different architectures. Second, the MSE and RMSE columns are mutually inconsistent across rows: for MLP-4 test, MSE is 0.0742 while RMSE is 0.0563, yet sqrt(0.0742) = 0.2724; for Mamba-4 test, RMSE 0.0278 matches sqrt(0.000777), which implies the MSE column is scaled by 10^-2 in some rows but not in others.
more of objection 2
Third, Table V reports an RMSE of 0.3456 for Radcliffe with L=1000, T=300, whereas Table IV, which covers the same stations and the same horizon configuration, reports DualMamba RMSE values of 0.0257-0.0292; the factor-of-about-13 gap is never explained. No standard deviations, confidence intervals, or multiple-seed results are reported anywhere.
The paper says, at Section IV.A, Theorem 1, Eq. (14)
The review did not quote this passage.
Pith says: Objection 3 of 6 · major
The universal approximation proof begins by asserting that the Mamba block implements a continuous kernel operator (Ku)(t) = integral K(t,s;theta)u(s)ds. This assertion is not satisfied by the implemented architecture: in Algorithm 1, the discretized state parameters are input-dependent (Delta, B, and C are computed from x'), so the map u -> y is nonlinear and context-dependent and cannot be written as a fixed Volterra kernel acting linearly on u.
more of objection 3
The cited universal approximation result for Volterra operators [41] therefore does not apply to the discrete, selective model that is actually trained. Steps 2 and 3 of the proof (composition density and residual flow-map approximation) are likewise asserted without verifying the hypotheses of the cited deep-operator and neural-ODE results for this architecture.
The paper says, at Section IV.B, Theorem 2, Assumption 1, Eqs. (18)-(21)
The review did not quote this passage.
Pith says: Objection 4 of 6 · major
The linear convergence rate in Eq. (18) depends on the Polyak-Lojasiewicz condition in Assumption 1. The paper itself limits this assumption in Remark 1 to a claim that the gating mechanisms "ensure the PL condition holds locally," but no argument is given that the training trajectory remains in such a basin, so the rate is not established for the actual optimization run.
more of objection 4
The contractivity bound ||A_bar||_2 <= e^{-gamma Delta} < 1 in Eq. (19) concerns only the discretized state-transition matrix and does not imply the full-layer Jacobian bound in Eq. (21), since the full layer includes input-dependent projections and the SiLU nonlinearity. In addition, the model is trained with AdamW per Section V.B while the proof's Step 3 invokes an Adam convergence framework [44]; no argument connects that framework to AdamW under Assumption 1.
The paper says, at Section IV.C, Theorem 3, Eqs. (23)-(29)
The review did not quote this passage.
Pith says: Objection 5 of 6 · major
The bound N_DualMamba = O(kappa^{L+T} log(1/epsilon)) in Eq. (23) decreases as the input and output dimensions L and T grow when kappa < 1, which is not a plausible scaling for approximating a family of maps from R^L to R^T; the "compression factor" kappa is never defined.
more of objection 5
The supporting claims-the information-preservation inequality in Eq. (26) and the tensor-train representation in Eq. (28) with bond dimension alpha_t <= D-are asserted without proof, and the error bound e^{-cD} in Eq. (29) is not connected to the stated rate. The comparison also places the output dimension T in the MLP rate's exponent N^{-r/(L+T)} in Eq. (24), which inflates the MLP's difficulty, since the output dimension multiplies the number of output units rather than entering the input-dimension curse of dimensionality. Consequently, the limit claim lim_{epsilon->0} N_MLP/N_DualMamba = infinity in Section VI is not established.
The paper says, at Section V.A-B and Section V.C
The review did not quote this passage.
Pith says: Objection 6 of 6 · major
The evaluation is too thin to support the paper's comparative claims. The baselines omit the current standard long-term forecasting methods (e.g., PatchTST, iTransformer, DLinear, TimesNet) that the paper itself acknowledges in its related-work discussion; all results come from single runs with no error bars or significance tests; and the claimed 5x inference speedup and the 1.1x-of-MLP latency statement in Section V.B are not backed by any timing measurements.
more of objection 6
The dataset description is also internally inconsistent: Section V.A describes a 1 km-resolution gridded monthly CET product over 1961-2024, while Table I lists station series beginning in 1815 with tens of thousands of samples, and the use of 1000-step histories with 300-step prediction horizons is never reconciled with monthly sampling.
6 minor objections
The paper says, at Section III.B
Pith says: minor objection 1 of 6
The text contains a dangling reference: "the description in Figure??" was never filled in with a figure number.
The paper says, at Figures 5 and 6
Pith says: minor objection 2 of 6
Figure 5's caption names Radcliffe, Rothamsted, Ross on Wye, and Stonyhurst, but the figure shows three panels, while Figure 6 shows four panels under a caption ending in "Respectively."
show 4 more
The paper says, at Throughout
Pith says: minor objection 3 of 6
Terminology is inconsistent: "villa-Mamba" and "Mamba-villa" in Section V.C presumably mean vanilla Mamba; "preceding horizon" is used where "prediction horizon" is meant; and the abstract's "theoretical analyzed" should read "theoretically analyzed."
The paper says, at Table III and Section V.B
Pith says: minor objection 4 of 6
Table III lists hidden widths of 60 for the Mamba and baseline variants, while Section V.B states that DualMamba uses hidden layers of 64 neurons; the exact configuration used for the reported runs should be stated.
The paper says, at Eq. (35)
Pith says: minor objection 5 of 6
MAPE is defined with the observed value in the denominator; near-zero temperature values make this metric unstable, and the paper should state how such observations were handled when reporting MAPE in Table IV.
The paper says, at Section I
Pith says: minor objection 6 of 6
The claim that this work is "the first demonstration of Mamba's viability in real-world climate prediction" is difficult to reconcile with refs. [27]-[32], which the paper itself cites for Mamba applications to weather and traffic forecasting.
What would settle it
Recompute the test-set RMSE for DualMamba-4 and Mamba-4 from Table IV using the original data and code. If the values are correct, then DualMamba does not outperform standard Mamba, and the central claim of superior accuracy is false. Additionally, compute 95% confidence intervals via bootstrapping (1000 resamples) for each model's test RMSE to assess whether any differences are statistically significant. Report the exact baseline used for the claimed 14.2% improvement and verify the calculation.
from the skeptic's reading
How the review went
4 readings by deepseek-v4-flash · 13 Nov 2026
- Reader does not hold up
- Skeptic agrees
- Editor wrote the verdict above
- Referee reject: 6 major objections, 6 minor
Not run on this paper: the simulated authors' defence.
Pith did not check this review's objections against the paper.
The review in full
The review in brief, machine-written
Yongxiang Lei's paper applies a bidirectional Mamba to UK temperature data. The reader's take is accurate and I largely agree. Let me be direct.
What is actually new: very little. Bidirectional Mamba for time series was already published as Bi-Mamba4TS (ref [28]), which the paper cites. The adaptive residual coefficient is a minor tweak. The application to climate data is a new domain, but that alone does not constitute a research contribution.
What the paper does well: it assembles a forecasting pipeline on real UK Met Office data and runs a reasonable set of baselines. The writing is clear in places. That is where the credit ends.
The soft spots are load-bearing. First, the central claim of 14.2% lower RMSE is unsupported. Table IV shows DualMamba-4 test RMSE 0.0292 versus Mamba-4 0.0278—DualMamba is worse. The paper never explains where the 14.2% figure comes from. This is not a minor inconsistency; it undermines the entire empirical case. Second, the theoretical analysis (Theorems 1-3) assumes the Polyak-Łojasiewicz condition and a continuous kernel operator representation without verifying either for the discrete architecture. These are generic arguments that do not depend on the proposed modifications. Third, the hyperparameter sensitivity analysis (Table V) shows nearly identical RMSE across all historical/prediction horizons (e.g., Radcliffe: 0.1194–0.1201). That flatness is suspicious and inconsistent with a model claimed to capture long-range dependencies. Fourth, the paper lacks error bars, confidence intervals, code, and comparison with recent state-of-the-art methods like PatchTST, TimesNet, or DLinear. Fifth, the validation MSE for DualMamba-3 (0.1591) versus training MSE (0.0765) suggests overfitting or data leakage.
Who this paper is for: perhaps a practitioner looking for a quick baseline on UK temperature data, but they would be better served by the existing Mamba or Bi-Mamba4TS implementations. The paper does not provide a reliable contribution.
Recommendation: desk reject. The empirical contradiction alone is fatal. The theoretical analysis is not rigorous, the novelty is marginal, and the evaluation is incomplete. This does not deserve referee time.
The strongest objection
The paper's strongest claim is that Deep DualMamba achieves superior predictive accuracy with a reduced parameter footprint, specifically 14.2% lower RMSE than baselines. However, Table IV directly contradicts this: on the test set, Mamba-4 achieves RMSE 0.0278 while DualMamba-4 achieves 0.0292—DualMamba is worse. For the 3-depth variants, Mamba-3 test RMSE is 0.0308 and DualMamba-3 is 0.0314, again worse. The only metric where DualMamba-4 leads is training RMSE (0.0257 vs 0.0281), but that is irrelevant for generalization. The paper claims '14.2% lower RMSE' but provides no calculation or reference to which baseline or which metric this applies. The abstract and introduction state '14.2% lower RMSE and 5x faster inference than Transformers,' but Table IV shows Transformer-3 test RMSE 0.0534 and Transformer-4 0.0659, so a comparison to Transformers would indeed show improvement—but the claim is phrased as 'compared to MLP and Transformer baselines' (contributions bullet) and the 14.2% figure is not traceable to any specific entry. The reader correctly identified this inconsistency. This is not a minor typo; it undermines the central empirical claim of the paper. If the model does not outperform standard Mamba, the entire motivation for the bidirectional architecture collapses. The paper also lacks error bars, confidence intervals, or statistical significance tests, so we cannot assess whether any observed differences are meaningful. The hyperparameter sensitivity analysis (Table V) shows nearly identical RMSE across all historical/prediction horizons (e.g., Radcliffe: 0.1194–0.1201), which is suspiciously flat and inconsistent with a model that is supposed to capture long-range dependencies. This further weakens the empirical case.
The reader's verdict is REJECT with high confidence, and the weakest assumption identified includes the empirical contradiction in Table IV. My stress-test confirms this is the single most load-bearing concern: the paper's headline empirical claim is directly contradicted by its own reported numbers. The reader also noted lack of code, error bars, and comparison with recent SOTA, but the internal inconsistency alone is sufficient for rejection. The theoretical analysis (Theorems 1-3) is not rigorous and relies on unverified assumptions (e.g., PL condition, continuous kernel operator interpretation of discrete Mamba), but even if the theory were correct, the empirical failure would still invalidate the paper's main contribution. The hyperparameter sensitivity showing near-identical performance across all settings further suggests the model is not actually learning meaningful temporal structure. I agree with the reader's assessment and recommend no change to the verdict.
The referee's report
The architecture description (Algorithm 2 and the DualMamba block) is clear, and the paper usefully documents its hypotheses, including the kernel-operator assumption in Eq. (14) and the PL condition in Assumption 1. If the empirical claims were substantiated, the contribution would be a moderate incremental engineering result: a bidirectional residual variant of Mamba with linear complexity that improves over vanilla Mamba and Transformers on a real climate-temperature benchmark. However, the paper provides no code, checkpoints, or error bars; the headline numbers (14.2%, 32%, 5x) are not traced to any reported measurement; the theoretical theorems are generic statements about state-space models rather than architecture-specific results; and, as detailed below, the central accuracy claim is contradicted by the paper's own Table IV. On the evidence reported, the significance of the contribution cannot currently be assessed as positive.
Pith's reading of the paper (a machine's summary, not the authors')
This paper presents Deep DualMamba, a neural network for climate temperature prediction that replaces the attention mechanism of Transformers with a bidirectional state space model. The authors claim that this architecture achieves higher accuracy with fewer parameters and faster inference on monthly temperature data from eight UK stations. They also provide theoretical proofs of universal approximation and linear convergence under specific assumptions. The work is framed as the first operational application of a Mamba-based model to real climate data, moving beyond synthetic benchmarks. If the claims hold, DualMamba offers a computationally cheaper alternative to Transformers for long-sequence time series forecasting.
What carries the argument. The central mechanism is the bidirectional Mamba block, which processes input sequences in both forward and reverse directions using selective structured state space models (SSMs). The forward and reverse representations are fused via addition, then passed through a feed-forward network with an adaptive residual connection (coefficient α). This stack is repeated L times to form the encoder. The SSM uses input-dependent discretization of continuous parameters (A, B, C) via a step size Δ, allowing the model to selectively focus on relevant temporal features. The hardware-aware parallel algorithm (Algorithm 1) ensures linear-time computation by exploiting the recurrent structure of the discretized SSM.
Core claim. The paper argues that a bidirectional Mamba encoder, combined with residual connections and a hardware-aware parallel algorithm, can outperform both traditional recurrent networks and Transformers in predicting monthly UK temperatures. The authors report a 14.2% reduction in RMSE and a fivefold speedup in inference compared to Transformer baselines on the Central England Temperature dataset. They also assert that the architecture achieves linear complexity with sequence length and exhibits stable training dynamics across eight stations. The core claim is that the selective state space mechanism captures long-range dependencies more efficiently than attention, and that the bidirectional processing overcomes the unidirectional limitation of standard Mamba.
The premise it rests on. The theoretical analysis assumes that the discrete Mamba block behaves as a continuous kernel operator and that the loss landscape satisfies the Polyak-Łojasiewicz condition, neither of which is verified for the actual architecture or data.
If the paper is right (Pith's inferences, not the authors')
If DualMamba's accuracy advantage generalizes beyond UK temperature data, it could replace Transformers in other long-sequence climate forecasting tasks (e.g., precipitation, wind) with lower computational cost.
The linear complexity with sequence length makes the architecture attractive for real-time or edge deployment where memory and latency are constrained.
The theoretical convergence guarantee (Theorem 2) suggests that training is stable even with deeper stacks, potentially enabling larger models without vanishing/exploding gradients.
The bidirectional design could be adapted to other domains where temporal context from both past and future is beneficial (e.g., speech, biosignals).
The empirical comparison does not include recent Transformer-free forecasting methods (PatchTST, TimesNet, DLinear), so the reported advantage over 'Transformers' may not hold against the current state of the art; a broader benchmark would clarify the practical significance.
The hyperparameter sensitivity analysis shows nearly identical performance across different historical and prediction horizons (Table V), which undermines the claim that the architecture is especially effective for long-term forecasting; if performance is flat, simpler baselines might suffice.
The theoretical analysis (Theorems 1-3) assumes continuous kernel operators and the Polyak-Łojasiewicz condition, which are not verified for the discrete architecture and real data; the practical convergence guarantees are weaker than the proofs suggest.
The paper does not release code or trained models, making it difficult to reproduce the results or test the claims on new data; reproducibility is a prerequisite for operational adoption.
Check this review
Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.
How often reviews like this one are right
Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.
How often objections from reviews like this one are right: not yet measured
Reviews by people
This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.
The paper
Abstract
Accurate temperatures forecasting relies on traditional meteorological parameters that are essential for monitoring weather informatics and guiding forecasting efforts. This study presents Deep DualMamba, a novel deep learning framework for temporal temperature prediction, built upon an enhanced variant of the recently proposed Mamba network. Unlike conventional Transformer-based architectures, which dominate foundation models but suffer from computational inefficiencies on long sequences, Deep DualMamba leverages selective structured state space models (SSMs) to achieve both scalability and performance. We identify a core limitation of prior subquadratic-time models-namely, their inability to perform long-term and robust forecasting and introduce two key innovations. First, we propose an adaptive bidirectional Mamba as encoders to learn complex and efficient features. Second, we develop a hardware-aware, parallel recurrent algorithm to compensate for the loss of convolutional efficiency, ensuring practical viability at scale. Last, the Deep DualMamba's approximation ability and convergence is theoretical analyzed. These design choices culminate in a simplified, attention- and MLP-free neural architecture that exhibits linear complexity with sequence length and significantly improved inference throughput. To demonstrate its applicability in climate informatics, we implement a full forecasting pipeline using historical meteorological data from UK monitoring stations.
The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.
abstract compiled · 2026-11-13
The authors' main claim, as the classifier picked it out 0.96
“These design choices culminate in a simplified, attention- and MLP-free neural architecture that exhibits linear complexity with sequence length and significantly improved inference throughput.”
How the main claim is stated: asserted 1.00
What the abstract itself states, as probabilities: claims first 0.11 · states limitation 0.23 · human participants 0.02 · controlled comparison 0.13 · randomized assignment 0.01 · states quantitative result 0.06 · compares with prior results 0.29 · mentions code or data availability 0.03
The abstract, sentence by sentence
This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| Accurate temperatures forecasting relies on traditional meteorological parameters that are essential for monitoring weather informatics and guiding forecasting efforts. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| This study presents Deep DualMamba, a novel deep learning framework for temporal temperature prediction, built upon an enhanced variant of the recently proposed Mamba network. | contribution 0.99 | 0.87 | 0.09 | asserted 1.00 |
| Unlike conventional Transformer-based architectures, which dominate foundation models but suffer from computational inefficiencies on long sequences, Deep DualMamba leverages selective structured state space models (SSMs) to achieve both scalability and performance. | background 0.45 | 0.17 | 0.08 | asserted 1.00 |
| We identify a core limitation of prior subquadratic-time models-namely, their inability to perform long-term and robust forecasting and introduce two key innovations. | gap 0.98 | 0.73 | 0.07 | asserted 1.00 |
| First, we propose an adaptive bidirectional Mamba as encoders to learn complex and efficient features. | contribution 0.80 | 0.94 | 0.05 | asserted 1.00 |
| Second, we develop a hardware-aware, parallel recurrent algorithm to compensate for the loss of convolutional efficiency, ensuring practical viability at scale. | contribution 0.80 | 0.94 | 0.06 | asserted 1.00 |
| Last, the Deep DualMamba's approximation ability and convergence is theoretical analyzed. | contribution 0.81 | 0.86 | 0.07 | asserted 1.00 |
| These design choices culminate in a simplified, attention- and MLP-free neural architecture that exhibits linear complexity with sequence length and significantly improved inference throughput. | result 0.41 | 0.86 | 0.44 | asserted 1.00 |
| To demonstrate its applicability in climate informatics, we implement a full forecasting pipeline using historical meteorological data from UK monitoring stations. | method 0.96 | 0.96 | 0.06 | asserted 1.00 |
What kind of paper the classifier reports this is: method or tool 1.00 · evidence from analysis of existing data 0.53
What was examined, and what was not
Sources read
- arXiv listing abstract v1
Not examined
- full text
- figures and tables
- references and citing sentences
- relations to other papers
Levels run
- P abstract
Not run
- S sections
- T body sentences
- C citations
- R cross-paper relations
How the labels were made
Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-13: 1 request, 6,897 input tokens.
Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON
Figures (7)
Figures are the authors', reproduced from the paper.
References (50)
- [28] A. Liang, X. Jiang, Y . Sun, and C. Lu, “Bi-mamba4ts: Bidirectional mamba for time series forecasting,”arXiv preprint arXiv:2404.15772, 2024 on PithPith's reviewarXiv
- [41] I. Gohberg and M. G. Krein,Theory and applications of Volterra operators in Hilbert space. American Mathematical Soc., 1970, vol. 24 on Pith
- [44] S. J. Reddi, S. Kale, and S. Kumar, “On the convergence of adam and beyond,”arXiv preprint arXiv:1904.09237, 2019 on PithPith's reviewarXiv
- [1] X. Zhang, Y . Zhang, and X. Meng, “Spatio-temporal mamba dynamic graph convolutional recurrent network for traffic prediction,”IEEE Transactions on Artificial Intelligence, 2025 on Pith
- [2] P. Li, X. Zheng, S. Xiang, J. Hou, Y . Qin, M. S. Kurboniyon, and W. Ren, “Channel independence bidirectional gated mamba with interactive recurrent mechanism for time series forecasting,”IEEE Transactions on Industrial Electronics, 2025. 15 Fig. 7: Training and Validation Los... on Pith
- [3] H. J. Fowler, D. Cooley, S. R. Sain, and M. Thurston, “Detecting change in uk extreme precipitation using results from the climate prediction. net bbc climate change experiment,”Extremes, vol. 13, pp. 241–267, 2010 on Pith
- [4] Y . Lei and H. R. Karimi, “Duallstm: A novel key-quality prediction for a hierarchical cone thickener,”Control Engineering Practice, vol. 137, p. 105566, 2023 on Pith
- [5] G. Papacharalampous, H. Tyralis, and D. Koutsoyiannis, “Univariate time series forecasting of temperature and precipitation with a focus on machine learning algorithms: A multiple-case study from greece,” Water resources management, vol. 32, no. 15, pp. 5207–5239, 2018 on Pith
- [6] Y . Song, R. Wan, L. Li, W. Wang, and H. Xing, “A multi-scale temporal-frequency fusion network based on mlp for long-term time series forecasting,”International Journal of Machine Learning and Cybernetics, pp. 1–12, 2024 on Pith
- [7] Z. Li, G. Li, K. Xu, and L. Wang, “Data-driven thermal error pre- diction of spindle with mechanism-reinforced temperature information,” Advanced Engineering Informatics, vol. 64, p. 103005, 2025 on Pith
- [8] Y . Lei, H. R. Karimi, and X. Chen, “A novel self-supervised deep lstm network for industrial temperature prediction in aluminum processes application,”Neurocomputing, vol. 502, pp. 177–185, 2022 on Pith
- [9] J. Xue, Y . Cheng, W. Zhai, X. Zhou, and S. Zhou, “Research on multi- step ahead prediction method for tool wear based on mstcn-sbigru-mha,” Advanced Engineering Informatics, vol. 65, p. 103219, 2025 on Pith
- [10] N. Azizi, M. Yaghoubirad, M. Farajollahi, and A. Ahmadi, “Deep learning based long-term global solar irradiance and temperature fore- casting using time series with multi-step multivariate output,”Renewable Energy, vol. 206, pp. 135–147, 2023 on Pith
- [11] R. Graf, S. Zhu, and B. Sivakumar, “Forecasting river water temperature time series using a wavelet–neural network hybrid modelling approach,” Journal of Hydrology, vol. 578, p. 124115, 2019 on Pith
- [12] H. Wang, Y . Mo, H. Dai, N. Yin, S. Fan, and B. Li, “Ftmlp: Mlp with feature-temporal block for multivariate time series forecasting,” Neurocomputing, vol. 607, p. 128365, 2024 on Pith
- [13] B. Mohammadi, S. Mehdizadeh, F. Ahmadi, N. T. T. Lien, N. T. T. Linh, and Q. B. Pham, “Developing hybrid time series and artificial intelli- gence models for estimating air temperatures,”Stochastic Environmental Research and Risk Assessment, vol. 35, pp. 1189–1204, 2021 on Pith
- [14] M. Mart ´ınez Comesa ˜na, L. Febrero-Garrido, F. Troncoso-Pastoriza, and J. Mart´ınez-Torres, “Prediction of building’s thermal performance using lstm and mlp neural networks,”Applied Sciences, vol. 10, no. 21, p. 7439, 2020 on Pith
- [15] F. Rodr ´ıguez, M. Genn, L. Font ´an, and A. Galarza, “Very short-term temperature forecaster using mlp and n-nearest stations for calculating key control parameters in solar photovoltaic generation,”Sustainable Energy Technologies and Assessments, vol. 45, p. 101085, 2021 on Pith
- [16] B. Ustaoglu, H. Cigizoglu, and M. Karaca, “Forecast of daily mean, maximum and minimum temperature time series by three artificial neural network methods,”Meteorological Applications: A journal of forecasting, practical applications, training techniques and modelling, vol. 15,... on Pith
- [17] M. Mohammadi, S. Jamshidi, A. Rezvanian, M. Gheisari, and A. Kumar, 16 “Advanced fusion of mtm-lstm and mlp models for time series forecast- ing: an application for forecasting the solar radiation,”Measurement: Sensors, vol. 33, p. 101179, 2024 on Pith
show 30 more
- [18] H. Du, L. Jiang, C. Zhao, W. Li, Y . Bu, Q. Xu, C. Zhang, and J. Yan, “Industrial equipment structure multivariate regression prediction via random input and hybrid temporal neural networks,”Advanced Engineering Informatics, vol. 64, p. 103006, 2025 on Pith
- [19] A. Gu and T. Dao, “Mamba: Linear-time sequence modeling with selective state spaces,”arXiv preprint arXiv:2312.00752, 2023 on PithPith's reviewarXiv
- [20] A. Gu,Modeling sequences with structured state spaces. Stanford University, 2023 on Pith
- [21] H. Ma, Y . Chen, W. Zhao, J. Yang, Y . Ji, X. Xu, X. Liu, H. Jing, S. Liu, and G. Yang, “A mamba foundation model for time series forecasting,” arXiv preprint arXiv:2411.02941, 2024 on PithPith's reviewarXiv
- [22] J. Alman and H. Yu, “Fundamental limitations on subquadratic alterna- tives to transformers,”arXiv preprint arXiv:2410.04271, 2024 on PithPith's reviewarXiv
- [23] Q. Li, J. Qin, D. Cui, D. Sun, and D. Wang, “Cmmamba: channel mixing mamba for time series forecasting,”Journal of Big Data, vol. 11, no. 1, p. 153, 2024 on Pith
- [24] G. Zhao, L. Zhou, and X. Wang, “Ismrnn: An implicitly segmented rnn method with mamba for long-term time series forecasting,”arXiv preprint arXiv:2407.10768, 2024 on PithPith's reviewarXiv
- [25] T. Dao and A. Gu, “Transformers are ssms: Generalized models and ef- ficient algorithms through structured state space duality,”arXiv preprint arXiv:2405.21060, 2024 on PithPith's reviewarXiv
- [26] A. Stephens, P. James, D. Alderson, S. Pascoe, S. Abele, A. Iwi, and P. Chiu, “The challenges of developing an open source, standards- based technology stack to deliver the latest uk climate projections,” International Journal of Digital Earth, vol. 5, no. 1, pp. 43–62, 2012 on Pith
- [27] Z. Wang, F. Kong, S. Feng, M. Wang, X. Yang, H. Zhao, D. Wang, and Y . Zhang, “Is mamba effective for time series forecasting?”Neurocom- puting, vol. 619, p. 129178, 2025 on Pith
- [29] M. A. Ahamed and Q. Cheng, “Timemachine: A time series is worth 4 mambas for long-term forecasting,” 2024 on Pith
- [30] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,”Advances in neural information processing systems, vol. 30, 2017 on Pith
- [31] W. Lin, Z. Zhang, G. Ren, Y . Zhao, J. Ma, and Q. Cao, “Mgcn: Mamba-integrated spatiotemporal graph convolutional network for long- term traffic forecasting,”Knowledge-Based Systems, vol. 309, p. 112875, 2025 on Pith
- [32] W. Zhang, J. Huang, R. Wang, C. Wei, W. Huang, and Y . Qiao, “Inte- gration of mamba and transformer-mat for long-short range time series forecasting with application to weather dynamics,” in2024 International Conference on Electrical, Communication and Computer Engineering (I... on Pith
- [33] Y . M. Karadag, S. Kalkan, and I. G. Dino, “ms-mamba: Multi-scale mamba for time-series forecasting,”arXiv preprint arXiv:2504.07654, 2025 on PitharXiv
- [34] C. Zeng, Z. Liu, G. Zheng, and L. Kong, “Cmamba: Channel correlation enhanced state space models for multivariate time series forecasting,” arXiv preprint arXiv:2406.05316, 2024 on PithPith's reviewarXiv
- [35] P. Pessoa, P. Campitelli, D. P. Shepherd, S. B. Ozkan, and S. Press ´e, “Mamba time series forecasting with uncertainty propagation,”stat, vol. 1050, p. 13, 2025 on Pith
- [36] A. Gu, I. Johnson, K. Goel, K. K. Saab, T. Dao, A. Rudra, and C. R’e, “Combining recurrent, convolutional, and continuous-time models with linear state-space layers,” inNeural Information Processing Systems, 2021 on Pith
- [37] A. Gu, K. Goel, and C. R ´e, “Efficiently modeling long sequences with structured state spaces,”arXiv preprint arXiv:2111.00396, 2021 on PithPith's reviewarXiv
- [38] A. Gu, T. Dao, S. Ermon, A. Rudra, and C. R ´e, “Hippo: Recurrent mem- ory with optimal polynomial projections,”ArXiv, vol. abs/2008.07669, 2020 on PithPith's reviewarXiv
- [39] S. Elfwing, E. Uchibe, and K. Doya, “Sigmoid-weighted linear units for neural network function approximation in reinforcement learning,” Neural networks : the official journal of the International Neural Network Society, vol. 107, pp. 3–11, 2017 on Pith
- [40] Y . Liu, T. Hu, H. Zhang, H. Wu, S. Wang, L. Ma, and M. Long, “itrans- former: Inverted transformers are effective for time series forecasting,” arXiv preprint arXiv:2310.06625, 2023 on PithPith's reviewarXiv
- [42] L. Lu, P. Jin, G. Pang, Z. Zhang, and G. E. Karniadakis, “Learning nonlinear operators via deeponet based on the universal approximation theorem of operators,”Nature machine intelligence, vol. 3, no. 3, pp. 218–229, 2021 on Pith
- [43] R. T. Chen, Y . Rubanova, J. Bettencourt, and D. K. Duvenaud, “Neural ordinary differential equations,”Advances in neural information pro- cessing systems, vol. 31, 2018 on Pith
- [45] D. Yarotsky, “Error bounds for approximations with deep relu networks,” Neural networks, vol. 94, pp. 103–114, 2017 on Pith
- [46] E. Stoudenmire and D. J. Schwab, “Supervised learning with tensor networks,”Advances in neural information processing systems, vol. 29, 2016 on Pith
- [47] J. Lu, Z. Shen, H. Yang, and S. Zhang, “Deep network approximation for smooth functions,”SIAM Journal on Mathematical Analysis, vol. 53, no. 5, pp. 5465–5506, 2021 on Pith
- [48] B. Poole, S. Lahiri, M. Raghu, J. Sohl-Dickstein, and S. Ganguli, “Exponential expressivity in deep neural networks through transient chaos,”Advances in neural information processing systems, vol. 29, 2016 on Pith
- [49] T. De Ryck, S. Lanthaler, and S. Mishra, “On the approximation of functions by tanh neural networks,”Neural Networks, vol. 143, pp. 732– 750, 2021 on Pith
- [50] L. Gonon and A. Jacquier, “Universal approximation theorem and error bounds for quantum neural networks and quantum reservoirs,”IEEE Transactions on Neural Networks and Learning Systems, 2025 on Pith
Challenges and discussion
Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.
No comments yet.
Sign in to comment