Mamba Integrated with Physics Principles Masters Long-term Chaotic System Forecasting

• URL: http://arxiv.org/abs/2505.23863v1
• Date: Thu, 29 May 2025 08:56:45 GMT
• Title: Mamba Integrated with Physics Principles Masters Long-term Chaotic System Forecasting
• Authors: Chang Liu, Bohao Zhao, Jingtao Ding, Huandong Wang, Yong Li,
• Abstract summary: PhyxMamba is a novel framework that integrates a Mamba-based state-space model with physics-informed principles to capture the underlying dynamics of chaotic systems.<n>Our generative training scheme enables Mamba to replicate the physical process, augmented by multi-token prediction and attractor geometry regularization.<n>This framework opens new avenues for reliably predicting chaotic systems under observation-scarce conditions, with broad implications across climate science, neuroscience, epidemiology, and beyond.
• Score: 16.519812316626584
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Long-term forecasting of chaotic systems from short-term observations remains a fundamental and underexplored challenge due to the intrinsic sensitivity to initial conditions and the complex geometry of strange attractors. Existing approaches often rely on long-term training data or focus on short-term sequence correlations, struggling to maintain predictive stability and dynamical coherence over extended horizons. We propose PhyxMamba, a novel framework that integrates a Mamba-based state-space model with physics-informed principles to capture the underlying dynamics of chaotic systems. By reconstructing the attractor manifold from brief observations using time-delay embeddings, PhyxMamba extracts global dynamical features essential for accurate forecasting. Our generative training scheme enables Mamba to replicate the physical process, augmented by multi-token prediction and attractor geometry regularization for physical constraints, enhancing prediction accuracy and preserving key statistical invariants. Extensive evaluations on diverse simulated and real-world chaotic systems demonstrate that PhyxMamba delivers superior long-term forecasting and faithfully captures essential dynamical invariants from short-term data. This framework opens new avenues for reliably predicting chaotic systems under observation-scarce conditions, with broad implications across climate science, neuroscience, epidemiology, and beyond. Our code is open-source at https://github.com/tsinghua-fib-lab/PhyxMamba.

Related papers

• A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments [16.251382658415494]
  We propose Phy-SSM, a generalizable method that integrates partial physics knowledge into state space models.<n>Our motivation is that SSMs can effectively capture long-range dependencies in sequential data and model continuous dynamical systems.<n>Experiments on three real-world applications, including vehicle motion prediction, drone state prediction, and COVID-19 epidemiology forecasting, demonstrate the superior performance of Phy-SSM.
  arXiv  Detail & Related papers  (2025-07-14T20:46:12Z)
• PINP: Physics-Informed Neural Predictor with latent estimation of fluid flows [11.102585080028945]
  We propose a new physics-informed learning approach that incorporates coupled physical quantities into the prediction process.<n>By incorporating physical equations, our model demonstrates temporal extrapolation and spatial generalization capabilities.
  arXiv  Detail & Related papers  (2025-04-08T14:11:01Z)
• Spatio-temporal Fourier Transformer (StFT) for Long-term Dynamics Prediction [13.502705948250359]
  Simulating the long-term dynamics of multi-scale and multi-physics systems poses a significant challenge in science and engineering.<n>Neural operators have emerged as promising models for predicting such dynamics due to their flexibility and computational efficiency.<n>We propose a generative residual correction mechanism to estimate and mitigate predictive uncertainties, enhancing the accuracy and reliability of long-term forecasts.
  arXiv  Detail & Related papers  (2025-03-14T22:04:03Z)
• Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint [12.638698799995815]
  We introduce the Dynamic System Prediction from Sparse Observations using Voronoi Tessellation (DSOVT) framework. By integrating Voronoi tessellations with deep learning models, DSOVT is adept at predicting dynamical systems with sparse, unstructured observations. Compared to purely data-driven models, our physics-based approach enables the model to learn physical laws within explicitly formulated dynamics.
  arXiv  Detail & Related papers  (2024-08-31T13:43:52Z)
• Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
  Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models. Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML) We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
  arXiv  Detail & Related papers  (2024-07-18T15:44:23Z)
• SFANet: Spatial-Frequency Attention Network for Weather Forecasting [54.470205739015434]
  Weather forecasting plays a critical role in various sectors, driving decision-making and risk management. Traditional methods often struggle to capture the complex dynamics of meteorological systems. We propose a novel framework designed to address these challenges and enhance the accuracy of weather prediction.
  arXiv  Detail & Related papers  (2024-05-29T08:00:15Z)
• A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics [51.147876395589925]
  A non-stationary PGDS is proposed to allow the underlying transition matrices to evolve over time. A fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed non-stationary PGDS achieves improved predictive performance.
  arXiv  Detail & Related papers  (2024-02-26T04:39:01Z)
• Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective [63.60312929416228]
  textbftextitAttraos incorporates chaos theory into long-term time series forecasting. We show that Attraos outperforms various LTSF methods on mainstream datasets and chaotic datasets with only one-twelfth of the parameters compared to PatchTST.
  arXiv  Detail & Related papers  (2024-02-18T05:35:01Z)
• Leveraging the structure of dynamical systems for data-driven modeling [111.45324708884813]
  We consider the impact of the training set and its structure on the quality of the long-term prediction. We show how an informed design of the training set, based on invariants of the system and the structure of the underlying attractor, significantly improves the resulting models.
  arXiv  Detail & Related papers  (2021-12-15T20:09:20Z)
• Physics-aware, probabilistic model order reduction with guaranteed stability [0.0]
  We propose a generative framework for learning an effective, lower-dimensional, coarse-grained dynamical model. We demonstrate its efficacy and accuracy in multiscale physical systems of particle dynamics.
  arXiv  Detail & Related papers  (2021-01-14T19:16:51Z)
• Stochastically forced ensemble dynamic mode decomposition for forecasting and analysis of near-periodic systems [65.44033635330604]
  We introduce a novel load forecasting method in which observed dynamics are modeled as a forced linear system. We show that its use of intrinsic linear dynamics offers a number of desirable properties in terms of interpretability and parsimony. Results are presented for a test case using load data from an electrical grid.
  arXiv  Detail & Related papers  (2020-10-08T20:25:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.