Interpretable Cross-Sphere Multiscale Deep Learning Predicts ENSO Skilfully Beyond 2 Years

• URL: http://arxiv.org/abs/2503.21211v1
• Date: Thu, 27 Mar 2025 06:55:29 GMT
• Title: Interpretable Cross-Sphere Multiscale Deep Learning Predicts ENSO Skilfully Beyond 2 Years
• Authors: Rixu Hao, Yuxin Zhao, Shaoqing Zhang, Guihua Wang, Xiong Deng,
• Abstract summary: PTSTnet produces interpretable predictions significantly outperforming state-the-art benchmarks with lead times beyond 24 months.<n>Our successful realizations mark substantial steps forward in interpretable insights into innovative neural ocean modelling.
• Score: 4.591672124307768
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: El Ni\~no-Southern Oscillation (ENSO) exerts global climate and societal impacts, but real-time prediction with lead times beyond one year remains challenging. Dynamical models suffer from large biases and uncertainties, while deep learning struggles with interpretability and multi-scale dynamics. Here, we introduce PTSTnet, an interpretable model that unifies dynamical processes and cross-scale spatiotemporal learning in an innovative neural-network framework with physics-encoding learning. PTSTnet produces interpretable predictions significantly outperforming state-of-the-art benchmarks with lead times beyond 24 months, providing physical insights into error propagation in ocean-atmosphere interactions. PTSTnet learns feature representations with physical consistency from sparse data to tackle inherent multi-scale and multi-physics challenges underlying ocean-atmosphere processes, thereby inherently enhancing long-term prediction skill. Our successful realizations mark substantial steps forward in interpretable insights into innovative neural ocean modelling.

Related papers

• Principled Operator Learning in Ocean Dynamics: The Role of Temporal Structure [2.5234156040689233]
  This study compares the standard Fourier Neural Operator (FNO) with its variant, FNOtD, which has been modified to internalize the dispersion relation while learning the solution operator for ocean PDEs.<n>The results demonstrate that entangling space and time in the training of integral kernels enables the model to capture multiscale wave propagation and effectively learn ocean dynamics.
  arXiv  Detail & Related papers  (2025-10-10T18:54:38Z)
• Langevin Flows for Modeling Neural Latent Dynamics [81.81271685018284]
  We introduce LangevinFlow, a sequential Variational Auto-Encoder where the time evolution of latent variables is governed by the underdamped Langevin equation.<n>Our approach incorporates physical priors -- such as inertia, damping, a learned potential function, and forces -- to represent both autonomous and non-autonomous processes in neural systems.<n>Our method outperforms state-of-the-art baselines on synthetic neural populations generated by a Lorenz attractor.
  arXiv  Detail & Related papers  (2025-07-15T17:57:48Z)
• Advanced long-term earth system forecasting by learning the small-scale nature [74.19833913539053]
  We present Triton, an AI framework designed to address this fundamental challenge.<n>Inspired by increasing grids to explicitly resolve small scales in numerical models, Triton employs a hierarchical architecture processing information across multiple resolutions to mitigate spectral bias.<n>We demonstrate Triton's superior performance on challenging forecast tasks, achieving stable year-long global temperature forecasts, skillful Kuroshio eddy predictions till 120 days, and high-fidelity turbulence simulations.
  arXiv  Detail & Related papers  (2025-05-26T02:49:00Z)
• 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. By incorporating physical equations, our model demonstrates temporal extrapolation and spatial generalization capabilities.
  arXiv  Detail & Related papers  (2025-04-08T14:11:01Z)
• Towards Long-Range ENSO Prediction with an Explainable Deep Learning Model [8.609672620715674]
  El Nino-Southern Oscillation (ENSO) is a prominent mode of interannual climate variability with far-reaching global impacts.<n>We introduce CTEFNet, a multivariate deep learning model that synergizes convolutional neural networks and transformers to enhance ENSO forecasting.
  arXiv  Detail & Related papers  (2025-03-25T09:50:19Z)
• Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction [84.26340606752763]
  In this paper, we introduce the conservation-informed GNN (CiGNN), an end-to-end explainable learning framework.<n>The network is designed to conform to the general symmetry conservation law via symmetry where conservative and non-conservative information passes over a multiscale space by a latent temporal marching strategy.<n>Results demonstrate that CiGNN exhibits remarkable baseline accuracy and generalizability, and is readily applicable to learning for prediction of varioustemporal dynamics.
  arXiv  Detail & Related papers  (2024-12-30T13:55:59Z)
• Enhanced Spatiotemporal Prediction Using Physical-guided And Frequency-enhanced Recurrent Neural Networks [17.91230192726962]
  This paper proposes a physical-guided neural network to estimate the Stemporal dynamics. We also propose an adaptive second-order Runge-Kutta method with physical constraints to model the physical states more precisely. Our model outperforms state-of-the-art methods and performs best in datasets, with a much smaller parameter count.
  arXiv  Detail & Related papers  (2024-05-23T12:39:49Z)
• Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale [54.15522908057831]
  We propose an adapted version of the computationally-Mixer for STTD forecast at scale. Our results surprisingly show that this simple-yeteffective solution can rival SOTA baselines when tested on several traffic benchmarks. Our findings contribute to the exploration of simple-yet-effective models for real-world STTD forecasting.
  arXiv  Detail & Related papers  (2023-07-04T05:19:19Z)
• EINNs: Epidemiologically-Informed Neural Networks [75.34199997857341]
  We introduce a new class of physics-informed neural networks-EINN-crafted for epidemic forecasting. We investigate how to leverage both the theoretical flexibility provided by mechanistic models as well as the data-driven expressability afforded by AI models.
  arXiv  Detail & Related papers  (2022-02-21T18:59:03Z)
• Multi-scale Feature Learning Dynamics: Insights for Double Descent [71.91871020059857]
  We study the phenomenon of "double descent" of the generalization error. We find that double descent can be attributed to distinct features being learned at different scales.
  arXiv  Detail & Related papers  (2021-12-06T18:17:08Z)
• Can neural networks predict dynamics they have never seen? [0.4588028371034407]
  Neural networks have proven to be remarkably successful for a wide range of complicated tasks. One of their successes is the skill in prediction of future dynamics given a suitable training set of data. Previous studies have shown how Echo State Networks (ESNs), a subset of Recurrent Neural Networks, can successfully predict even chaotic systems for times longer than the Lyapunov time. This study shows that, remarkably, ESNs can successfully predict dynamical behavior that is qualitatively different from any behavior contained in the training set.
  arXiv  Detail & Related papers  (2021-11-12T15:49:34Z)
• Kinematically consistent recurrent neural networks for learning inverse problems in wave propagation [0.0]
  We propose a new kinematically consistent, physics-based machine learning model. In particular, we attempt to perform physically interpretable learning of inverse problems in wave propagation. Even with modest training data, the kinematically consistent network can reduce the $L_infty$ error norms of the plain LSTM predictions by about 45% and 55%, respectively.
  arXiv  Detail & Related papers  (2021-10-08T05:51:32Z)
• Physics-Coupled Spatio-Temporal Active Learning for Dynamical Systems [15.923190628643681]
  One of the major challenges is to infer the underlying causes, which generate the perceived data stream. Success of machine learning based predictive models requires massive annotated data for model training. Our experiments on both synthetic and real-world datasets exhibit that the proposed ST-PCNN with active learning converges to optimal accuracy with substantially fewer instances.
  arXiv  Detail & Related papers  (2021-08-11T18:05:55Z)
• Causal Navigation by Continuous-time Neural Networks [108.84958284162857]
  We propose a theoretical and experimental framework for learning causal representations using continuous-time neural networks. We evaluate our method in the context of visual-control learning of drones over a series of complex tasks.
  arXiv  Detail & Related papers  (2021-06-15T17:45:32Z)
• On Long-Tailed Phenomena in Neural Machine Translation [50.65273145888896]
  State-of-the-art Neural Machine Translation (NMT) models struggle with generating low-frequency tokens. We propose a new loss function, the Anti-Focal loss, to better adapt model training to the structural dependencies of conditional text generation. We show the efficacy of the proposed technique on a number of Machine Translation (MT) datasets, demonstrating that it leads to significant gains over cross-entropy.
  arXiv  Detail & Related papers  (2020-10-10T07:00:57Z)
• Learning to Simulate Complex Physics with Graph Networks [68.43901833812448]
  We present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains. Our framework---which we term "Graph Network-based Simulators" (GNS)--represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing. Our results show that our model can generalize from single-timestep predictions with thousands of particles during training, to different initial conditions, thousands of timesteps, and at least an order of magnitude more particles at test time.
  arXiv  Detail & Related papers  (2020-02-21T16:44:28Z)

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.