Physics-Constrained Neural Networks for Improved Short-Term Weather Forecasting: A Case Study over the South Pacific

• URL: http://arxiv.org/abs/2606.17659v1
• Date: Tue, 16 Jun 2026 08:18:48 GMT
• Title: Physics-Constrained Neural Networks for Improved Short-Term Weather Forecasting: A Case Study over the South Pacific
• Abstract summary: This study introduces enhancements to physics-constrained neural networks (PCNNs) that improve the accuracy and stability of hybrid short-term weather forecasting models.<n>An upgraded numerical solver, combined with a beta-plane approximation, and subgrid-scale viscosity, permits a fourfold increase in the integration time step to 1200 s.<n>A unified autoregressive hybrid block replaces the original chain of 24 specialised modules, eliminating overfitting to specific lead times.
• Score: 0.7705076872059964
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This study introduces enhancements to physics-constrained neural networks (PCNNs) that improve the accuracy and stability of hybrid short-term weather forecasting models. Building on the WeatherGFT architecture, three innovations are proposed. First, an upgraded numerical solver, combining a fifth-order weighted essentially non-oscillatory scheme (WENO-5), a beta-plane approximation, and subgrid-scale viscosity, permits a fourfold increase in the integration time step to 1200 s while reducing the daily mean squared error by up to 26%. Second, a unified autoregressive hybrid block replaces the original chain of 24 specialised modules, eliminating overfitting to specific lead times. Third, the physical core is integrated with two state-of-the-art neural backbones, resulting in PI-PredFormer and PI-IAM4VP. Evaluation on the WeatherBench South Pacific subset from 2000 to 2004 shows that these hybrids reduce root mean squared error at 1-12 h lead times by 8-22% compared to purely neural counterparts, while better preserving physical consistency. These results demonstrate that incremental refinement of hybrid components offers a practical route toward more accurate and efficient short-range weather forecasting.

Related papers

• PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption [0.0]
  This paper presents a systematic reliability characterization of pruned CKKS-encritical neural networks.<n>Polynomial-Sensitivity-Aware Pruning (PSAP) is a structured pruning method that is inherently reliability-aware.
  arXiv  Detail & Related papers  (2026-07-20T05:47:06Z)
• t-STEP: An interpretable model for Total Electron Content predictions and irregularities estimations [8.965320425114603]
  GPS communications are affected by ionospheric Total Electron Content (TEC) gradients.<n>To address this gap, we introduce an interpretable ML-based model, t-STEP, designed to predict TEC at a 30-second resolution.<n>The model is developed using GPS observations from solar cycle 24 at a station located at 5.49S, 47.49W.
  arXiv  Detail & Related papers  (2026-06-28T23:21:37Z)
• Leveraging Structural Constraints for Diffusion-based Neural TSP Solvers [3.588053519843615]
  State-ofthe-art approaches like FT2T combine fast consistency-based prediction with gradient-based inference time refinement.<n>We introduce Projected Consistency Inference ( PCI), a plug-and-play, retraining-free alternative that replaces gradient refinement with structure-aware projections.<n> PCI achieves an average optimality gap (OG) of 0.17% on the Euclidean Traveling Salesman Problem with 500 cities, and 0.31% on the Euclidean Traveling Salesman Problem with 1000 cities, outperforming FT2T best settings.
  arXiv  Detail & Related papers  (2026-06-08T11:08:36Z)
• PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting [62.22445401483844]
  Existing methods are severely constrained by the bottleneck of compounding errors.<n>We propose a universal framework called -Cast-Corrector (Plug-and-Play Corrector)<n>Our method significantly enhances the long-term stability of coupled forecasting systems.
  arXiv  Detail & Related papers  (2026-05-09T13:12:33Z)
• NeuroDDAF: Neural Dynamic Diffusion-Advection Fields with Evidential Fusion for Air Quality Forecasting [3.9956853658477307]
  We propose Dynamic Neural Diffusion-Advection Fields (NeuroDDAF), a physics-informed forecasting framework.<n>NeuroDDAF unifies neural representation learning with open-system transport modeling.<n>Experiments on four urban datasets show that NeuroDDAF consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-04-01T17:27:43Z)
• SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction [46.645872209565574]
  We present a specialized large-scale foundation model for virtual cell perturbation prediction.<n>First, we build a BioNeMo-based training and inference framework that substantially improves data throughput.<n>Second, we formulate perturbation prediction as conditional transport and implement it with a set-aware flow architecture.<n>Third, we evaluate the model on Tahoe-100M using a rigorous cell-level protocol centered on biologically meaningful metrics.
  arXiv  Detail & Related papers  (2026-03-18T05:51:08Z)
• Learning-based Radio Link Failure Prediction Based on Measurement Dataset in Railway Environments [46.243901410461596]
  We benchmark six models, namely CNN, LSTM, XGBoost, Anomaly Transformer, PatchTST, and TimesNet.<n>Results indicate that deep temporal models can anticipate reliability degradations several seconds in advance using lightweight features available on commercial devices.
  arXiv  Detail & Related papers  (2025-11-12T00:13:37Z)
• Long-Term PM2.5 Forecasting Using a DTW-Enhanced CNN-GRU Model [0.0]
  Long-term forecasting of PM2.5 concentrations is critical for public health early-warning systems.<n>Existing deep learning approaches struggle to maintain prediction stability beyond 48 hours.<n>This paper presents a framework that combines DTW for intelligent station similarity selection with a CNN-GRU architecture.
  arXiv  Detail & Related papers  (2025-10-26T23:04:10Z)
• Accelerating HEC-RAS: A Recurrent Neural Operator for Rapid River Forecasting [0.0]
  This paper introduces a deep learning surrogate that treats HEC-RAS not as a solver but as a data-generation engine.<n>Trained on 67 reaches of the Mississippi River Basin, the surrogate was evaluated on a year-long, unseen hold-out simulation.<n>Results show the model achieves a strong predictive accuracy, with a median absolute stage error of 0.31 feet.
  arXiv  Detail & Related papers  (2025-07-21T13:38:54Z)
• Hybrid Quantum Recurrent Neural Network For Remaining Useful Life Prediction [67.410870290301]
  We introduce a Hybrid Quantum Recurrent Neural Network framework, combining Quantum Long Short-Term Memory layers with classical dense layers for Remaining Useful Life forecasting.<n> Experimental results demonstrate that, despite having fewer trainable parameters, the Hybrid Quantum Recurrent Neural Network achieves up to a 5% improvement over a Recurrent Neural Network.
  arXiv  Detail & Related papers  (2025-04-29T14:41:41Z)
• How to systematically develop an effective AI-based bias correction model? [15.73933701556121]
  This study introduces ReSA-ConvLSTM, an artificial intelligence (AI) framework for systematic bias correction in numerical weather prediction (NWP)<n>We propose three innovations by integrating dynamic climatological normalization, ConvLSTM with temporal causality constraints, and residual self-attention mechanisms.<n>Using 41 years (1981-2021) of global atmospheric data, the framework reduces systematic biases in 2-m air temperature (T2m), 10-m winds (UV10), and sea-level pressure (SLP)<n>The lightweight architecture (10.6M parameters) enables efficient generalization to multiple variables and downstream applications, reducing retraining time by
  arXiv  Detail & Related papers  (2025-04-21T03:02:42Z)
• ResoNet: Robust and Explainable ENSO Forecasts with Hybrid Convolution and Transformer Networks [47.60320586459432]
  Deep learning models can skillfully predict the El Nino-Southern Oscillation (ENSO) forecasts over 1.5 years ahead. We propose ResoNet, a DL model that combines convolutional neural network (CNN) and Transformer architectures. We show that ResoNet can robustly predict ESNO at lead times between 19 and 26 months, thus outperforming existing approaches in terms of the forecast horizon.
  arXiv  Detail & Related papers  (2023-12-16T12:12:31Z)
• Continual Spatio-Temporal Graph Convolutional Networks [87.86552250152872]
  We reformulating the Spatio-Temporal Graph Convolutional Neural Network as a Continual Inference Network. We observe up to 109x reduction in time complexity, on- hardware accelerations of 26x, and reductions in maximum allocated memory of 52% during online inference.
  arXiv  Detail & Related papers  (2022-03-21T14:23:18Z)

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.