# Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling

arXiv: https://arxiv.org/abs/2405.13796 · HTML: https://mlsanity.com/paper/2405.13796/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 65 references that are in the map.
- First posted on arXiv 22 May 2024.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Physics-Informed Neural Operator for Learning Partial Differential Equations](https://mlsanity.com/paper/2111.03794/) (2021)
- [Physics-informed neural networks (PINNs) for fluid mechanics: A review](https://mlsanity.com/paper/2105.09506/) (2021)
- [WeatherBench: A benchmark dataset for data-driven weather forecasting](https://mlsanity.com/paper/2002.00469/) (2020)
- [Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers](https://mlsanity.com/paper/2111.13587/) (2021)
- [FuXi: A cascade machine learning forecasting system for 15-day global weather forecast](https://mlsanity.com/paper/2306.12873/) (2023)
- [FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators](https://mlsanity.com/paper/2208.05419/) (2022)
- [SimVP: Simpler yet Better Video Prediction](https://mlsanity.com/paper/2206.05099/) (2022)
- [FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead](https://mlsanity.com/paper/2304.02948/) (2023)
- [Forecasting Global Weather with Graph Neural Networks](https://mlsanity.com/paper/2202.07575/) (2022)
- [Earthformer: Exploring Space-Time Transformers for Earth System Forecasting](https://mlsanity.com/paper/2207.05833/) (2022)
- [Convergence Analysis of Two-layer Neural Networks with ReLU Activation](https://mlsanity.com/paper/1705.09886/) (2017)
- [Scaling transformer neural networks for skillful and reliable medium-range weather forecasting](https://mlsanity.com/paper/2312.03876/) (2023)
- [FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation](https://mlsanity.com/paper/2012.08512/) (2020)
- [Comparative Study of CNN and RNN for Natural Language Processing](https://mlsanity.com/paper/1702.01923/) (2017)
- [ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs](https://mlsanity.com/paper/2404.10024/) (2024)
- [Deep Learning for Day Forecasts from Sparse Observations](https://mlsanity.com/paper/2306.06079/) (2023)
- [CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling](https://mlsanity.com/paper/2402.04290/) (2024)
- [A Unified Pyramid Recurrent Network for Video Frame Interpolation](https://mlsanity.com/paper/2211.03456/) (2022)
- [FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting](https://mlsanity.com/paper/2402.00059/) (2024)
- [Permute, Quantize, and Fine-tune: Efficient Compression of Neural Networks](https://mlsanity.com/paper/2010.15703/) (2020)
- [Scaling physics-informed hard constraints with mixture-of-experts](https://mlsanity.com/paper/2402.13412/) (2024)
- [FengWu-4DVar: Coupling the Data-driven Weather Forecasting Model with 4D Variational Assimilation](https://mlsanity.com/paper/2312.12455/) (2023)
- [CRA5: Extreme Compression of ERA5 for Portable Global Climate and Weather Research via an Efficient Variational Transformer](https://mlsanity.com/paper/2405.03376/) (2024)
- [Towards an end-to-end artificial intelligence driven global weather forecasting system](https://mlsanity.com/paper/2312.12462/) (2023)

## Built on by (most cited first, 23 of 23)

- [Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systems](https://mlsanity.com/paper/2410.19892/) (2024)
- [WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning](https://mlsanity.com/paper/2411.05420/) (2024)
- [PhyDA: Physics-Guided Diffusion Models for Data Assimilation in Atmospheric Systems](https://mlsanity.com/paper/2505.12882/) (2025)
- [STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting](https://mlsanity.com/paper/2509.25210/) (2025)
- [PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplines](https://mlsanity.com/paper/2407.08418/) (2024)
- [VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting](https://mlsanity.com/paper/2412.02503/) (2024)
- [EMFormer: Efficient Multi-Scale Transformer for Accumulative Context Weather Forecasting](https://mlsanity.com/paper/2602.01194/) (2026)
- [FuXi-RTM: A Physics-Guided Prediction Framework with Radiative Transfer Modeling](https://mlsanity.com/paper/2503.19940/) (2025)
- [RainPro-8: An Efficient Deep Learning Model to Estimate Rainfall Probabilities Over 8 Hours](https://mlsanity.com/paper/2505.10271/) (2025)
- [Physics-Assisted and Topology-Informed Deep Learning for Weather Prediction](https://mlsanity.com/paper/2505.04918/) (2025)
- [XiChen: A global weather observation-to-forecast machine learning system via four-dimensional variational gradient-guided flexible assimilation](https://mlsanity.com/paper/2507.09202/) (2025)
- [DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation space](https://mlsanity.com/paper/2510.15978/) (2025)
- [Breaking Scale Anchoring: Frequency Representation Learning for Accurate High-Resolution Inference from Low-Resolution Training](https://mlsanity.com/paper/2512.05132/) (2025)
- [VeinCast: Physics-Guided Dynamic Field Graphs with Graph-Conditioned Fusion for Global Medium-Range Weather Forecasting](https://mlsanity.com/paper/2608.09286/) (2026)
- [StationPDE: Station-Oriented Surface PDE Learning for Multi-Station Multivariate Weather Forecasting](https://mlsanity.com/paper/2609.22123/) (2026)
- [SSTODE: Ocean-Atmosphere Physics-Informed Neural ODEs for Sea Surface Temperature Prediction](https://mlsanity.com/paper/2511.05629/) (2025)
- [Sharpness-Aware Hybrid Model Learning for Architecture-Agnostic Parameter Estimation](https://mlsanity.com/paper/2602.06837/) (2026)
- [Station2Radar: query conditioned gaussian splatting for precipitation field](https://mlsanity.com/paper/2603.00418/) (2026)
- [Generative 3D Gaussian Splatting for Arbitrary-ResolutionAtmospheric Downscaling and Forecasting](https://mlsanity.com/paper/2604.07928/) (2026)
- [Physics-Constrained Neural Networks for Improved Short-Term Weather Forecasting: A Case Study over the South Pacific](https://mlsanity.com/paper/2606.17659/) (2026)
- [Physics-Informed Super-Resolution of Atmospheric Data](https://mlsanity.com/paper/2607.18877/) (2026)
- [M2Weather: A Benchmark for Joint Multi-Station and Multi-Variable Weather Forecasting](https://mlsanity.com/paper/2610.00370/) (2026)
- [Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography](https://mlsanity.com/paper/2610.01835/) (2026)

## Abstract (arXiv)

Data-driven artificial intelligence (AI) models have made significant advancements in weather forecasting, particularly in medium-range and nowcasting. However, most data-driven weather forecasting models are black-box systems that focus on learning data mapping rather than fine-grained physical evolution in the time dimension. Consequently, the limitations in the temporal scale of datasets prevent these models from forecasting at finer time scales. This paper proposes a physics-AI hybrid model (i.e., WeatherGFT) which generalizes weather forecasts to finer-grained temporal scales beyond training dataset. Specifically, we employ a carefully designed PDE kernel to simulate physical evolution on a small time scale (e.g., 300 seconds) and use a parallel neural networks with a learnable router for bias correction. Furthermore, we introduce a lead time-aware training framework to promote the generalization of the model at different lead times. The weight analysis of physics-AI modules indicates that physics conducts major evolution while AI performs corrections adaptively. Extensive experiments show that WeatherGFT trained on an hourly dataset, effectively generalizes forecasts across multiple time scales, including 30-minute, which is even smaller than the dataset's temporal resolution.