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

TL;DR

This paper introduces WeatherGFT, a hybrid physics-AI model that enhances weather forecasting at fine-grained temporal scales, surpassing dataset limitations through PDE kernels and adaptive neural networks.

Contribution

The paper presents a novel hybrid modeling approach combining PDE kernels with neural networks for fine-grained, multi-scale weather forecasting beyond training data constraints.

Findings

WeatherGFT effectively generalizes to 30-minute forecasts from hourly data.

Physics modules dominate the evolution, with AI providing adaptive corrections.

The model outperforms traditional data-driven models in fine-scale temporal predictions.

Abstract

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.