Deep Learning and Foundation Models for Weather Prediction: A Survey

2025-01-12

AI Summary

Deep learning and foundation models face significant challenges in weather forecasting—including high computational cost, weak physical consistency, and limited generalization. Method: This paper introduces the first comprehensive three-paradigm classification framework for meteorological DL/foundation model training—deterministic forecasting, probabilistic generation, and pretraining-finetuning—systematically surveying over 100 pivotal works from 2020–2024. It integrates state-of-the-art architectures (e.g., CNNs, GNNs, Transformers, diffusion models, Pangu-Weather, FourCastNet) with hybrid physics-informed and data-driven modeling. Contribution/Results: We release an open-source unified codebase, standardized benchmark datasets, and reproducible implementation guidelines. This promotes transparency, reproducibility, and real-world deployment of AI-powered meteorology, providing a systematic roadmap toward high-accuracy, low-latency, and interpretable weather AI.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Physics-based numerical models have been the bedrock of atmospheric sciences for decades, offering robust solutions but often at the cost of significant computational resources. Deep learning (DL) models have emerged as powerful tools in meteorology, capable of analyzing complex weather and climate data by learning intricate dependencies and providing rapid predictions once trained. While these models demonstrate promising performance in weather prediction, often surpassing traditional physics-based methods, they still face critical challenges. This paper presents a comprehensive survey of recent deep learning and foundation models for weather prediction. We propose a taxonomy to classify existing models based on their training paradigms: deterministic predictive learning, probabilistic generative learning, and pre-training and fine-tuning. For each paradigm, we delve into the underlying model architectures, address major challenges, offer key insights, and propose targeted directions for future research. Furthermore, we explore real-world applications of these methods and provide a curated summary of open-source code repositories and widely used datasets, aiming to bridge research advancements with practical implementations while fostering open and trustworthy scientific practices in adopting cutting-edge artificial intelligence for weather prediction. The related sources are available at https://github.com/JimengShi/ DL-Foundation-Models-Weather.

Problem

• Deep Learning
• Weather Prediction
• Resource Efficiency

Innovation

• Deep Learning Models
• Weather Forecasting
• AI Ethics in Meteorology