Skillful high-resolution weather forecasting independent of physical models

2026-05-27

AI Summary

This study addresses the limitations of traditional numerical weather prediction (NWP), which relies on physical models and reanalysis data and is often constrained by biases, limited resolution, and high computational costs—particularly in data-scarce regions. To overcome these challenges, this work proposes ObsCast, the first end-to-end regional weather forecasting system that operates exclusively on local ground-based observations without incorporating any NWP or reanalysis data during either training or inference. As a purely data-driven approach, ObsCast directly learns the spatiotemporal evolution of weather from observational data alone. Evaluated over the contiguous United States and Europe, it outperforms operational NWP systems in forecasting near-surface variables up to 18 hours ahead and produces skillful precipitation predictions, thereby substantially enhancing forecast flexibility, adaptability, and practical utility.

Abstract

Accurate and timely weather forecasts are critical for high-impact decisions in modern society. Machine-learning-based weather prediction is emerging as an alternative for producing initial conditions, forecasts, and even both in end-to-end systems. These methods deliver predictions faster and often with higher skill than traditional numerical weather prediction (NWP). However, even end-to-end models typically rely on NWP-generated reanalyses for supervision, thereby inheriting the biases and resolution limitations of those NWPs, and limiting adaptation to settings where suitable reanalysis products are unavailable, infrequently updated, or expensive to produce. Here we introduce ObsCast, a regional system that generates both analysis and predictions, without using any NWP-derived data in either training or inference, while still achieving state-of-the-art performance in short-term high-resolution regional modeling. Over the contiguous United States and Europe, ObsCast outperforms operational NWP for near-surface variables through 18 h and produces skillful precipitation forecasts. It provides a simpler and more adaptable route to build and refine regional forecasting services directly from local observations, without the need to develop complex and costly traditional forecasting pipelines.

Problem

• weather forecasting
• numerical weather prediction
• reanalysis data
• machine learning
• high-resolution modeling

Innovation

• ObsCast
• NWP-independent
• observation-based forecasting
• high-resolution weather prediction
• end-to-end machine learning