OMG-HD: A High-Resolution AI Weather Model for End-to-End Forecasts from Observations

2024-12-24

AI Summary

Short-term weather forecasting traditionally relies on numerical weather prediction (NWP) systems that require data assimilation of reanalysis products, introducing significant uncertainty. Method: We propose the first purely observation-driven, end-to-end AI forecasting framework—bypassing data assimilation entirely—and directly fusing heterogeneous observational data from ground stations, radar, and satellites. Our approach employs a multimodal spatiotemporal fusion deep neural network explicitly embedded with physical consistency constraints to generate high-resolution (CONUS) 12-hour forecasts. Results: Experiments demonstrate substantial improvements over the operational HRRR system: RMSE reductions of 13% (2-m temperature), 17% (10-m wind speed), 48% (2-m specific humidity), and 32% (surface pressure); our model also outperforms ECMWF’s IFS-HRES. This work provides the first empirical validation of the feasibility and superiority of assimilation-free, observation-only AI-based meteorological modeling, establishing a novel paradigm for nowcasting and very-short-range forecasting.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

In recent years, Artificial Intelligence Weather Prediction (AIWP) models have achieved performance comparable to, or even surpassing, traditional Numerical Weather Prediction (NWP) models by leveraging reanalysis data. However, a less-explored approach involves training AIWP models directly on observational data, enhancing computational efficiency and improving forecast accuracy by reducing the uncertainties introduced through data assimilation processes. In this study, we propose OMG-HD, a novel AI-based regional high-resolution weather forecasting model designed to make predictions directly from observational data sources, including surface stations, radar, and satellite, thereby removing the need for operational data assimilation. Our evaluation shows that OMG-HD outperforms both the European Centre for Medium-Range Weather Forecasts (ECMWF)'s high-resolution operational forecasting system, IFS-HRES, and the High-Resolution Rapid Refresh (HRRR) model at lead times of up to 12 hours across the contiguous United States (CONUS) region. We achieve up to a 13% improvement on RMSE for 2-meter temperature, 17% on 10-meter wind speed, 48% on 2-meter specific humidity, and 32% on surface pressure compared to HRRR. Our method shows that it is possible to use AI-driven approaches for rapid weather predictions without relying on NWP-derived weather fields as model input. This is a promising step towards using observational data directly to make operational forecasts with AIWP models.

Problem

• Direct Observation
• Weather Prediction
• Short-term Forecasting

Innovation

• OMG-HD Model
• Direct Observation Utilization
• AI-based Weather Forecasting