AIFS-TC: A simple correction competitive with the operational frontier for tropical cyclone intensity forecasting

2026-07-24

AI Summary

This study addresses the persistent underestimation of tropical cyclone intensity by current AI-based weather models, despite their strong performance in track prediction. Focusing on the open-source AIFS-Single model, the authors propose a lightweight post-processing correction method that substantially improves forecast accuracy for both maximum wind speed and minimum central pressure. Notably, a large language model (Claude Fable 5) autonomously designed and implemented the entire prediction system within hours, enabling end-to-end development from natural language prompts to operational deployment. The resulting system achieves state-of-the-art performance in forecasting tropical cyclone intensity and rapid intensification events across lead times from 12 hours to 7 days, demonstrating the feasibility and promise of agent-driven approaches in meteorological modeling.

Abstract

AI weather models are in the process of revolutionising weather forecasting. While these models have been shown to achieve superior performance to physics-based NWP in forecasting tropical cyclone (TC) tracks, they dramatically underestimate intensity. Here we present AIFS-TC, a simple correction to the AIFS-Single model that is competitive with the operational state-of-the-art for forecasting maximum wind speed and minimum central pressure at lead times of 12 h to seven days. This performance also holds for rapid intensification events. Notably, the entire system was autonomously designed and built by a large language model (Claude Fable 5) in a few hours, directed through a small number of natural-language prompts by a single domain scientist. That the operational frontier can be reached with an open-source AI forecast model (AIFS-Single) and relatively simple, cheap post-processing is significant for TC science, and points to agentic coding as a route to rapid exploration and progress in life-saving early-warning systems in other domains.

Problem

• tropical cyclone intensity forecasting
• AI weather models
• intensity underestimation
• maximum wind speed
• minimum central pressure

Innovation

• AIFS-TC
• tropical cyclone intensity forecasting
• AI weather models
• agentic coding
• post-processing correction