From AI Weather Prediction to Infrastructure Resilience: A Correction-Downscaling Framework for Tropical Cyclone Impacts

TL;DR

This paper presents ACDF, a novel AI-based framework that transforms coarse global weather forecasts into detailed, asset-scale risk assessments for tropical cyclones, enhancing infrastructure resilience and early warning capabilities.

Contribution

Introduction of ACDF, a new correction-downscaling framework that accurately converts AI weather forecasts into high-resolution, actionable risk data for infrastructure impact analysis.

Findings

Reduces wind-speed MAE by 38.8% compared to Pangu-Weather

Reproduces observed high-wind tails and identifies high-risk corridors

Runs efficiently in 25 seconds per 12-hour cycle on a single GPU

Abstract

This paper addresses a missing capability in infrastructure resilience: turning fast, global AI weather forecasts into asset-scale, actionable risk. We introduce the AI-based Correction-Downscaling Framework (ACDF), which transforms coarse AI weather prediction (AIWP) into 500-m, unbiased wind fields and transmission tower/line failure probabilities for tropical cyclones. ACDF separates storm-scale bias correction from terrain-aware downscaling, preventing error propagation while restoring sub-kilometer variability that governs structural loading. Tested on 11 typhoons affecting Zhejiang, China under leave-one-storm-out evaluation, ACDF reduces station-scale wind-speed MAE by 38.8% versus Pangu-Weather, matches observation-assimilated mesoscale analyses, yet runs in 25 s per 12-h cycle on a single GPU. In the Typhoon Hagupit case, ACDF reproduced observed high-wind tails, isolated a coastal high-risk corridor, and flagged the line that failed, demonstrating actionable guidance at tower and line scales. ACDF provides an end-to-end pathway from AI global forecasts to operational, impact-based early warning for critical infrastructure.