Enhancing AI-Based Tropical Cyclone Track and Intensity Forecasting via Systematic Bias Correction

TL;DR

This paper introduces BaguanCyclone, a novel AI framework that significantly improves tropical cyclone track and intensity forecasts by addressing discretization errors and localized intensity extremes, outperforming existing models.

Contribution

The paper presents a unified AI system with probabilistic center refinement and region-aware intensity modules, advancing tropical cyclone forecasting accuracy and reliability.

Findings

Outperforms operational NWP and AI baselines on IBTrACS dataset

Accurately predicts re-intensification and complex cyclone behaviors

Enhances forecast precision for strong and re-entrant cyclones

Abstract

Tropical cyclones (TCs) pose severe threats to life, infrastructure, and economies in tropical and subtropical regions, underscoring the critical need for accurate and timely forecasts of both track and intensity. Recent advances in AI-based weather forecasting have shown promise in improving TC track forecasts. However, these systems are typically trained on coarse-resolution reanalysis data (e.g., ERA5 at 0.25 degree), which constrains predicted TC positions to a fixed grid and introduces significant discretization errors. Moreover, intensity forecasting remains limited especially for strong TCs by the smoothing effect of coarse meteorological fields and the use of regression losses that bias predictions toward conditional means. To address these limitations, we propose BaguanCyclone, a novel, unified framework that integrates two key innovations: (1) a probabilistic center refinement module that models the continuous spatial distribution of TC centers, enabling finer track precision; and (2) a region-aware intensity forecasting module that leverages high-resolution internal representations within dynamically defined sub-grid zones around the TC core to better capture localized extremes. Evaluated on the global IBTrACS dataset across six major TC basins, our system consistently outperforms both operational numerical weather prediction (NWP) models and most AI-based baselines, delivering a substantial enhancement in forecast accuracy. Remarkably, BaguanCyclone excels in navigating meteorological complexities, consistently delivering accurate forecasts for re-intensification, sweeping arcs, twin cyclones, and meandering events. Our code is available at https://github.com/DAMO-DI-ML/Baguan-cyclone.