VQLTI: Long-Term Tropical Cyclone Intensity Forecasting with Physical Constraints

TL;DR

This paper introduces VQLTI, a novel deep learning framework that enhances long-term tropical cyclone intensity forecasting by integrating physical knowledge and constraints, significantly reducing forecast errors over 24 to 120 hours.

Contribution

VQLTI is the first framework to transfer TC intensity into a discrete latent space while incorporating physical constraints and external physical knowledge for improved long-term forecasts.

Findings

Achieves state-of-the-art results for 24h to 120h forecasts.

Reduces MSW forecast error by up to 42.51% compared to ECMWF-IFS.

Effectively integrates physical constraints into deep learning for meteorological forecasting.

Abstract

Tropical cyclone (TC) intensity forecasting is crucial for early disaster warning and emergency decision-making. Numerous researchers have explored deep-learning methods to address computational and post-processing issues in operational forecasting. Regrettably, they exhibit subpar long-term forecasting capabilities. We use two strategies to enhance long-term forecasting. (1) By enhancing the matching between TC intensity and spatial information, we can improve long-term forecasting performance. (2) Incorporating physical knowledge and physical constraints can help mitigate the accumulation of forecasting errors. To achieve the above strategies, we propose the VQLTI framework. VQLTI transfers the TC intensity information to a discrete latent space while retaining the spatial information differences, using large-scale spatial meteorological data as conditions. Furthermore, we leverage the forecast from the weather prediction model FengWu to provide additional physical knowledge for VQLTI. Additionally, we calculate the potential intensity (PI) to impose physical constraints on the latent variables. In the global long-term TC intensity forecasting, VQLTI achieves state-of-the-art results for the 24h to 120h, with the MSW (Maximum Sustained Wind) forecast error reduced by 35.65%-42.51% compared to ECMWF-IFS.