Improving Typhoon Predictions by Integrating Data-Driven Machine Learning Models with Physics Models Based on the Spectral Nudging and Data Assimilation

TL;DR

This paper presents a hybrid typhoon prediction model combining machine learning and physics-based models, which improves forecast accuracy and interpretability by integrating data assimilation techniques.

Contribution

It introduces a novel ML-physics hybrid model using spectral nudging and data assimilation, enhancing typhoon intensity and track predictions over existing models.

Findings

Pangu_SP outperforms GFS_INIT and ECMWF IFS in typhoon track forecasts.

Hybrid model yields more accurate typhoon intensity predictions.

Data assimilation reduces errors in typhoon intensity forecasts.

Abstract

With the rapid development of data-driven machine learning (ML) models in meteorology, typhoon track forecasts have become increasingly accurate. However, current ML models still face challenges, such as underestimating typhoon intensity and lacking interpretability. To address these issues, this study establishes an ML-driven hybrid typhoon model, where forecast fields from the Pangu-Weather model are used to constrain the large-scale forecasts of the Weather Research and Forecasting model based on the spectral nudging method (Pangu_SP). The results show that forecasts from the Pangu_SP experiment obviously outperform those by using the Global Forecast System as the initial field (GFS_INIT) and from the Integrated Forecasting System of the European Centre for Medium-Range Weather Forecasts (ECMWF IFS) for the track forecast of Typhoon Doksuri (2023). The predicted typhoon cloud patterns from Pangu_SP are also more consistent with satellite observations. Additionally, the typhoon intensity forecasts from Pangu_SP are notably more accurate than those from the ECMWF IFS, demonstrating that the hybrid model effectively leverages the strengths of both ML and physical models. Furthermore, this study is the first to explore the significance of data assimilation in ML-driven hybrid dynamical systems. The findings reveal that after assimilating water vapor channels from the Advanced Geostationary Radiation Imager onboard Fengyun-4B, the errors in typhoon intensity forecasts are reduced.