Dual-Branched Spatio-Temporal Fusion Network for Multihorizon Tropical Cyclone Track Forecast

Abstract

A tropical cyclone (TC) is a typical extreme tropical weather system, which could cause serious disasters in transit areas. Accurate TC track forecasting is the key to reducing casualties and damages, however, long-term forecasting of TCs is a challenging problem due to their extremely high dynamics and uncertainty. Existing TC track forecasting methods mainly focus on utilizing a single modality of source data, meanwhile, suffer from limited long-term forecasting capability and high computational complexity. In this paper, we propose to address the above challenges from a new perspective -by utilizing largescale spatio-temporal multimodal historical data and advanced deep learning techniques. A novel multi-horizon tropical cyclone track forecasting model named Dual-Branched spatio-temporal Fusion Network (DBF-Net) is proposed and evaluated. DBF-Net contains a TC features branch that extracts temporal features from 2D state vectors and a pressure field branch that extracts spatio-temporal features from reanalysis 3D pressure field. We show that with the above design, DBF-Net can fully exploit the implicit associations of multimodal data, achieving advantages that unimodal data-based method does not have. Extensive experiments on 39 years of historical TCs track data in the Northwest Pacific show that our DBF-Net achieves significant accuracy improvement compared with previous TCs track forecast methods.

MGTCF: Multi-Generator Tropical Cyclone Forecasting with Heterogeneous Meteorological Data

“…Data 2d we used, geopotential height (GPH), were from the fifth-generation atmospheric reanalysis of the global climate (ERA5) (ECMWF 2022) by the European Centre for Medium-Range Weather Forecasts (ECMWF). We followed (Liu et al 2022) and chose the 500 hPa GPH data to describe the pressure structure of TCs.…”

“…Therefore, predictions using only single-modal data are not sufficiently precise. Then, heterogeneous meteorological data were used in various TC prediction methods (Giffard-Roisin et al 2020;Liu et al 2022). These data include the inherent attribute data of TC called Data 1d (e.g., longitude, latitude, and wind) and meteorological grid data called Data 2d (e.g., satellite images and meteorological fields).…”

Spatio-Temporal Alignment and Track-To-Velocity Module for Tropical Cyclone Forecast

“…The idea of using past track data and reanalysis fields (e.g., wind and pressure 3D fields) to obtain the longitudinal and latitudinal displacement of TCs was first proposed by Giffard-Roisin et al [10], and utilized multi-branch network merge features from different data modalities. A similar idea was also proposed by Liu et al [12], who employed dual-branched 3D-CNN and LSTM to encode meteorological field data and temporal data separately, and utilized an LSTM decoder to fuse different features. However, the concatenation of the two types of features in the multi-branch network hinders the preservation of spatial information.…”

Hierarchical Predictions of Fine-to-Coarse Time Span and Atmospheric Field Reconstruction for Typhoon Track Prediction

“…Therefore, determining how to better fuse the 3D TC atmospheric state with 2D features has become a hot research topic in recent years [29,30]. Guangning Xu et al [31,32] proposed a fusion of convolutional networks and recurrent networks, combined with segmented training, to fully integrate 2D positional features and 3D geopotential features. This approach further enhances the accuracy of trajectory prediction.…”