Dual-Branched Spatio-temporal Fusion Network for Multi-horizon Tropical Cyclone Track Forecast
This work addresses the challenge of multi-horizon tropical cyclone track forecasting for meteorology and disaster management, though it appears incremental as it builds on existing encoder-decoder architectures for feature fusion.
The paper tackles the problem of accurately forecasting tropical cyclone tracks by efficiently mining multi-modal spatio-temporal data, proposing a dual-branched network that fuses features from 1D TC data and 2D pressure fields, achieving significant improvement over existing methods in experiments on Northwest Pacific data.
Tropical cyclone (TC) is an extreme tropical weather system and its trajectory can be described by a variety of spatio-temporal data. Effective mining of these data is the key to accurate TCs track forecasting. However, existing methods face the problem that the model complexity is too high or it is difficult to efficiently extract features from multi-modal data. In this paper, we propose the Dual-Branched spatio-temporal Fusion Network (DBF-Net) -- a novel multi-horizon tropical cyclone track forecasting model which fuses the multi-modal features efficiently. DBF-Net contains a TC features branch that extracts temporal features from 1D inherent features of TCs and a pressure field branch that extracts spatio-temporal features from reanalysis 2D pressure field. Through the encoder-decoder-based architecture and efficient feature fusion, DBF-Net can fully mine the information of the two types of data, and achieve good TCs track prediction results. Extensive experiments on historical TCs track data in the Northwest Pacific show that our DBF-Net achieves significant improvement compared with existing statistical and deep learning TCs track forecast methods.