Drought forecasting using a hybrid neural architecture for integrating time series and static data
This work addresses drought forecasting for early warning systems and adaptive management, offering a novel method for handling heterogeneous data in climate tasks.
The paper tackled drought forecasting by developing a hybrid neural architecture that integrates time series and static data, achieving state-of-the-art performance on the DroughtED dataset with reliable prediction of USDM categories.
Reliable forecasting is critical for early warning systems and adaptive drought management. Most previous deep learning approaches focus solely on homogeneous regions and rely on single-structured data. This paper presents a hybrid neural architecture that integrates time series and static data, achieving state-of-the-art performance on the DroughtED dataset. Our results illustrate the potential of designing neural models for the treatment of heterogeneous data in climate related tasks and present reliable prediction of USDM categories, an expert-informed drought metric. Furthermore, this work validates the potential of DroughtED for enabling location-agnostic training of deep learning models.