Long-term drought prediction using deep neural networks based on geospatial weather data

TL;DR

This paper presents a deep neural network approach for long-term drought prediction using geospatial weather data, demonstrating the effectiveness of Transformer and ConvLSTM models across different regions.

Contribution

Introduces an end-to-end spatio-temporal neural network framework for drought forecasting with open climate data, evaluating multiple models across diverse environmental regions.

Findings

Transformer model (EarthFormer) excels in short-term forecasts up to six months.

ConvLSTM performs best for longer-term drought prediction.

The approach achieves high accuracy in PDSI prediction across five regions.

Abstract

The problem of high-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. Yet, it is still unsolved with reasonable accuracy due to data complexity and aridity stochasticity. We tackle drought data by introducing an end-to-end approach that adopts a spatio-temporal neural network model with accessible open monthly climate data as the input. Our systematic research employs diverse proposed models and five distinct environmental regions as a testbed to evaluate the efficacy of the Palmer Drought Severity Index (PDSI) prediction. Key aggregated findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts. At the same time, the Convolutional LSTM excels in longer-term forecasting.