Long-term drought prediction using deep neural networks based on geospatial weather data
This work addresses drought forecasting for agriculture planning and insurance, but it appears incremental as it compares existing models like Transformer and Convolutional LSTM on a specific domain.
The paper tackled long-term drought prediction up to a year ahead using deep neural networks on geospatial weather data, finding that a Transformer model (EarthFormer) excels in short-term forecasts up to six months, while Convolutional LSTM performs better for longer-term forecasting.
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.