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

2023/09/12 by Alexander Marusov, Vsevolod Grabar, Marusov, Alexander +9 · 1 citation
Environmental Science · #Climate variability and models #FOS: Computer and information sciences #Hydrology and Drought Analysis #Hydrology and Watershed Management Studies #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2309.06212

openalex publication_date 2023/09/12 · openalex created_date 2023/09/14 · openalex updated_date 2026/07/28

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.

Cited by

• A theoretical framework for self-supervised contrastive learning for continuous dependent data

Related

• Predicting spatial distribution of Palmer Drought Severity Index
• Drought forecasting using a hybrid neural architecture for integrating time series and static data
• DroughtSet: Understanding Drought Through Spatial-Temporal Learning
• A Machine Learning Approach to Long-Term Drought Prediction using Normalized Difference Indices Computed on a Spatiotemporal Dataset
• AI-driven U.S. drought prediction using machine learning and deep learning