Prediction of Drought and Flash Drought in Africa at the Seasonal-to-Subseasonal Scale using the Community Research Earth Digital Intelligence Twin Framework

TL;DR

This study develops DroughtFormer, a machine learning model within the CREDIT framework, to predict drought-related variables in Africa, demonstrating skillful forecasts up to 90 days ahead despite some limitations.

Contribution

Introduces DroughtFormer, a novel ML model that integrates multiple data sources and physical constraints to predict drought variables in Africa at seasonal-to-subseasonal scales.

Findings

DroughtFormer predicts soil moisture and vegetation health with significant skill.

The model provides stable forecasts up to 90 days ahead.

It captures climate anomalies but struggles with anomaly magnitudes.

Abstract

Droughts and flash droughts (rapidly developing droughts; FDs) remain impactful events that are known to desiccate landscape and destroy crops. In particular, droughts in Africa are often more impactful than in other locations, such as the United States or Europe, due to many regions in Africa heavily depending on local agriculture for sustenance. In recent years, large machine learning (ML) models, such as GraphCast and AIFS, have emerged as effective tools for global weather prediction. However, sparse data observations and few ML studies in Africa have left it unclear if these ML models retain their skill when focused on Africa. As such, this project seeks to examine the predictability of drought and FD in Africa using a CrossFormer model based on the Community Research Earth Digital Intelligence Twin (CREDIT) framework developed by NSF NCAR. Our CrossFormer model, termed DroughtFormer, incorporates variables from the ERA5 and GLDAS2 reanalyses and the IMERG and MODIS satellite observations, and employs dry air mass and moisture conservation, to predict soil moisture, vegetation health, and other drought-related surface variables. While DroughtFormer displayed lower accuracy in predicting precipitation and FD indices, it showed significant skill in predicting the remaining variables, delivering stable and skillful forecasts out to 90-day lead times (either beating out or having comparable skill to climatology). In particular, DroughtFormer skillfully represented climate anomalies for key variables, such as soil moisture (though it struggled with the magnitude of the anomalies). Thus, DroughtFormer showed significant promise in representing and predicting agricultural level drought in a region that is heavily impacted by drought events.