Drought Forecasting in a Brazilian Semi-Arid Region: LSTM Models Performance Evaluation
Authors:
- Anderson Batista Evangelista LimaALAnderson Batista Evangelista Lima
- João Victor Silveira RibeiroJRJoão Victor Silveira Ribeiro
- Luiz Henrique Barcelos DuarteLDLuiz Henrique Barcelos Duarte
- Érick Oliveira RodriguesÉRÉrick Oliveira Rodrigues
- Ana Carolina Vasques FreitasAFAna Carolina Vasques Freitas
- Sandro Carvalho IzidoroSISandro Carvalho Izidoro
Preprint
- 22 August 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
The Northern Mesoregion of Minas Gerais (NMMG) lies within the brazilian semi-arid region and is subject to recurrent and prolonged droughts. Despite the advances to drought forecast using machine learning techniques, evaluating the extent to which predictive models trained on specific locations can generalize their estimates to regional scales remain necessary. Thus, we proposed a spatial transferability experiment using Long Short-Term Memory (LSTM) models to predict the Standardized Precipitation Evapotranspiration Index (SPEI) with sliding and tumbling window techniques in five selected municipalities and their bordering districts in the NMMG. To evaluate the efficacy of this transferability, the results were contrasted with the locally trained model’s performance. Although this approach yielded robust performance in 71.8% of bordering districts with the tumbling window, it resulted in limited generalization capability in 28.2% due to the size of geographical area, differences in the rainfall spatial distribution and the presence of physiographic outliers.Keywords
This publication has 15 references indexed in Scilit:
- Global drought extremes in 2025Nature Reviews Earth & Environment, 2026
- Validation of ERA5 and ERA5-land reanalysis data for maximum and minimum temperatures in the Brazilian semiarid regionTheoretical and Applied Climatology, 2026
- Investigating the spatial propagation patterns of meteorological drought events and underlying mechanisms using complex network theory: A case study of the Yangtze River Basin, ChinaClimate Dynamics, 2024
- Standard precipitation-temperature index (SPTI) drought identification by fuzzy c-means methodologyEarth Science Informatics, 2024
- Identification of influential weather parameters and seasonal drought prediction in Bangladesh using machine learning algorithmScientific Reports, 2024
- Characteristics and propagation of meteorological and hydrological droughts in eastern Gansu, a typical semi‐arid region, ChinaInternational Journal of Climatology, 2023
- Combining deep learning methods and multi-resolution analysis for drought forecasting modelingEarth Science Informatics, 2023
- New improved Brazilian daily weather gridded data (1961–2020)International Journal of Climatology, 2022
- Assessing drought in the drylands of northeast Brazil under regional warming exceeding 4 °CNatural Hazards, 2020
- Hydrological drought explainedWIREs Water, 2015