Building early drought forecasting model in the Dak Dak province using machine learning algorithms

Abstract

Abstract Drought is a natural disaster that has severe economic and environmental consequences. In the Dak Lak province, drought has frequently occurred in recent years, causing severe water scarcity in the dry season. Therefore, drought forecasting information will be essential to take timely response measures for water resource management and agricultural production. This study used machine learning methods for drought forecasting in the Dak Lak province. The three machine learning models used in this study include Artificial Neural Network (ANN), Support Vector Regression (SVR), and Random Forest (RF), combined with the use of the Standardized Precipitation - Evapotranspiration Index (SPEI) to predict meteorological droughts. Results showed that the ANN models give high accuracy in the drought prediction for the study area.