Meteorological drought forecasting for ungauged areas based on machine learning: Using long-range climate forecast and remote sensing data

Abstract

A high-resolution drought forecast model for ungauged areas was developed in this study. The Standardized Precipitation Index (SPI) and Standardized Precipitation Evapotranspiration Index (SPEI) with 3-, 6-, 9-, and 12-month time scales were forecasted with 1–6-month lead times at 0.05×0.05° resolution. The use of long-range climate forecast data was compared to the use of climatological data for periods with no observation data. Machine learning models utilizing drought-related variables based on remote sensing data were compared to the spatial interpolation of Kriging. Two performance measures were used; one is producer’s drought accuracy, defined as the number of correctly classified samples in extreme, severe, and moderate drought classes over the total number of samples in those classes, and the other is user’s drought accuracy, defined as the number of correctly classified samples in drought classes over the total number of samples classified to those classes. One of the machine learning models, extremely randomized trees, performed the best in most cases in terms of producer’s accuracy reaching up to 64%, while spatial interpolation performed better in terms of user’s accuracy up to 44%. The contribution of long-range climate forecast data was not significant under the conditions used in this study, but further improvement is expected if forecast skill is improved or a more sophisticated downscaling method is used. Simulated decreases of forecast error in precipitation and mean temperature were tested: the simulated decrease of forecast error in precipitation improves drought forecast while the decrease of forecast error in mean temperature does not contribute much. Although there is still some room for improvement, the developed model can be used for drought-related decision making in ungauged areas.