Generating High-Resolution and Long-Term SPEI Dataset over Southwest China through Downscaling EEAD Product by Machine Learning

Drought is an event of shortages in the water supply, whether atmospheric, surface water or ground water. Prolonged droughts have negative impacts on ecosystems, agriculture, society, and the economy. Although existing drought index products are widely utilized in drought monitoring, the coarse spatial resolution greatly limits their applications on regional or local scales. Machine learning driven by remote sensing observations offers an opportunity to monitor regional scale droughts. However, the limited time range of remote sensing observations such as vegetation index (VI) resulted in a substantial gap in generating high resolution drought index products before 2000. This study generated spatiotemporally continuous Standardized Precipitation Evapotranspiration Index (SPEI) data spanning from 1901-2018 in southwestern China by machine learning. It indicated that four Classification and Regression Tree (CART) approaches, decision trees (DT), random forest (RF), gradient boosted regression trees (GBRT) and extra trees (ET), can provide valid local drought information by downscaling the Estacion Experimental de Aula Dei (EEAD) data. The in-situ SPEI dataset produced by the Penman-Monteith method was used as a benchmark to evaluate the temporal and spatial performance of the downscaled SPEI. In addition, the necessity of VI in SPEI downscaling was also assessed. The results showed that: (1) the ET-based product has the best performance (R-2 = 0.889, MAE = 0.232, RMSE = 0.432); (2) the VI provides no significant improvement for SPEI re-construction; (3) topography exerts an obvious influence on the downscaling process, and (4) the downscaled SPEI shows more consistency with the in-situ SPEI compared with EEAD SPEI. The proposed method can be easily extended to other areas without in-situ data and enhance the ability of long-term drought monitoring.