Drought prediction models driven by meteorological and remote sensing data in Guanzhong Area, China

Drought is an important factor that limits economic and social development due to its frequent occurrence and profound influence. Therefore, it is of great significance to make accurate predictions of drought for early warning and disaster alleviation. In this paper, SPEI-1 was confirmed to classify drought grades in theGuanzhongArea, and theautoregressive integratedmoving average (ARIMA), random forest (RF) and support vectormachine (SVM)model were established. Meteorological data and remote sensing datawereused to derive thepredictionmodels. The results showed that (1) the SVMmodel performed the best when the models were developed using meteorological data, remote sensing data and a combination ofmeteorological and remote sensing data, but themodel’s corresponding kernel functions aredifferent and include linear, polynomial andGaussian radial basiskernel functions, respectively. (2) The RF model driven by the remote sensing data and the SVMmodel driven by the combinedmeteorological and remote sensing datawere found to perform better than themodel driven by the corresponding other data in the Guanzhong Area. It is difficult to accurately measure drought with the single meteorological data. Only by considering the combined factors canwemore accuratelymonitor and predict drought. This study can provide an important scientific basis for regional drought warnings and predictions.