Drought prediction serves as an early warning to the effective management of water resources to avoid the drought impact. The drought prediction is carried out for arid, semi-arid, sub-humid, and humid climate types in the desert region. The drought is predicted using Standardized precipitation evapotranspiration index (SPEI). The application of machine learning methods such as artificial neural network (ANN), K-Nearest Neighbors (KNN), and Deep Neural Network (DNN) for the drought prediction suitability is analyzed. The SPEI is predicted using the aforesaid machine learning methods with inputs used to calculate SPEI. The predictions are assessed using statistical indicators. The coefficient of determination of ANN, KNN, and DNN are 0.93, 0.83, and 0.91 respectively. The mean square error of ANN, KNN, and DNN are 0.065, 0.512, and 0.52 respectively. The mean absolute error of ANN, KNN, and DNN are 0.001, 0.512, and 0.01 respectively. Based on results of statistical indicator and validations it is found that DNN is suitable to predict drought in all the four types of desert region.

This chapter aims to develop landslide susceptibility maps for the Sikkim state in India by combining the analytical hierarchy process, geographic information systems, and remote sensing. The delineation of the landslide susceptibility maps has taken into consideration a variety of data such as density of lineament, slope, lithology, aspect, land cover and land use, road buffer, rainfall, and drainage density. Using both Landsat 8 and ground data in a GIS framework, spatial distribution of maps and map layers of required themes were produced. The appropriate weights based on the Saaty's scale were given to these thematic layers in accordance with their respective significance in the occurrence of landslides in the study area. According to the study area's demarcated landslide susceptibility map, the risk levels were very low (12.52%), low (21.12%), moderate (8.05%), high (31.13%), and very high (27.18%). The accuracy of the study region is computed using the AUC curve using the AHP model landslide map and inventory map, which shows good result with 70% accuracy.

Meticulous knowledge of evapotranspiration is vital for managing water resources. In this study, we used Landsat 8 to assess and evaluate four remote sensing-based energy balance models: SEBAL, SSEB, TSEB, and S-SEBI to predict evapotranspiration (ET) for seasonal crops in the desert environment. All models performed well in the prediction of spatial-temporal variation of ET. The actual ET of crops for different days of the year has been calculated using the Penman-Monteith equation and crop coefficients. The ET estimated for Kharif crops is higher than the Rabi crops. With different land cover, NDVI, and land surface temperature, the change of ET and transpiration is analysed. The seasonal transpiration is estimated using the trapezoidal and Gaussian fitting method. SSEB resulted in higher accuracy for Kharif crops, similarly TSEB model for Rabi crops. The spatiotemporal extent knowledge of ET can assist reservoir managers in allocating water for agriculture and other uses.