We assessed the changes in meteorological drought severity and drought return periods during cropping seasons in Afghanistan for the period of 1901 to 2010. The droughts in the country were analyzed using the standardized precipitation evapotranspiration index (SPEI). Global Precipitation Climatology Center rainfall and Climate Research Unit temperature data both at 0.5° resolutions were used for this purpose. Seasonal drought return periods were estimated using the values of the SPEI fitted with the best distribution function. Trends in climatic variables and SPEI were assessed using modified Mann–Kendal trend test, which has the ability to remove the influence of long-term persistence on trend significance. The study revealed increases in drought severity and frequency in Afghanistan over the study period. Temperature, which increased up to 0.14 °C/decade, was the major factor influencing the decreasing trend in the SPEI values in the northwest and southwest of the country during rice- and corn-growing seasons, whereas increasing temperature and decreasing rainfall were the cause of a decrease in SPEI during wheat-growing season. We concluded that temperature plays a more significant role in decreasing the SPEI values and, therefore, more severe droughts in the future are expected due to global warming.

Ensemble machine learning models have been widely used in hydro-systems modeling as robust prediction tools that combine multiple decision trees. In this study, three newly developed ensemble machine learning models, namely gradient boost regression (GBR), AdaBoost regression (ABR) and random forest regression (RFR) are proposed for prediction of suspended sediment load (SSL), and their prediction performance and related uncertainty are assessed. The SSL of the Mississippi River, which is one of the major world rivers and is significantly affected by sedimentation, is predicted based on daily values of river discharge (Q) and suspended sediment concentration (SSC). Based on performance metrics and visualization, the RFR model shows a slight lead in prediction performance. The uncertainty analysis also indicates that the input variable combination has more impact on the obtained predictions than the model structure selection.

Suspended sediment load (SSL) is one of the essential hydrological processes that affects river engineering sustainability. Sediment has major influence on the operation of dams and reservoir capacity. This investigation is aimed at exploring a new version of machine learning models (i.e., data mining), including M5P, attribute selected classifier (AS M5P), M5Rule (M5R), and K Star (KS) models for SSL prediction at the Trenton meteorological station on the Delaware River, USA. Different input scenarios were examined based on the river flow discharge and sediment load database. The performance of the applied data mining models was evaluated using various statistical metrics and graphical presentation. Among the applied data mining models, the M5P model gave a superior prediction result. The current and one-day lead time river flow and sediment load were the influential predictors for one-day-ahead SSL prediction. Overall, the applied data mining models achieved excellent predictions of SSL process.