The water level of the Urmia Lake Basin (ULB), located in the northwest of Iran, started to decline dramatically about two decades ago. As a result, the area has become the focus of increasing scientific research. In order to improve understanding of the connections between declining lake level and changing local drought conditions, three common drought indices are employed to analyze the period 1981–2018: The Standard Precipitation Index (SPI), the Standard Precipitation-Evaporation Index (SPEI), and the Standardized Snow Melt and Rain Index (SMRI). Although rainfall is a significant indicator of water availability, temperature is also a key factor since it determines rates of evapotranspiration and snowmelt. These different processes are captured by the three drought indices mentioned above to describe drought in the catchment. Therefore, the main objective of this paper is to provide a comparative analysis of drought over the ULB by incorporating different drought indices. Since there is not enough long-term observational data of sufficiently high density for the ULB region, ECMWF Reanalysis data version 5(ERA5) has been used to estimate SPI, SPEI, and SMRI drought indicators. These are shown to work well, with AUC-ROC > 0.9, in capturing different classes of basin drought characteristics. The results show a downward trend for SPEI and SMRI (but not for SPI), suggesting that both evaporation and lack of snowmelt exacerbate droughts. Owing to the increasing temperatures in the basin and the decrease in snowfall, drought events have become particularly pronounced in the SPEI and SMRI time series since 1995. No significant SMRI drought was detected prior to 1995, thus indicating that sufficient snowfall was available at the beginning of the study period. The study results also reveal that the decrease in lake water level from 2010 to 2018 was not only caused by changes in the water balance components, but also by unsustainable water management.

Although many meteorological prediction models have been developed recently, their accuracy is still unreliable. Post-processing is a task for improving meteorological predictions. This study proposes a post-processing method for the Climate Forecast System Version 2 (CFSV2) model. The applicability of the proposed method is shown in Iran for observation data from 1982 to 2017. This study designs software to perform post-processing in meteorological organizations automatically. From another point of view, this study presents a decision support system (DSS) for controlling precipitation-based natural side effects such as flood disasters or drought phenomena. It goes without saying that the proposed DSS model can meet sustainable development goals (SDGs) with regards to a grantee of human health and environmental protection issues. The present study, for the first time, implemented a platform based on a graphical user interface due to the prediction of precipitation with the application of machine learning computations. The present research developed an academic idea into an industrial tool. The final finding of this paper is to introduce a set of efficient machine learning computations where the random forest (RF) algorithm has a great level of accuracy with more than a 0.87 correlation coefficient compared with other machine learning methods.

Southwest Asia has different climate types including arid, semiarid, Mediterranean, and temperate regions. Due to the complex interactions among components of the Earth system, forecasting precipitation is a difficult task in such large regions. The aim of this paper is to propose a learning approach, based on artificial neural network (ANN) and random forest (RF) algorithms for post-processing the output of forecasting models, in order to provide a multi-model ensemble forecasting of monthly precipitation in southwest Asia. For this purpose, four forecasting models, including GEM-NEMO, NASA-GEOSS2S, CanCM4i, and COLA-RSMAS-CCSM4, included in the North American multi-model ensemble (NMME) project, are considered for the ensemble algorithms. Since each model has nine different lead times, a total of 108 different ANN and RF models are trained for each month of the year. To train the proposed ANN an RF models, the ERA5 reanalysis dataset is employed. To compare the performance of the proposed algorithms, four performance evaluation criteria are calculated for each model. The results indicate that the performance of the ANN and RF post-processing is better than that of the individual NMME models. Moreover, RF outperformed ANN for all lead times and months of the year.