Agriculture, meteorological, and hydrological drought is a natural hazard which affects ecosystems in the central India of Maharashtra state. Due to limited historical data for drought monitoring and forecasting available in the central India of Maharashtra state, implementing machine learning (ML) algorithms could allow for the prediction of future drought events. In this paper, we have focused on the prediction accuracy of meteorological drought in the semi-arid region based on the standardized precipitation index (SPI) using the random forest (RF), random tree (RT), and Gaussian process regression (GPR-PUK kernel) models. A different combination of machine learning models and variables has been performed for the forecasting of metrological drought based on the SPI-6 and 12 months. Models were developed using monthly rainfall data for the period of 2000-2019 at two meteorological stations, namely, Karanjali and Gangawdi, each representing a geographical region of Upper Godavari river basin area in the central India of Maharashtra state which frequently experiences droughts. Historical data from the SPI from 2000 to 2013 was processed to train the model into machine learning model, and the rest of the 2014 to 2019-year data were used for testing to forecast the SPI and metrological drought. The mean square error (MSE), root mean square error (RMSE), adjusted R2, Mallows' (Cp), Akaike's (AIC), Schwarz's (SBC), and Amemiya's PC were used to identify the best combination input model and best subregression analysis for both stations of SPI-6 and 12. The correlation coefficient ([Formula: see text]), mean absolute error (MAE), root mean square error (RMSE), relative absolute error (RAE), and root relative squared error (RRSE) were used to perform evaluation for SPI-6 and 12 months of both stations with RF, RT, and GPR-PUK kernel models during the training and testing scenarios. The results during testing phase revealed that the RF was found as the best model in forecasting droughts with values of [Formula: see text], MAE, RMSE, RAE (%), and RRSE (%) being 0.856, 0.551, 0.718, 74.778, and 54.019, respectively, for SPI-6 while 0.961, 0.361, 0.538, 34.926, and 28.262, respectively, for SPI-12 scales at Gangawdi station. Further, the respective values of evaluators at Karanjali station were 0.913 and 0.966, 0.541 and 0.386, 0.604 and 0.589, 52.592 and 36.959, and 42.315 and 31.394 for PUK kernel and RT models, respectively, during SPI-6 and SPI-12. Machine learning models are potential drought warning techniques because they take less time, have fewer inputs, and are less sophisticated than dynamic or scientific models.
The Damoh district, which is located in the central India and characterized by limestone, shales, and sandstone compact rock. The district has been facing groundwater development challenges and problems for several decades. To facilitate groundwater management, it is crucial to monitoring and planning based on geology, slope, relief, land use, geomorphology, and the types of the basaltic aquifer in the drought-groundwater deficit area. Moreover, the majority of farmers in the area are heavily dependent on groundwater for their crops. Therefore, delineation of groundwater potential zones (GPZ) is essential, which is defined based on various thematic layers, including geology, geomorphology, slope, aspect, drainage density, lineament density, topographic wetness index (TWI), topographic ruggedness index (TRI), and land use/land cover (LULC). The processing and analysis of this information were carried out using Geographic Information System (GIS) and Analytic Hierarchy Process (AHP) methods. The validity of the results was trained and tested using Receiver Operating Characteristic (ROC) curves, which showed training and testing accuracies of 0.713 and 0.701, respectively. The GPZ map was classified into five classes such as very high, high, moderate, low, and very low. The study revealed that approximately 45% of the area falls under the moderate GPZ, while only 30% of the region is classified as having a high GPZ. The area receives high rainfall but has very high surface runoff due to no proper developed soil and lack of water conservation structures. Every summer season show a declined groundwater level. In this context, results of study area are useful to maintain the groundwater under climate change and summer season. The GPZ map plays an important role in implementing artificial recharge structures (ARS), such as percolation ponds, tube wells, bore wells, cement nala bunds (CNBs), continuous contour trenching (CCTs), and others for development of ground level. This study is significant for developing sustainable groundwater management policies in semi-arid regions, that are experiencing climate change. Proper groundwater potential mapping and watershed development policies can help mitigate the effects of drought, climate change, and water scarcity, while preserving the ecosystem in the Limestone, Shales, and Sandstone compact rock region. The results of this study are essential for farmers, regional planners, policy-makers, climate change experts, and local governments, enabling them to understand the groundwater development possibilities in the study area.
This research was established to accurately forecast daily scale air quality index (AQI) which is an essential environmental index for decision-making. Researchers have projected different types of models and methodologies for AQI forecasting, such as statistical techniques, machine learning (ML), and most recently deep learning (DL) models. The modelling development was adopted for Delhi city, India which is a major city with air pollution issues simialir to entire urban cities of India especially during winter seasons. This research was predicted AQI using different versions of DL models including Long-Short Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM) and Bidirectional Recurrent Neural Networks (Bi-RNN) in addition to Kernel Ridge Regression (KRR). Results indicated that Bi-RNN model consistently outperformed the other models in both training and testing phases, while the KRR model consistently displayed the weakest performance. The outstanding performance of the models development displayed the requirement of adequate data to train the models. The outcomes of the models showed that LSTM, BI-LSTM, KRR had lower performance compared with Bi-RNN models. Statistically, Bi-RNN model attained maximum cofficient of determination (R2 = 0.954) and minimum root mean square error (RMSE = 25.755). The proposed model in this research revealed the robust predictable to provide a valuable base for decision-making in the expansion of combined air pollution anticipation and control policies targeted at addressing composite air pollution problems in the Delhi city.