As one of nature’s most destructive calamities, floods cause fatalities, property destruction, and infrastructure damage, affecting millions of people worldwide. Due to its ability to accurately anticipate and successfully mitigate the effects of floods, flood modeling is an important approach in flood control. This study provides a thorough summary of flood modeling’s current condition, problems, and probable future directions. The study of flood modeling includes models based on hydrologic, hydraulic, numerical, rainfall–runoff, remote sensing and GIS, artificial intelligence and machine learning, and multiple-criteria decision analysis. Additionally, it covers the heuristic and metaheuristic techniques employed in flood control. The evaluation examines the advantages and disadvantages of various models, and evaluates how well they are able to predict the course and impacts of floods. The constraints of the data, the unpredictable nature of the model, and the complexity of the model are some of the difficulties that flood modeling must overcome. In the study’s conclusion, prospects for development and advancement in the field of flood modeling are discussed, including the use of advanced technologies and integrated models. To improve flood risk management and lessen the effects of floods on society, the report emphasizes the necessity for ongoing research in flood modeling.

The management of water resources depends heavily on hydrological prediction, and advances in machine learning (ML) present prospects for improving predictive modelling capabilities. This study investigates the use of a variety of widely used machine learning algorithms, such as CatBoost, ElasticNet, k-Nearest Neighbors (KNN), Lasso, Light Gradient Boosting Machine Regressor (LGBM), Linear Regression (LR), Multilayer Perceptron (MLP), Random Forest (RF), Ridge, Stochastic Gradient Descent (SGD), and the Extreme Gradient Boosting Regression Model (XGBoost), to predict the river inflow of the Garudeshwar watershed, a key element in planning for flood control and water supply. The substantial engineering feature used in the study, which incorporates temporal lag and contextual data based on Indian seasons, leads it distinctiveness. The study concludes that the CatBoost method demonstrated remarkable performance across various metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R²) values, for both training and testing datasets. This was accomplished by an in-depth investigation and model comparison. In contrast to CatBoost, XGBoost and LGBM demonstrated a higher percentage of data points with prediction errors exceeding 35% for moderate inflow numbers above 10,000. CatBoost established itself as a reliable method for hydrological time-series modelling, easily managing both categorical and continuous variables, and thereby greatly enhancing prediction accuracy. The results of this study highlight the value and promise of widely used machine learning algorithms in hydrology and offer valuable insights for academics and industry professionals.

Floods are a devastating natural calamity that may seriously harm both infrastructure and people. Accurate flood forecasts and control are essential to lessen these effects and safeguard populations. By utilizing its capacity to handle massive amounts of data and provide accurate forecasts, deep learning has emerged as a potent tool for improving flood prediction and control. The current state of deep learning applications in flood forecasting and management is thoroughly reviewed in this work. The review discusses a variety of subjects, such as the data sources utilized, the deep learning models used, and the assessment measures adopted to judge their efficacy. It assesses current approaches critically and points out their advantages and disadvantages. The article also examines challenges with data accessibility, the interpretability of deep learning models, and ethical considerations in flood prediction. The report also describes potential directions for deep-learning research to enhance flood predictions and control. Incorporating uncertainty estimates into forecasts, integrating many data sources, developing hybrid models that mix deep learning with other methodologies, and enhancing the interpretability of deep learning models are a few of these. These research goals can help deep learning models become more precise and effective, which will result in better flood control plans and forecasts. Overall, this review is a useful resource for academics and professionals working on the topic of flood forecasting and management. By reviewing the current state of the art, emphasizing difficulties, and outlining potential areas for future study, it lays a solid basis. Communities may better prepare for and lessen the destructive effects of floods by implementing cutting-edge deep learning algorithms, thereby protecting people and infrastructure.

Industrial and municipal wastes, agricultural contamination owing to pesticides and chemical hazards, seawater intrusion in coastal areas, and other factors damage groundwater. In several towns and industrial clusters across India, this is becoming a rising subject of concern. Groundwater is difficult to contaminate, but once contaminated, it is difficult to clean up. It is critical to attain this goal using a variety of aquifer vulnerability assessment approaches. All of these strategies rely on process models as well as statistical or overlay index methodologies. Groundwater vulnerability is a major topic of discussion due to declining groundwater levels and rising contamination, posing a serious threat to the environment and water sources. To identify the risk and to assess the vulnerability, extensive research has been carried out among all the methods based on different parameters and different indexes. The DRASTIC method is one of the most important and accurate of the overlay and index methods for the assessment of groundwater vulnerability. This research study is a systematic analysis of the available research articles on the applications of the DRASTIC and Modified DRASTIC (DRASTIC-L) performance management process on Geographical Information Systems (GIS). This research also reveals research gaps in the various groundwater vulnerability assessment approaches, as well as their limits and hypotheses. This study discovered that integrating GIS with DRASTIC is the most effective and accurate way for determining groundwater vulnerability. In agricultural, arid, semi-arid, and basaltic zones, the modified DRASTIC model also outperforms the traditional DRASTIC model.

Groundwater is a natural resource used for drinking, agriculture, and industry, apart from surface water. Its quality should be assessed regularly, and the condition of water resources should be maintained accordingly. The most common analytical method for describing and assessing the general water quality is the Water Quality Index (WQI). This study aims to assess the South Gujarat Region’s groundwater quality using the WQI. Various physicochemical parameters like pH, turbidity, total dissolved solids, total hardness, calcium, magnesium, chloride, sulphate, nitrate, fluorides, and total alkalinity are considered for the present study. The data period from 2018 to 2022 is considered for the same. The Weighted Arithmetic Water Quality Index Technique is used to evaluate these data. For checking the potability of the parameters within the acceptable limit, the Indian Standard Drinking Water Specification code (IS: 10050-2012) is adopted. According to the study mentioned above, a few wells’ groundwater quality has been found to be higher than the WQI value. It is also observed that four wells were found unsuitable for drinking purposes in 2018. It is noted that if the WQI value of groundwater is above 51, it is considered harmful to human health; therefore, it requires some kind of processing before use. This study will be beneficial to the policymakers for identifying and providing details about groundwater quality in the form of a specific value, i.e., WQI.

Land use/land cover (LULC) and climate are two crucial environmental factors that impact watershed hydrology worldwide. The current study seeks to comprehend how the evolving climate and LULC patterns are impacting the hydrology of the Mahanadi Reservoir catchment. A semi-distributed Soil and Water Assessment Tool (SWAT) model was utilized to simulate various water balance elements. Twelve distinct scenarios were developed by combining three different climatic data periods (1985–1996, 1997–2008, and 2009–2020) with four sets of land use maps (1985, 1995, 2005, and 2014). The SWAT model demonstrated strong performance in simulating monthly stream flows throughout the calibration and validation phases. The study reveals that changes in LULC have a distinct effect on the environment. Specifically, the changes in LULC lead to heightened streamflow and reduced evapotranspiration (ET). These changes are mainly attributed to amplified urbanization and the diminished presence of water bodies, forest cover, and barren land within the Mahanadi Reservoir catchment. The combined impact of climate change and LULC shifts reveals complex interactions. Therefore, the present study offers an understanding of how changes in climate and land use over the past few decades have influenced the hydrological behavior of the Mahanadi Reservoir catchment in Chhattisgarh. The findings of this study have the potential to offer advantages to governmental bodies, policymakers, water resource engineers, and planners seeking effective strategies for water resource management. These strategies would be particularly relevant in the context of climate change and land use/land cover changes in ecological regions similar to those of the Mahanadi Reservoir catchment. In addition, a rational regulatory framework for land use patterns is essential for assisting stakeholders in managing water resources and appropriately developing the entire catchment.