Ant-inspired metaheuristic algorithms known as ant colony optimization (ACO) offer an approach that has the ability to solve complex problems in both discrete and continuous domains. ACOs have gained significant attention in the field of water resources management, since many problems in this domain are non-linear, complex, challenging and also demand reliable solutions. The aim of this study is to critically review the applications of ACO algorithms specifically in the field of hydrology and hydrogeology, which include areas such as reservoir operations, water distribution systems, coastal aquifer management, long-term groundwater monitoring, hydraulic parameter estimation, and urban drainage and storm network design. Research articles, peer-reviewed journal papers and conference papers on ACO were critically analyzed to identify the arguments and research findings to delineate the scope for future research and to identify the drawbacks of ACO. Implementation of ACO variants is also discussed, as hybrid and modified ACO techniques prove to be more efficient over traditional ACO algorithms. These algorithms facilitate formulation of near-optimal solutions, and they also help improve cost efficiency. Although many studies are attempting to overcome the difficulties faced in the application of ACO, some parts of the mathematical analysis remain unsolved. It is also observed that despite its popularity, studies have not been successful in incorporating the uncertainty in ACOs and the problems of dimensionality, convergence and stability are yet to be resolved. Nevertheless, ACO is a potential area for further research as the studies on the applications of these techniques are few.

The presence of uranium in groundwater is a cause of concern all over the world. In mineralized regions where elevated concentrations of uranium are possible in groundwater, mining activities can further degrade the water quality. Hence, it is essential to document the baseline uranium concentration in groundwater before the commencement of mining. This study was carried out with the objective of assessing the concentration of uranium in groundwater around a proposed uraninite mining site in the Gogi region, Karnataka, India. Gogi is a village in the Yadgir district of Karnataka where groundwater is the main source of water for domestic needs. The uranium mineralized zone in this region occurs along the major E-W trending Gogi-Kurlagere fault at a depth of about 150 m. Groundwater samples were collected every three months from January 2020 to October 2020 from 52 wells located in this area. The concentration of uranium in groundwater ranged from 1.5 ppb to 267 ppb. The USEPA and WHO have recommended a permissible limit of 30 ppb, while the Atomic Energy Regulatory Board of India has a limit of 60 ppb for the purpose of drinking water. Based on these permissible limits for uranium in drinking water, concentrations exceeded the limit in about 25% of wells within 20 km from the mineralized region. Wells present in the granitic and limestone terrain exhibited higher concentrations of uranium in this area. Uranium concentration in groundwater changes depending on the degree of weathering, lithology, and rainfall recharge. This study will serve as a baseline and will help to assess the impact of mining activities in this region in the future. In wells where the uranium concentration exceeds permissible limits, it is suggested not to use groundwater directly for drinking purposes. These sites need to be explored further for the possible presence of uranium-bearing minerals.

The quality of groundwater is of utmost importance, as it directly impacts human health and the environment. In major parts of the world, groundwater is the main source of drinking water, hence it is essential to periodically monitor its quality. Conventional water-quality monitoring techniques involve the periodical collection of water samples and subsequent analysis in the laboratory. This process is expensive, time-consuming and involves a lot of manual labor, whereas data-driven models based on artificial intelligence can offer an alternative and more efficient way to predict groundwater quality. In spite of the advantages of such models based on artificial neural network (ANN) and ant colony optimization (ACO), no studies have been carried out on the applications of these in the field of groundwater contamination. The aim of our study is to build an ant colony optimized neural network for predicting groundwater quality parameters. We have proposed ANN comprising of six hidden layers. The approach was validated using our groundwater quality dataset of a hard rock region located in the northern part of Karnataka, India. Groundwater samples were collected by us once every 4 months from March 2014 to October 2020 from 50 wells in this region. These samples were analyzed for the pH, electrical conductivity, Na+, Ca+, K+, Mg2+, HCO3−, F−, Cl− and U+. This temporal dataset was split for training, testing and validation of our model. Metrics such as R2 (Coefficient of Determination), RMSE (Root Mean Squared Error), NSE (Nash–Sutcliffe efficiencies) and MAE (Mean Absolute Error) were used to evaluate the prediction error and model performance. These performance evaluation metrics indicated the efficiency of our model in predicting the temporal variation in groundwater quality parameters. The method proposed can be used for prediction and it will aid in modifying or reducing the temporal frequency of sample collection to save time and cost. The study confirms that the combination of ANN with ACO is a promising tool to optimize weights while training the network, and for prediction of groundwater quality.