Water resource management plays a very important role in reducing the situation for water shortage in dry areas and enhancing the supply of water. Environment stewardship and sustainable development cannot be achieved without the proper management of water resources. The conventional methods of water resource management (WRM) are challenged by the inabilities to obtain real time data, process it correctly and take appropriate decisions. Novel solutions are needed to solve these challenges. The review discusses how sophisticated machine learning methods would enhance decision support system in the different sectors of water resource management that consist of groundwater management, stream flow forecasting, water distribution system, water quality, waste water treatment, water demand and consumption and water drainage system. In this paper, there are different machine learning models like Artificial Neural Network(ANN), Long Short-Term Memory(LSTM), Support Vector Mechanism(SVM) and Random Forest are applied in predicting Water Quality Index(WQI), streamflow forecasting, soil moisture prediction in agriculture setting. Through the development of the different models, water resource can be predicted in the quantitative manner which offers a scientific foundation of water resource management protection and planning. In order to offer new knowledge on the subject of ML applications in water resource management,this paper around the key basics, key applications ( prediction, clustering and reinforcement learning) and challenges that are currently being faced.
Khandelwal et al. (Sun,) studied this question.