River Network Optimization Using Machine Learning

Lack of potable water is a perennial problem in the day-to-day life of mankind around the world. The demand-supply variations have been on an increasing trend for so many years in different developing countries. To address this prevailing issue is the need of the hour for the society and the relevant government agencies. In this paper, as an explorative approach, we address this predominant issue in the form of an alternate solution which re-routes the course of the natural water sources, like rivers, through those areas, where the water supply is minimal in comparison with the demand, in a cost-effective and highly beneficial manner. Our analysis and discussions are more prone to Indian scenario where India is one of the worst affected fast developing countries for the water crisis. This involves the consideration of the physical, ecological and social characteristics of the lands on the route that fall under the course of the river and also the regions dependent on its flow. In order to understand and predict the optimized new flow paths to divert the water sources, we have employed Machine Learning algorithms like Multiple Regression and Multi-Swarm Optimization techniques. For selecting the most needed re-route, we have also considered the areas that are prone to droughts, and unite the re-routed water with the original course of the river, finally, draining into the sea, for the sustainable development. The proposed methodology is experimented by analyzing the flow areas (river basins) of river Mahanadi in India, one of the considerably important projects cited many times without any real implementation. The results are validated with the help of a study conducted earlier by the National Water Development Agency (NWDA), Government of India, in 2012.