Analysis of the Surface Water Quality in the State of Karnataka using Distributed Platform

Water, one of the essential substances for life on earth is crucial for humans, plants and animals. Regular testing and monitoring of water quality is essential to ensure its safety for consumption. This process includes measuring physical and chemical parameters such as PH, total dissolved solids (TDS) etc. Herein, surface water quality in Karnataka, India was analyzed over 40 years. In order to analyze the large amount of data collected, high performance computing cluster (HPCC) systems was used. Biochemical oxygen demand (BOD) predictive model was built using linear regression. Additionally, a potability classification model was built using the random forest classifier algorithm. These algorithms are present in the LinearRegression and LearningTrees bundle provided by HPCC Systems. Finally, a graphical visualization of water quality in four basins over time was performed with the Visualizer bundle. This was done to understand the improvement or degradation of water quality. The analysis was performed on a single node and an 8-node cluster respectively. In comparison with the former, the latter had a shorter execution time.