Estimating the Water Quality Class of a Major Irrigation Canal in Odisha, India: A Supervised Machine Learning Approach

Contamination of surface water by rapid industrialization, natural and anthropogenic activities is ofgreat concern over the last few decades. Nowadays, canal water systems are no exception to thisform of contamination, which results in water quality degradation. To classify the canal water basedon the Bureau of Indian Standards (BIS), it was thought to develop a quick and inexpensive approachas an alternative to the time-consuming analysis approach. With this motivation, the present studyexplores building a machine learning model for water quality classification of a major canal namelythe Talaldanda canal operating in the state of Odisha, India. The water quality class is predicted usingsupervised machine learning (ML) prediction models for the new canal water input parameters. Thewater quality parameters such as pH, dissolved oxygen (DO), biochemical oxygen demand (BOD), andtotal coliform (TC) at six strategic locations of the canal from the year 2013-2020 were collected fromOdisha State Pollution Control Board for the training phase. The supervised ML models used in thestudy are Decision Tree (DT), Neural Network (NN), k-NN (k-Nearest Neighbor), Naïve Bayes (NV),Support Vector Machine (SVM), and Random Forest (RF). The predictions of the models are evaluatedusing the Orange-3.29.3 data analytics tool. When analyzing the performance parameters by samplingthe training data into training and testing using cross-validation, the results show that DT has a higherclassification accuracy (CA) of 96.6 percent than other ML models. In addition, the likelihood of DTcorrectly predicting water quality class for the testing dataset is higher than that of other predictionmodels.