Simulating the Scenarios of Surface Water Quality Indicators for Lower Mahanadi River System using Artificial Intelligence

Abstract

Water quality describes the suitability of water in terms of its physical, chemical, and biological characteristics. To identify these characteristics adequately, one needs to comprehend the variation of the significant parameters affecting the water quality of a particular region. The study area for this work is the lower Mahanadi River basin, comprising of 13 stations located along the river course from which data from 20 different physicochemical parameters are collected for 2001 to 2023. The parameters include temperature, pH, turbidity, dissolved oxygen (DO), biochemical oxygen demand (BOD), total coliform (TC), faecal coliform (FC), conductivity, chloride, total hardness, calcium hardness, magnesium hardness, alkalinity, sulphate, sodium, chemical oxygen demand (COD), total dissolved solids (TDS), total suspended solids (TSS), nitrate-N, and nitrite-N. Multivariate statistical methods are used to determine the seasonal variation of the water quality and to reduce the number of parameters. In particular, principal component analysis (PCA) provided desirable results that have a major impact on the water quality. In the non-monsoon season, the parameters are reduced to 45%. Deep learning and machine learning have gained significant attention for analysing time-series data. However, these methods often suffer from high complexity and significant forecasting errors, primarily due to non-linear datasets and hyperparameter settings. An innovative HDTO-DeepAR approach for predicting water quality indicators has been developed to address these challenges. HDTO-DeepAR outperformed the other methods. The forecasted frequency is expected to fall within a prediction interval of 95% and 98%. Improving surface water monitoring capabilities may result in accurate predictions, which can help policymakers develop a strategy to reduce water pollution. Traditional monitoring techniques are time-consuming and costly, making it difficult to meet the demands of real-time visualisation in current situations. To deal with this challenge, a novel approach (GHPSO-ATLSTM) has been developed to predict water quality indicators in surface water. The optimal features are selected using a genetic algorithm (GA), and the hyperparameters of LSTM are optimized with the hidden particle swarm optimisation (HPSO) technique followed by an attention (AT) layer to enhance the prediction accuracy. The R2 value lies between 0.89 and 0.95 using the proposed method. The novelty of the work lies in determining a specific set of most significant variables using PCA, forecasting the significant variables based on a probabilistic approach using HDTO-DeepAR, and predicting water quality parameters based on point prediction using GHPSO-ATLSTM. The major conclusions drawn from the case study are that DO might fluctuate between 6 mg/l and 10 mg/l in the coming years. All the parameters are found to be lying within the permissible limit. Government intervention and increased public knowledge of environmental degradation’s effects on health risks may be responsible for reducing the amount of water pollution in the Mahanadi River system.