Dissolved oxygen modelling of the Yamuna River using different ANFIS models

Abstract

Dissolved oxygen is one of the prime parameters for assessing the water quality of any stream. Thus, the accurate estimation of dissolved oxygen is necessary to evolve measures for maintaining the riverine ecosystem and designing the appropriate water quality improvement plans. Machine learning techniques are becoming valuable tools for the prediction and simulation of water quality parameters. A study has been performed in the Delhi stretch of Yamuna River, India, and physiochemical parameters were examined for five years to simulate the dissolved oxygen using various machine learning techniques. Simulation and prediction competencies of adaptive neuro fuzzy inference system – grid partitioning (ANFIS-GP) and subtractive clustering (ANFIS-SC) were performed on high dimensional river characteristics. Four different models (M1, M2, M3 and M4) were developed using different combination of input parameters to predict dissolved oxygen. Results obtained from the models were evaluated using root mean square error (RMSE) and coefficient of determination (R2) to identify the appropriate combination of parameters to simulate the dissolved oxygen. Results suggest that both types of ANFIS models work adequately and accurately predict the DO; however, ANFIS-GP outperforms the ANFIS-SC. M4 generated R2 of 0.953 from ANFIS-GP compared to 0.911 from ANFIS-SC.

Fuzzy Inference System-based Geo Visualization Tool Development for Yamuna River Water Quality Analysis

“…Inference provides a measure of how well fuzzy sets match defined rules, whereas de-fuzzing reverts machine data into humancomprehensible categories based on conditional statements. [11,12,13]. The membership function projects the input data onto a graph between 0 and 1.…”

Analysis of Seasonal Variations in Surface Water Quality over Wet and Dry Regions

“…A rapid surge in population has exponentially intensified the demands of clean water globally [1][2][3][4]. Water quality is a key environmental issue due to its influence on aquatic life and the general health of the water ecosystem [5,6]. Generally, water quality management is performed using different water quality models of water channels and rivers, the point and nonpoint sources playing a vital role in the nitrogen dynamics, biochemical oxygen demand (BOD), and dissolved oxygen (DO) [7][8][9][10].…”

Investigations on the co-occurrence of microplastics and other pollutants in the River Yamuna, Delhi

“…Global trends reveal that wastewater treatment infrastructure is comparatively less effective in developing countries as compared to developed countries which often creates losses in terms of human and environmental health (Mumbi & Watanabe 2022). In India also, a consistent degradation in the water quality of riverine resources has been reported due to the inflow of mismanaged sewage, industrial wastewater, solid waste, and agricultural run-off (Arora & Keshari 2021;Begum et al 2022;Slathia & Jamwal 2022).…”

“…Yamuna River is one of the most important freshwater resources for the megacity Delhi, located in Northern India. Through its course in the city, the river receives partially treated and untreated wastewater discharges from around 16 drains (Arora & Keshari 2021) and has been found contaminated with harmful pollutants like heavy metals, antibiotics, and pathogenic microorganisms (Bhardwaj et al 2017;Lamba et al 2020). Out of all the drains, Najafgarh and Shahdara are of primary importance as they discharge the maximum load of wastewater in the river (Bhardwaj et al 2017).…”