Neural Network and Random Forest-Based Analyses of the Performance of Community Drinking Water Arsenic Treatment Plants

Abstract

A plethora of technologies has been developed over decades of extensive research on arsenic remediation, although the technical and financial perspective of arsenic removal plants in the field requires critical evaluation. In the present study, focusing on some of the pronounced arsenic-affected areas in West Bengal, India, we assessed the implementation and operation of different arsenic removal technologies using a dataset of 4000 spatio-temporal data collected from an in-depth field survey of 136 arsenic removal plants engaged in the public water supply. Our statistical analysis of this dataset indicates a 120% rise in the average cumulative capacity of the plants during 2014–2021. The majorities of the plants are based on the activated alumina with FeCl3 technology and serve about 49% of the population in the study area. The average cost of water production for the activated alumina with FeCl3 technology was found to be ₹ 7.56 /m3 (USD $1 ≈ INR ₹70), while the lowest was ₹ 0.39 /m3 for granular ferric hydroxide technology. A machine learning-based framework was employed to analyze the impact of water quality and treatment plant parameters on the removal efficiency, capital, and operational cost of the plants. The artificial neural network model exhibited adequate statistical significance, with a high F-value and R2 of 5830.94 and 0.72 for the capital cost model, 136954, and 0.98 for the operational cost model, respectively. The relative importance of the process variables was identified through random forest models. The models indicated that flow rate, media, and chemicals are the predominant costs, while contaminant loading in influent water and a coagulating agent was important for removal efficiency. The established framework may be instrumental as a decision-making tool for water providers to assess the expected performance and financial involvement for proposed or ongoing arsenic removal plants concerning various design and quality parameters.

A review of arsenic mitigation strategies in community water supplies with insights from South Asia: options, opportunities and constraints

“…AA with ferric chloride, AA with alum and ferric chloride, AA with alum and ferrous sulfate, GFH with sodium aluminate, and HIX with ferric chloride are some of the most prevalent combinations. 202 During the evaluation of these AIRPs, some of the commissioned plants reported operational and maintenance issues. The issues were inadequate dosing of chemicals, improper sludge disposal and management, erratic monitoring of plants, and non-functional flow meters.…”

“…A comprehensive analysis of the process parameters and economic viability is crucial since it identifies areas for technology innovation and assists future implementation. With this objective Bhattacharya et al (2021) 202 conducted an extensive study on techno-commercial aspects, operational parameters, removal efficiency, and current status of the As removal plants by evaluating 136 AIRPs commissioned in Maldah, Murshidabad, Nadia, and North 24 Parganas. The findings show that there has been a 120 percent increase in the AIRP capacity between 2014 and 2021 (Fig.…”

“…The parameters that had the greatest impact on removal efficiency were flow rate (28.97%), Fe and As concentration in the inflow water (30.99% and 22.3%), pH (9.99%), and coagulating agent (5.49%). 202 This study established a benchmark for the application of data science in the evaluation of As-based treatment plants and identifies the key process variables that can be adjusted going forward to achieve desired outcomes.…”

Artificial Intelligence Modelling to Support the Groundwater Chemistry-Dependent Selection of Groundwater Arsenic Remediation Approaches in Bangladesh

“…Water 2023, 15, 3539 2 of 15 due to the intersectionality of technical (including the influence of source water chemistry), socio-economic, regulatory, and other implementation factors [17][18][19].…”