Machine learning (ML): An emerging tool to access the production and application of biochar in the treatment of contaminated water and wastewater

Abstract

To achieve sustainable development goals (SDGs), drinking water and/or wastewater treatment must be performed at a minimum cost along with negligible environmental impacts. Traditional approaches, like coagulation, precipitation, ion exchange, and membrane filtration have numerous drawbacks in terms of cost and effectiveness. Recently, the thermochemical conversion of biomasses/lignocellulosic wastes for biochar production and subsequently their application in the remediation of contaminated matrices is gaining attention. Further, the application of machine learning (ML) and artificial intelligence (AI) to optimize the production and application of biochar is a topical topic. Therefore, this review critically explains the optimised production process of biochar and its application in the removal of a diverse range of organic and inorganic contaminants from contaminated water and wastewater. Moreover, the review highlights the progress in organic and inorganic pollutants remediation with biochar, focusing on the significance and benefits of utilizing ML and AI to optimize adsorption variables and biochar feedstock properties. The surface area, porosity, and functional groups of the biochar, the type and quantity of the pollutants and the solution's pH, temperature, and ionic strength, all influence the adsorption capacity of the biochar. Furthermore, the duration of the biochar's interaction with the contaminants and the existence of competing ions are significant factors. Utilizing AI and ML proves to be efficient in terms of cost and time, enabling a multidisciplinary approach to eliminate pollutants using biochar. Finally, this review discusses the challenges associated with the application of ML and AI in the treatment of contaminated water and wastewater using biochar and proposed future prospects to make these technologies economically viable and sustainable.