In the Journal of Environmental Science and Health, Part A, Banza M. Jean Claude and Linda L. Sibali explore how machine learning (ML) is being used to advance environmentally friendly practices, focusing on biomass-derived materials (BDMs) in wastewater treatment and agriculture. This review highlights the pivotal role of ML in optimizing BDM systems, predicting material properties and performance, and enhancing sustainability evaluations. The authors suggest that while ensemble models and neural networks show promise, there’s room for growth in the interpretability of these models and in incorporating geo-temporal dynamics into sustainability assessments.  

BiomassBiomass is a complex biological organic or non-organic solid product derived from living or recently living organism and available naturally. Various types of wastes such as animal manure, waste paper, sludge and many industrial wastes are also treated as biomass because like natural biomass these More is gaining recognition as a sustainable alternative to fossil fuels, with over 40 countries incorporating bio-economies into their policies. Biomass-derived materials (BDMs) like biocharBiochar is a carbon-rich material created from biomass decomposition in low-oxygen conditions. It has important applications in environmental remediation, soil improvement, agriculture, carbon sequestration, energy storage, and sustainable materials, promoting efficiency and reducing waste in various contexts while addressing climate change challenges. More, biosorbents, and activated carbonActivated carbon is a form of carbon that has been processed to create a vast network of tiny pores, increasing its surface area significantly. This extensive surface area makes activated carbon exceptionally effective at trapping and holding impurities, like a molecular sponge. It is commonly More are derived from renewable feedstocks such as wood, aquatic biomass, plant life, and animal waste. These materials are pivotal in reducing greenhouse gas emissions and have found applications in soil amendments, wastewater treatment, energy storage, and medicine. Machine learning is emerging as a crucial tool to tackle challenges in material, process, and supply chain design within BDM systems.  

The review categorizes ML applications into material and process design, performance prediction, and sustainability evaluation. ML optimizes BDM systems, predicts material properties and performance, aids in reverse engineering, and addresses data challenges in sustainability evaluations. Algorithms like TFBB and Neural Networks are effective on BDM datasets and easily generalized.

The authors highlight the need for future ML research to follow a workflow that investigates the potential uses of ML in BDM system optimization, evaluation, and sustainable development. This includes addressing the limitations of current ensemble and neural network models, such as poor interpretability and the lack of consideration for geo-temporal dynamics in sustainability assessments. By doing so, ML can be better harnessed to create efficient methods for converting biomass to meet desired material properties, ultimately supporting environmentally friendly advancement in wastewater treatment and agriculture.  

Source: Claude, B. M. J., & Sibali, L. L. (2025). Application of machine learning for environmentally friendly advancement: exploring biomass-derived materials in wastewater treatment and agricultural sector – a review. Journal of Environmental Science and Health, Part A, 59(11-14), 606-621