Optimizing the Mitigation of Heavy Metal Pollution in Biochar-treated Soils with Machine Learning

▲From left to right: Kumuduni Niroshika Palansooriya (Post-doctoral Researcher), Xiaonan Wang (Full Professor), 

and Yong Sik Ok (Full Processor)

Researchers use machine learning modeling to predict the most important factors underlying heavy metal pollution remediation in biochar-treated soils

Biochar, or thermally decomposed biowaste, is an effective way of managing heavy metal (HM) contamination of soils. However, the optimal conditions for achieving maximum HM immobilization with biochar vary widely depending on biochar, soil, and HM properties. An international research team adopted an empirical approach to determining the optimum conditions beforehand using machine learning modeling. Their results can help optimize biochar-based soil remediation efficiency and open doors to a biochar-based green economy.

Environmental pollution is one of the biggest global concerns of our time. Building a sustainable future is only possible if we proactively address every aspect of this problem. In this regard, soil pollution due to the accumulation of heavy metals (HMs) poses a serious threat to sustainable development as well as human health. This is because the HMs that enter the soil eventually find their way up the food chain, and upon entering the human body, can cause life-threatening diseases like cancer, renal failure, and cardiovascular disease. Minimizing HM concentration in soils is, therefore, a key goal in our fight against environmental pollution.

A notable development in this direction has been the use of “biochar”—biological waste decomposed thermally in absence of oxygen—to immobilize HM contaminants in the soil. Compared to raw feedstock, biochar can adsorb and immobilize HMs more efficiently owing to its unique physical and chemical properties. Moreover, it is highly adaptable and economically feasible, making it a promising alternative to fossil fuels.

There is, however, a catch: the HM immobilization efficiency in biochar-applied soils can vary depending on the type of soil, biochar, and HMs involved. In other words, the optimum conditions for maximum HM immobilization are extremely site-specific. Identifying these optimum conditions before applying biochar to the soil through a generalized empirical approach can reduce the cost and time involved in biochar remediation of soils. However, it is extremely difficult to optimize all the parameters involved simultaneously through experimentation.

Fortunately, an international research team led by Prof. Yong Sik Ok and Dr. Kumuduni N. Palansooriya from Korea University has now offered an ingenious solution—using machine learning (ML) to predict the HM immobilization efficiency for biochar-treated soils. In their study published in Environmental Science & Technology, the team developed three ML models, namely random forest, supporting vector regression, and neural network, to predict the immobilization efficiency based on biochar characteristics and production temperature, experimental conditions, soil properties, and HM properties.

Speaking about the motivation for pursuing an ML-based approach, Prof. Ok comments, “There has been a paucity of studies on ML-based prediction of biochar efficiency for immobilization of HM contaminants in soils due to the complex nature of biochar-soil interactions and a lack of systematic dataset. In our study, we wanted to address this gap.”

They identified a total of 20 parameters as input features and used 152 data points to train the models for predicting the immobilization efficiency. Among the three models, random forest gave the most accurate predictions.

Among the input features, biochar nitrogen content and application rate were found to be the most important features in determining HM immobilization. Furthermore, soil properties and pH were found to be the third and fourth most important features, respectively, showing that soil properties had an important role to play as well. Additionally, a causal analysis estimate showed that the importance of properties in HM immobilization followed the order: biochar properties > experimental conditions > soil properties > HM properties.

With these illuminating findings, the team is excited about the future prospects of biochar in the application of HM immobilization. “Future research needs to focus on improving the ML-based approach by using a database based on studies with well-defined scientific objectives and similar methodologies under uniform experimental conditions,” says Dr. Palansooriya. “With luck, biochar would offer us the chance to convert bioenergy into a carbon-negative industry.” An exciting consequence to look forward to, for sure!

The team acknowledges Prof. Xiaonan Wang (Tsing University, China) and Jie Li (National University of Singapore, Singapore) for their support during this study.

[Reference]

Authors

Kumuduni N. Palansooriya^a, Jie Li^b, Pavani D. Dissanayake^a, Manu Suvarna^b, Lanyu Li^b, Xiangzhou Yuan^a, Binoy Sarkar^c, Daniel C. W. Tsang^d, Jörg Rinklebe^e,f, Xiaonan Wang^g, Yong Sik Ok^a

Title of original paper

Prediction of soil heavy metal immobilization by biochar using machine learning

Journal

Environmental Science & Technology

[Affiliations]

^aKorea Biochar Research Center, APRU Sustainable Waste Management Program & Division of Environmental Science and Ecological Engineering, Korea University
^bDepartment of Chemical and Biomolecular Engineering, National University of Singapore
^cLancaster Environment Centre, Lancaster University
^dDepartment of Civil and Environmental Engineering, The Hong Kong Polytechnic University
^eUniversity of Wuppertal, School of Architecture and Civil Engineering, Institute of Foundation Engineering, Water and Waste Management, Laboratory of Soil and Groundwater Management
^fDepartment of Environment, Energy and Geoinformatics, Sejong University
^gDepartment of Chemical Engineering, Tsinghua University

[Figure 1] Biochar is a promising approach to mitigating heavy metal (HM) pollution in soils. However, the optimum conditions for maximum remediation vary with site, biochar, and HM properties. Now, scientists show that machine learning can help predict these optimum conditions beforehand.

About Professor Yong Sik Ok

Dr. Ok is a full professor and global research director of Korea University, Seoul, Korea. He has published over 900 research papers and books, 92 of which have been ranked as Web of Science ESI top papers (90 have been selected as “Highly Cited Papers” (HCPs), and two as “Hot Papers”). He has been a Web of Science Highly Cited Researcher (HCR) since 2018 in Cross Field, Environment and Ecology, and Engineering. In 2019, he became the first Korean to be selected as an HCR in the field of Environment and Ecology. Again in 2021, he became the first Korean HCR in two fields: Environment and Ecology, and Engineering. He is working at the vanguard of global efforts to develop sustainable waste management strategies and technologies to address the rising crisis in electronic and plastic waste, and pollution of soil and air with particulate matter. Dr. Ok has also served in a number of positions worldwide including, as an honorary professor at the University of Queensland (Australia), a visiting professor at Tsinghua University (China), an adjunct professor at the University of Wuppertal (Germany), and a guest professor at Ghent University (Belgium). He maintains a worldwide professional network by serving as a Co-Editor-in-Chief of Critical Reviews in Environmental Science and Technology, an Editor of Environmental Pollution, a member of the editorial advisory board of Environmental Science & Technology, and an editorial board member of Renewable and Sustainable Energy Reviews, Chemical Engineering Journal, and Environmental Science: Water Research & Technology, and several other top journals. He currently serves as the Director of the Sustainable Waste Management Program for the Association of Pacific Rim Universities (APRU) and the Co-President of the International ESG Association. Moreover, he has served on the Scientific Organizing Committee of P4G Nature Forum: Climate Change and Biodiversity, and Nature Forum: Plastics and Sustainability. Dr. Ok has also served as the chairman of numerous major conferences such as Engineering Sustainable Development series (ESD series), organized by the APRU and the American Institute of Chemical Engineers (AIChE). In 2021, Dr. Ok hosted the first Nature conference among South Korean universities in Seoul on waste management and valorization for a sustainable future together with Chief Editors of Nature Sustainability (Dr. Monica Contestabile), Nature Electronics (Dr. Owain Vaughan), and Nature Nanotechnology (Dr. Fabio Pulizzi). Prof. Ok will host the first Nature Forum on Environmental, Social & Governance (ESG) for Global Sustainability: the “E” Pillar for Sustainable Business. 

For more information, visit: https://koreauniv.pure.elsevier.com/en/persons/yong-sik-ok-2