Machine learning-assisted life cycle assessment of biochar soil application

Aug 3, 2026

Upload by Eden

Pyrolysis of waste biomass to produce biochar for soil application supports negative carbon emissions, but evaluating its full environmental performance requires an integrated approach. This study builds an environmental impact assessment framework that combines machine learning with life cycle assessment to quantify carbon footprints for biochar derived from agricultural waste. Five models are compared for yield and key properties, and multi-layer perceptron and Gaussian process regression achieve the strongest predictive accuracy. The framework incorporates carbon sequestration and fertiliser substitution scenarios, identifying the largest carbon saving potentials from urea ammonium nitrate and calcium ammonium nitrate substitutions, and enabling parameter optimization for up-scaling.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Climate and negative emission technology context

Biochar production, soil conditioning, and sustainability rationale

Materials and Methods

Machine learning models for yield and properties

Life cycle assessment and scenario design

Results and Discussion

Model performance for biochar predictions

Carbon savings under fertiliser substitution scenarios

Sensitivity of environmental impacts to pyrolysis operating conditions

Conclusion

Journal of Cleaner Production 498 (2025) 145109 Contents lists available at ScienceDirect Journal of Cleaner Production journal [homepage: www.elsevier.com/locate/jclepro](homepage: www.elsevier.com/locate/jclepro) | Machine learning-assisted life cycle assessment of biochar soil application Yize Li a,b , Rohit Gupta c,d , Wangliang Lie, Yi Fangb,e, Jaime Toney f, Siming You b,*
a University of Shanghai for Science and Technology, Shanghai, 200093, China
b James Watt School of Engineering, University of Glasgow, Glasgow, G12 8QQ, United Kingdom c UCL Mechanical Engineering, University College London, London, WC1E 7JE, United Kingdom d UCL Hawkes Institute, University College London, London, W1W 7TS, United Kingdom
e CAS Key Laboratory of Green Process and Engineering, Institute of Process Engineering, Chinese Academy of Sciences, Beijing, 100190, China f School of Geographical and Earth Sciences, University of Glasgow, Glasgow, G12 8QQ, Scotland, United Kingdom | | | | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | Handling Editor: Zhifu Mi | | Pyrolysis of waste biomass to produce biochar for soil application is receiving great attention for its potential to achieve negative carbon emissions. This study presents an environmental impact assessment framework combining machine learning modelling and life cycle assessment to evaluate the carbon footprints of biochar production from agricultural waste for soil application. Five machine learning models were compared for predicting biochar yields and properties, with multi-layer perceptron neural network and Gaussian process regression models showing excellent performance for the prediction of yield, and carbon and nitrogen contents of biochar (R2 = 0.97, RMSE = 3.5; R2 = 0.92, RMSE = 3.2; R2 = 0.94, RMSE = 0.36, respectively). The multi-layer perceptron neural network model predicted a maximum GWP saving associated condition is PT = 400 ◦ C, HR = 15 ◦ C/min, and RT = 40 min. The environmental impact assessment was carried out considering carbon sequestration and two fertiliser substitution scenarios. It was shown that the highest carbon saving potentials were − 1323 and − 1355 kg CO2-eq/t feedstock achieved by the scenarios of urea ammonium nitrate and calcium ammonium nitrate fertiliser substitutions, respectively. This framework is capable of simulating the influences of various operating conditions of pyrolysis towards the environmental impacts of its biochar soil application. It offers a useful tool for maximizing the environmental benefits of pyrolysis while accounting for the complex interdependencies between process parameters. The results highlight the importance of optimizing biochar production parameters while assessing the life cycle environmental impacts of biochar soil application to minimize trial and error and facilitate process up-scaling. | | Keywords:
Neural networks Intelligence modelling Waste management
Negative emission technologies Environmental impact assessment | | | 1. Introduction The Intergovernmental Panel on Climate Change (IPCC) has presented evidence indicating a significant rise in global temperatures over the past three decades. This emphasizes the urgent need to limit the temperature rise to mitigate the adverse impacts of global warming (Wang et al., 2020). Effective reduction in greenhouse gas (GHG) emissions is necessary to achieve the net-zero target established by the IPCC (Yoo et al., 2022). The utilization of biomass is one of the feasible methods to facilitate the fulfilment of the target, and it is considered tobe a relatively quick way of decarbonisation as compared to other methods such as tree planting which may have a much longer turnaround timeframe. In particular, biochar derived from the thermochemical treatment (e.g., pyrolysis) of biomass is a carbon-rich product and can be used for soil conditioning while achieving carbon sequestration. The utilization of this approach for cli

FAQs

What framework is proposed to assess biochar soil application impacts?

An environmental impact assessment framework combines machine learning modeling with life cycle assessment to quantify carbon footprints of biochar production for soil application.

Which machine learning models performed best for predicting biochar yield and properties?

Multi-layer perceptron neural network and Gaussian process regression showed excellent performance, with high R2 and low RMSE for predicting yield and carbon/nitrogen contents.

How do fertiliser substitution scenarios affect the carbon saving results?

The assessment considers carbon sequestration and fertiliser substitution scenarios, with the highest carbon saving potentials reported for urea ammonium nitrate and calcium ammonium nitrate substitution cases.

Aug 3, 2026

Upload by Eden