In a recent study published in ACS Sustainable Resource Management, Monica A. McCall and colleagues explored a more efficient way to determine 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 stability. Biochar, a carbon-rich material produced from 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 pyrolysisPyrolysis is a thermochemical process that converts waste biomass into bio-char, bio-oil, and pyro-gas. It offers significant advantages in waste valorization, turning low-value materials into economically valuable resources. Its versatility allows for tailored products based on operational conditions, presenting itself as a cost-effective and efficient More, is gaining attention for its potential in climate change mitigation and soil improvement. The key to biochar’s effectiveness lies in its stability—resistance to degradation—which is traditionally assessed through lengthy and costly elemental analysis. This study demonstrates that machine learning, using data from Fourier-transform infrared spectroscopy (FTIR), can accurately predict biochar stability, offering a more rapid and cost-effective alternative.  

The researchers pyrolyzed six different lignocellulosic feedstocks—barley straw, rice husk, chestnut wood, eucalyptus bark, pine bark, and miscanthus grass—at temperatures ranging from 150 to 700°C. They then used FTIR to analyze the chemical composition of the resulting biochars. Biochar stability is determined by the molar ratios of hydrogen to carbon (H:C) and oxygen to carbon (O:C), with certified biochar requiring H:C ratios less than 0.7 and O:C ratios less than 0.4.  

The study revealed that all biochars produced at 400°C and above met these criteria, indicating that higher temperatures enhance biochar stability. Machine learning models, including Random Forest (RF) and Support Vector Machines (SVM), were trained on the FTIR data to predict the H:C and O:C ratios. The Random Forest model, incorporating full data preprocessing, achieved the highest accuracy, with an R² of 0.96 for both H:C and O:C ratios when tested on an unseen feedstockFeedstock refers to the raw organic material used to produce biochar. This can include a wide range of materials, such as wood chips, agricultural residues, and animal manure. More.  

This level of accuracy suggests that FTIR spectroscopy, combined with machine learning, can serve as a rapid and reliable tool for estimating biochar stability. The ability to quickly assess biochar stability is crucial for its widespread adoption in environmental applications, offering a promising avenue for climate change mitigation and soil enhancement.

Source: McCall, M. A., Watson, J. S., Tan, J. S. W., & Sephton, M. A. (2025). Biochar Stability Revealed by FTIR and Machine Learning. ACS Sustainable Resource Management.