Recently, the team of the Institute of Agricultural Environment and Sustainable Development of the Chinese Academy of Agricultural Sciences, focusing on the clean conversion and high-value utilization of crop residues, constructed a machine learning big data model to reveal the structure-property relationship of straw biochar materials and their energy storage characteristics. The research results were published in the Chemical Engineering Journal.
Biochar, due to its renewability and unique physicochemical properties, is an ideal precursor for supercapacitor electrodes. Applying biochar in the field of energy storage is of great significance for achieving China's "dual carbon" goals. However, the process of straw biochar preparation and regulation is complex, making it difficult to determine the optimal process through traditional experiments. Furthermore, the structure-property relationship between physicochemical properties and energy storage remains unclear.
This study utilized big data retrieval and analysis of biochar energy storage materials to construct and optimize three machine learning models for predicting biochar preparation processes and energy storage characteristics. The model prediction accuracy reached 93%, and it was found that heating rate, micropore ratio, and specific surface area are the most important factors affecting the specific capacitance of biochar.
Furthermore, the research found that increasing the amount of activator addition and reaction temperature, while reducing reaction time and heating rate, has a positive effect on improving the energy storage performance of biochar. The research results provide theoretical basis and technical support for the application of straw biochar in the field of energy storage.
This study was supported by projects such as the National Modern Agricultural Industry Technology System, the Chinese Academy of Agricultural Sciences Science and Technology Innovation Project, and the National Natural Science Foundation of China.
Related paper information: https://doi.org/10.1016/j.cej.2024.149975
