基于機器學習的多孔生物炭吸附 CO₂ 性能預測

打開文本圖片集

中圖分類號：TU528.1 文獻標志碼：A 文章編號：2096-6717（2025）03-0242-09

Prediction of CO2 adsorption performance in porous biochar based on machine learning

CHEN Yifei’，ZHANG Xiaoqing'，TAN Kanghao12，WANG Junsong2，QIN Yinghong （1.SchoolofCivilEngineeringandArchitecture;KeyLaboratoryofDisasterPreventionandEngineeringSafetyof Guangxi， Guangxi University，Nanning 53Oo04，P.R. China; 2.State Key Laboratory of Subtropical Building Science，South China University of Technology，Guangzhou 5lo64o，P.R.China）

Abstract： CO2 capture and sequestration （CCS） is an emission reduction measure with great potential. Porous biochar contains rich multi-scale pore structure，which makes it have excellent CO2 adsorption performance. To address the shortcomings of traditional CO2 adsorption prediction models built with experimental data，such as low accuracy and complicated calculation， this paper adopts machine learning methods such as gradient boosting decision tree（GBDT），extreme gradient enhancement algorithm （XGB）and light gradient booster algorithm （LGBM） to make model predictions of CO2 adsorption by biochar，and conducts comparative analysis of the prediction results. The results showed that the three most important factors affecting CO2 adsorption were the specific surface area，Ccontent，andOcontent of biochar inorder.Allthree algorithms could effctively predict the CO2 adsorption performance of biochar. In comparison， LGBM has the highest prediction accuracy of 94% GBDT has a significant advantage in processing anomalous sample data; and XGB has more stable prediction results for diferent test set variations. When designing the adsorption performance of biochar，excessive surface area should not be blindly pursued.It is recommended that the selection of biochar C content should preferably be between 83% and 88% ，and O content should preferably be between 15% and 18%

Keywords： biochar; machine learning; CO2 adsorption； feature importance；partial dependency map

溫室氣體積累導致全球變暖，已經成為國際社會研究的熱點問題[]。（剩余14416字）