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, C content, and O content of biochar in order. All three algorithms could effectively 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 different 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%.