首页|Central South University Reports Findings in Machine Learning (Feature engineering for improved machine-learning-aided studying heavy metal adsorption on biochar)
Central South University Reports Findings in Machine Learning (Feature engineering for improved machine-learning-aided studying heavy metal adsorption on biochar)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
New research on Machine Learning is the subject of a report. According to news originating from Changsha, People’s Republic of China, by NewsRx correspondents, research stated, “Due to the broad interest in using biochar from biomass pyrolysis for the adsorption of heavy metals (HMs) in wastewater, machine learning (ML) has recently been adopted by many researchers to predict the adsorption capacity (e) of HMs on biochar. However, previous studies focused mainly on developing different ML algorithms to increase predictive performance, and no study shed light on engineering features to enhance predictive performance and improve model interpretability and generalizability.” Our news journalists obtained a quote from the research from Central South University, “Here, based on a dataset widely used in previous ML studies, features of biochar were engineered-elemental compositions of biochar were calculated on mole basis-to improve predictive performance, achieving test R of 0.997 for the gradient boosting regression (GBR) model. The elemental ratio feature (H-O-2N)/C, representing the H site links to C (non-active site to HMs), was proposed for the first time to help interpret the GBR model. The (H-O-2N)/C and pH of biochar played essential roles in replacing cation exchange capacity (CEC) for predicting e. Moreover, expanding the coverages of variables by adding cases from references improved the generalizability of the model, and further validation using cases without CEC and specific surface area (R 0.78) and adsorption experimental results (R 0.72) proved the ML model desirable.”
ChangshaPeople’s Republic of ChinaAsiaCyborgsEmerging TechnologiesEngineeringMachine Learning
NETL
NSTL
