Insight into the Adsorption of Nutrients from Water by Pyrogenic Carbonaceous Adsorbents Using a Bootstrap Method and Machine Learning
Xuan Cuong Nguyen, Thi Thanh Huyen Nguyen, Nguyễn Thị Thúy Hằng, Văn Nam Thái, Thi Oanh Doan, Thi Thuy Duong, Thanh Nghi Duong, Yuhoon Hwang, Vinh Son Lam, Quang Viet Ly
Abstract
Herein, findings from 98 research papers [52 biochar (BC) and 46 activated carbon (AC) papers] were analyzed using a bootstrap method and a 95% confidence interval (CI) to provide insights into nutrient adsorption. The results indicated the solution temperature, pore volume, specific surface area, and pyrolysis temperature were correlated significantly to the maximum adsorption capacity (Qm), achieving r values of 0.37, 0.23, 0.16, and 0.14, respectively. A statistically significant difference was witnessed for nitrate Qm between AC and BC with median values of 17.64 and 0.51 mg/g, respectively, and CIs of 11.01–27.56 and 0.39–0.82 mg/g, respectively. In contrast, the difference in Qm between AC and BC for phosphate and ammonium contained a high probability of chance. On average, engineered biochar achieved higher Qm values of ammonium and phosphate (12.13 and 24.73 mg/g, respectively) in comparison with that of the original biochar. However, there is a good probability of no difference in nitrate between the two, albeit greater nitrate adsorption on the modified biochar with a mean Qm of 3.03 mg/g. The tuned Cubist estimated equilibrium adsorption capacity with an R2 of ∼0.90–0.91. The median and bootstrap 95% CI can be used as an average standard for designing adsorbate–adsorbent systems.