Machine learning prediction of nitrogen heterocycles in bio-oil produced from hydrothermal liquefaction of biomass. (October 2022)

• Record Type: Journal Article
• Authors: Leng, Lijian; Zhang, Weijin; Chen, Qingyue; Zhou, Junhui; Peng, Haoyi; Zhan, Hao; Li, Hailong
• Is Part Of: Bioresource technology. Volume 362(2022)
• Publication Date: 2022-10
• Subjects: Nitrogen containing heterocyclic compounds -- Bio-crude oil -- Hydrothermal conversion -- Random forest -- Data mining -- Nitrogenous bio-oil; Biomass -- Periodicals; Biomass energy -- Periodicals; Bioremediation -- Periodicals; Agricultural wastes -- Periodicals; Factory and trade waste -- Periodicals; Organic wastes -- Periodicals; Bioénergie -- Périodiques; Déchets agricoles -- Périodiques; Déchets industriels -- Périodiques; Déchets organiques -- Périodiques; Déchets (Combustible) -- Périodiques; 662.88
• DOI: 10.1016/j.biortech.2022.127791
• Languages: English
• ISSNs: 0960-8524

Abstract

Graphical abstract: Highlights: Random forest predicted the yield and N content of bio-oil with test R 2 ≥ 0.92. Prediction of relative content of N -Heterocycles in bio-oil obtained test R 2 = 0.82. N/C and protein were positively related to NH, while lipid was negatively related. Optimal models were posted online to predict and instruct experimental studies. The forward optimization of NH was implemented based on optimal prediction models. Abstract: Hydrothermal liquefaction (HTL) of high-moisture biomass or biowaste to produce bio-oil is a promising technology. However, nitrogen-heterocycles (NH) presence in bio-oil is a bottleneck to the upgrading and utilization of bio-oil. The present study applied the machine learning (ML) method (random forest) to predict and help control the bio-oil NH, bio-oil yield, and N content of bio-oil (N_oil). The results indicated that the predictive performance of the yield and N_oil were better than previous studies, achieving test R 2 of 0.92 and 0.95, respectively. Acceptable predictive performance (test R 2 of 0.82 and RMSE of 7.60) for the prediction of NH was also achieved. The feature importance analysis, partial dependence, and Shapely value were used to interpret the prediction models and study the NH formation mechanisms and behavior. Then, forward optimization of NH was implemented based on optimal predictive models, indicating the high potential of ML-aided bio-oil production and engineering.