{"title":"A novel intelligent system based on machine learning for hydrochar multi-target prediction from the hydrothermal carbonization of biomass","authors":"","doi":"10.1007/s42773-024-00303-8","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>Hydrothermal carbonization (HTC) is a thermochemical conversion technology to produce hydrochar from wet biomass without drying, but it is time-consuming and expensive to experimentally determine the optimal HTC operational conditions of specific biomass to produce desired hydrochar. Therefore, a machine learning (ML) approach was used to predict and optimize hydrochar properties. Specifically, biochemical components (proteins, lipids, and carbohydrates) of biomass were predicted and analyzed first via elementary composition. Then, accurate single-biomass (no mixture) based ML multi-target models (average <em>R</em><sup>2</sup> = 0.93 and RMSE = 2.36) were built to predict and optimize the hydrochar properties (yield, elemental composition, elemental atomic ratio, and higher heating value). Biomass composition (elemental and biochemical), proximate analyses, and HTC conditions were inputs herein. Interpretation of the model results showed that ash, temperature, and the N and C content of biomass were the most critical factors affecting the hydrochar properties, and that the relative importance of biochemical composition (25%) for the hydrochar was higher than that of operating conditions (19%). Finally, an intelligent system was constructed based on a multi-target model, verified by applying it to predict the atomic ratios (N/C, O/C, and H/C). It could also be extended to optimize hydrochar production from the HTC of single-biomass samples with experimental validation and to predict hydrochar from the co-HTC of mixed biomass samples reported in the literature. This study advances the field by integrating predictive modeling, intelligent systems, and mechanistic insights, offering a holistic approach to the precise control and optimization of hydrochar production through HTC.</p> <span> <h3>Graphical Abstract</h3> <p> <span> <span> <img alt=\"\" src=\"https://static-content.springer.com/image/MediaObjects/42773_2024_303_Figa_HTML.png\"/> </span> </span></p> </span>","PeriodicalId":8789,"journal":{"name":"Biochar","volume":"86 1","pages":""},"PeriodicalIF":13.1000,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biochar","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1007/s42773-024-00303-8","RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Hydrothermal carbonization (HTC) is a thermochemical conversion technology to produce hydrochar from wet biomass without drying, but it is time-consuming and expensive to experimentally determine the optimal HTC operational conditions of specific biomass to produce desired hydrochar. Therefore, a machine learning (ML) approach was used to predict and optimize hydrochar properties. Specifically, biochemical components (proteins, lipids, and carbohydrates) of biomass were predicted and analyzed first via elementary composition. Then, accurate single-biomass (no mixture) based ML multi-target models (average R2 = 0.93 and RMSE = 2.36) were built to predict and optimize the hydrochar properties (yield, elemental composition, elemental atomic ratio, and higher heating value). Biomass composition (elemental and biochemical), proximate analyses, and HTC conditions were inputs herein. Interpretation of the model results showed that ash, temperature, and the N and C content of biomass were the most critical factors affecting the hydrochar properties, and that the relative importance of biochemical composition (25%) for the hydrochar was higher than that of operating conditions (19%). Finally, an intelligent system was constructed based on a multi-target model, verified by applying it to predict the atomic ratios (N/C, O/C, and H/C). It could also be extended to optimize hydrochar production from the HTC of single-biomass samples with experimental validation and to predict hydrochar from the co-HTC of mixed biomass samples reported in the literature. This study advances the field by integrating predictive modeling, intelligent systems, and mechanistic insights, offering a holistic approach to the precise control and optimization of hydrochar production through HTC.
期刊介绍：
Biochar stands as a distinguished academic journal delving into multidisciplinary subjects such as agronomy, environmental science, and materials science. Its pages showcase innovative articles spanning the preparation and processing of biochar, exploring its diverse applications, including but not limited to bioenergy production, biochar-based materials for environmental use, soil enhancement, climate change mitigation, contaminated-environment remediation, water purification, new analytical techniques, life cycle assessment, and crucially, rural and regional development. Biochar publishes various article types, including reviews, original research, rapid reports, commentaries, and perspectives, with the overarching goal of reporting significant research achievements, critical reviews fostering a deeper mechanistic understanding of the science, and facilitating academic exchange to drive scientific and technological development.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
