A novel intelligent system based on machine learning for hydrochar multi-target prediction from the hydrothermal carbonization of biomass

IF 13.1 2区环境科学与生态学 Q1 ENVIRONMENTAL SCIENCES Biochar Pub Date : 2024-03-01 DOI:10.1007/s42773-024-00303-8

{"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.

Graphical Abstract

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于机器学习的新型智能系统，用于生物质水热碳化过程中水炭多目标预测

摘要水热碳化（HTC）是一种无需干燥即可从湿生物质中产生水炭的热化学转化技术，但要通过实验确定特定生物质的最佳 HTC 操作条件以产生所需的水炭，既费时又费钱。因此，我们采用了机器学习（ML）方法来预测和优化水炭特性。具体来说，首先通过基本成分预测和分析生物质的生化成分（蛋白质、脂类和碳水化合物）。然后，建立基于单一生物质（无混合物）的精确 ML 多目标模型（平均 R2 = 0.93，RMSE = 2.36），以预测和优化水煤碳特性（产量、元素组成、元素原子比和较高热值）。这里输入了生物质成分（元素和生化）、近似分析和 HTC 条件。对模型结果的解释表明，灰分、温度以及生物质中的氮和碳含量是影响水煤炭特性的最关键因素，而生化成分（25%）对水煤炭的相对重要性高于操作条件（19%）。最后，基于多目标模型构建了一个智能系统，并通过应用该系统预测原子比（N/C、O/C 和 H/C）进行了验证。通过实验验证，该系统还可扩展用于优化单一生物质样品 HTC 产生的炭化水，以及预测文献中报道的混合生物质样品共 HTC 产生的炭化水。本研究通过整合预测建模、智能系统和机理见解，为精确控制和优化通过 HTC 生产水炭提供了一种整体方法，从而推动了该领域的发展。图表摘要

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Biochar Multiple-

CiteScore

18.60

自引率

10.20%

发文量

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.