Pub Date : 2024-03-01DOI: 10.1007/s42773-024-00303-8
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.
{"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":"https://doi.org/10.1007/s42773-024-00303-8","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":12.7,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140008444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-01DOI: 10.1007/s42773-024-00312-7
Qi Liu, Cuiyan Wu, Liang Wei, Shuang Wang, Yangwu Deng, Wenli Ling, Wu Xiang, Yakov Kuzyakov, Zhenke Zhu, Tida Ge
Combined straw and straw-derived biochar input is commonly applied by farmland management in low-fertility soils. Although straw return increases soil organic matter (SOM) contents, it also primes SOM mineralization. The mechanisms by which active microorganisms mineralize SOM and the underlying factors remain unclear for such soils. To address these issues, paddy soil was amended with 13C-labeled straw, with and without biochar (BC) or ferrihydrite (Fh), and incubated for 70 days under flooded conditions. Compound-specific 13C analysis of phospholipid fatty acids (13C-PLFAs) allowed us to identify active microbial communities utilizing the 13C-labeled straw and specific groups involved in SOM mineralization. Cumulative SOM mineralization increased by 61% and 27% in soils amended with Straw + BC and Straw + Fh + BC, respectively, compared to that with straw only. The total PLFA content was independent of the straw and biochar input. However, 13C-PLFAs contents increased by 35–82% after biochar addition, reflecting accelerated microbial turnover. Compared to that in soils without biochar addition, those with biochar had an altered microbial community composition-increased amounts of 13C-labeled gram-positive bacteria (13C-Gram +) and fungi, which were the main active microorganisms mineralizing SOM. Microbial reproduction and growth were susceptible to nutrient availability. 13C-Gram + and 13C-fungi increased with Olsen P but decreased with dissolved organic carbon and ({text{NO}}_{3}^{ - }) contents. In conclusion, biochar acts as an electron shuttle, stimulates iron reduction, and releases organic carbon from soil minerals, which in turn increases SOM mineralization. Gram + and fungi were involved in straw decomposition in response to biochar application and responsible for SOM mineralization.