文献类型： 外文期刊

作者： Pei, Zhanjiang ¹ ; Liu, Shujun ² ; Jing, Zhangmu ³ ; Zhang, Yi ² ; Wang, Jingtian ² ; Liu, Jie ¹ ; Wang, Yajing ⁴ ; Guo, Wenyang ⁵ ; Li, Yeqing ² ; Feng, Lu ⁶ ; Zhou, Hongjun ² ; Li, Guihua ⁴ ; Han, Yongming ⁷ ; Liu, Di ⁸ ; Pan, Junting ⁴ ;

作者机构： 1.Heilongjiang Acad Black Soil Conservat & Utilizat, Key Lab Combining Farming & Anim Husb, Key Lab Energy Utilizat Main Crop Stalk Resources, Harbin 150086, Peoples R China

2.China Univ Petr Beijing CUPB, Coll New Energy & Mat, State Key Lab Heavy Oil Proc, Beijing Key Lab Biogas Upgrading Utilizat, Beijing 102249, Peoples R China

3.Tongji Univ, Sch Environm Sci & Engn, State Key Lab Pollut Control & Resource Reuse, 1239 Siping Rd, Shanghai 200092, Peoples R China

4.Chinese Acad Agr Sci, Inst Agr Resources & Reg Planning, Beijing 100081, Peoples R China

5.Henan Acad Sci Inst Biol Co Ltd, 28 Huayuan Rd, Zhengzhou 453003, Henan, Peoples R China

6.Norwegian Inst Bioecon Res, Postbox 115, NO-1431 As, Norway

7.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China

8.Heilongjiang Acad Agr Sci, Harbin 150086, Peoples R China

关键词： Microbiological analysis; High-solid anaerobic digestion; Corn straw; Cattle manure; Machine learning

期刊名称：JOURNAL OF CLEANER PRODUCTION （ 影响因子：11.072； 五年影响因子：11.016 ）

ISSN： 0959-6526

年卷期： 2022 年 373 卷

页码：

收录情况： SCI

摘要： Co-digestion of lignocellulosic biomass and animal manure is a common approach to increase the efficiency of methane production, but the niche differentiation and microbial metabolism of the anaerobic digestion (AD) process remain to be determined. To further explore the effect of the interaction between species and their compositional niches, the methane yield and resulting microbial community were determined by machine learning (ML) and 16S rRNA gene sequencing in mixed high-solid anaerobic digestion (HS-AD) with spray -enhanced conditions to explore the internal relationship between physical and chemical parameters and mi-croorganisms and to speculate on the enhancement mechanism of co-digestion. In this study, three ML models (extreme learning machine (ELM), artificial neural network (ANN), and random forest (RF)) were applied to analyse and model AD of dry fermentation. The results showed that the best prediction model, based on ELM, could best predict the material biogas production in this experiment with a mean absolute error (MAE/10) of 0.678 and a coefficient of determination (R-2) of 0.9574, whereas the characteristic percentage analysis of the RF model showed that butyric acid, acetic acid, and pH had three important influences on the biogas production values. Meanwhile, the results of high-throughput 16S rRNA gene sequencing and PICRUSt showed that the addition of manure containing ammonia nitrogen improved the metabolism of amino acids, enriched species capable of Clostridiales and Methanosarcinales, promoted the electronic transfer of nutrient metabolism, and thus enhanced AD. Moreover, the co-occurrence network showed that seven niches were differentiated within the HS -AD system to reduce the shock of ammonia nitrogen for methanogens. Overall, microbial analysis and ML can help understand the dynamic processes of methanogenic microorganisms and predict biogas production for the efficient operation of AD.