数字农科院2.0

Decoding soil health constraints in regional agroecosystems: Machine learning reveals microbial enzymatic thresholds and drivers

文献类型： 外文期刊

作者： Xu, Xuebin;Zhang, Kailu;Zhu, Zhenke;Wei, Liang;Wang, Shuang;Zhang, Wenju;Li, Lujun;Kuzyakov, Yakov;Chen, Jianping;Ge, Tida

作者机构：

关键词： Soil health;Machine learning;SHapley Additive exPlanations;Threshold;Constraint factor;Enzymatic activity

期刊名称： SOIL & TILLAGE RESEARCH

ISSN： 0167-1987

年卷期： 2025 年 258 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Soil health assessment in heterogeneous agroecosystems presents significant challenges in integrating biological mechanisms and diagnosing multifactorial constraints. This study applied interpretable machine learning approaches to establish scientifically derived thresholds for constraint typology and provide spatially explicit diagnostics in farmlands of Ningbo, China. Eight soil health index (SHI) formulations were evaluated, incorporating combinations of total (TDS) versus minimum datasets (MDS) with linear and nonlinear scoring and integration methods. A random forest model was employed to identify key drivers of SHI, with SHAP (SHapley Additive exPlanations) values used to determine critical constraint thresholds. Structural equation modeling and microbial history strategy analyses were subsequently applied to quantify interactive mechanisms affecting soil health in sites with multiple constraints. Results demonstrated that SHI derived from the TDS using nonlinear weighted integration (TD-N-WQI) exhibited superior sensitivity to soil organic carbon (SOC) content (Pearson r = 0.840, p < 0.001) and effectively discriminated against different land-use types (ANOVA F = 50.5, p < 0.001). Microbial enzyme activities emerged as the predominant regulators of soil health, with N-Acetyl-beta-D-glucosaminidase (NAG, 28.2 %), beta-glucosidase (BG, 22.0 %), and xylanase (XYL, 13.9 %) collectively accounting for 64.1 % of feature importance, substantially exceeding contributions from SOC (9.40 %) and total nitrogen (7.80 %). Critical constraint thresholds were as follows: bulk density 1.13 g/cm(3), SOC 16.9 g/kg, electrical conductivity 0.160 mS/cm, pH 4.50 and 6.24, microbial biomass carbon 508 mg/kg, and enzymatic deficits (BG 90.0, NAG 40.7, XYL 15.0, beta-D-Cellobiohydrolase 20.0, acid phosphatase 439 nmol/g/h). Spatial analysis revealed that 39.2 % (127/324) of sites exhibited multiple constraints, predominantly in coastal areas where salinity indirectly reduced SOC through enzymatic and microbial suppression (beta = -0.150, p < 0.05). This study establishes that high microbial enzymatic activity, driven by Y-strategist microbial communities characterized by rapid growth and efficient resource processing, constitutes the core mechanism of soil health. These insights provide a robust, ML-driven framework that identifies critical constraint thresholds to guide precision management and prioritize microbial-based restoration in heterogeneous agricultural landscapes.

分类号：

  • 相关文献

[1]The bioaccumulation of Cd in rice grains in paddy soils as affected and predicted by soil properties. Ye, Xinxin,Wu, Liang,Sun, Bo,Ye, Xinxin,Li, Hongying,Ma, Yibing,Wu, Liang. 2014

[2]Effects of anaerobic digestion on chlortetracycline and oxytetracycline degradation efficiency for swine manure. Yin, Fubin,Dong, Hongmin,Tao, Xiuping,Chen, Yongxing,Ji, Chao.

[3]Impervious surface impact on water quality in the process of rapid urbanization in Shenzhen, China. Liu, Zhenhuan,Li, Zhengguo,Liu, Zhenhuan,Li, Zhengguo,Liu, Zhenhuan,Wang, Yanglin,Peng, Jian. 2013

[4]Quantification of southern rice black streaked dwarf virus and rice black streaked dwarf virus in the organs of their vector and nonvector insect over time. Wang, Biao,Wang, Xifeng,Ren, Yingdang,Lu, Chuantao.

[5]Bitterness quantification and simulated taste mechanism of theasinensin A from tea. Jian Yong Zhang,Hong Chun Cui,Zhi Hui Feng,Wei Wei Wang,Yun Zhao,Yu Liang Deng,He Yuan Jiang,Jun Feng Yin,Ulrich H. Engelhardt. 2023

[6]Bibliometric Analysis of the Influencing Factors, Derivation, and Application of Heavy Metal Thresholds in Soil. Du, Zhaolin,Lin, Dasong,Li, Haifeng,Li, Yang,Chen, Hongan,Dou, Weiqiang,Qin, Li,An, Yi. 2022

[7]Evaluation of environmental and physiological indicators in lactating dairy cows exposed to heat stress. Shu, Hang,Guo, Leifeng,Bindelle, Jerome,Fang, Tingting,Xing, Mingjie,Sun, Fuyu,Chen, Xiaoyang,Zhang, Wenju,Wang, Wensheng. 2022

[8]Evaluation of the effect of the indoor environment on the physiological responses of early-gestation sows in a commercial house in China. Yangyang Li,Tong Li,Bin Shang,Yang Zhao,Xiuping Tao,Feng Peng,Xiaojun Zou,Sixin Zhang. 2023

[9]Threshold-like effect of soil NO3− concentrations on denitrification product N2O/(N2O+N2) ratio is mediated by soil pH. Bowen Zhang,Minghua Zhou,Bo Zhu,Björn Kemmann,Lisa Pfülb,Stefan Burkart,Hongbin Liu,Klaus Butterbach-Bahl,Reinhard Well. 2023

[10]The impact of anthropogenic pressures on microbial diversity and river multifunctionality relationships on a global scale. Qian Qu,Shuting Wang,Xiangang Hu,Li Mu. 2024

[11]Assessing grassland degradation based on abrupt changes in living status of vegetation in a subalpine meadow. Zhang, Yong,Zhang, Yun,Ganjurjav, Hasbagan,Yue, Haitao,Tian, Kun,Wang, Hang,Zhang, Qiong,Zhao, Zijiao. 2025

[12]Differences In The Digestive Enzyme A.ctivity, Intestinal Mucosa And M icrobial Community In Loach Cultivated In Two Separate Environments. Yang, Song,Lin, Qiang,Zhao, Liu-lan,Du, Jie,Li, Ning-qiu,Du, Jun,Zhou, Jian,Duan, Yuan-liang,Xiao, Qing,Du, Zong-jun. 2018

[13]Cloning, expression and enzymatic characterization of 3-phosphoglycerate kinase from Schistosoma japonicum. Hong, Yang,Huang, Lini,Yang, Jianmei,Cao, Xiaodan,Han, Qian,Zhang, Min,Han, Yanhui,Fu, Zhiqiang,Zhu, Chuangang,Lu, Ke,Lin, Jiaojiao,Zhang, Min,Han, Yanhui,Li, Xiangrui,Lin, Jiaojiao.

[14]Environmental conditions rather than microbial inoculum composition determine the bacterial composition, microbial biomass and enzymatic activity of reconstructed soil microbial communities. Xun, Weibing,Zhao, Jun,Ran, Wei,Shen, Qirong,Zhang, Ruifu,Xun, Weibing,Zhao, Jun,Ran, Wei,Shen, Qirong,Zhang, Ruifu,Xun, Weibing,Zhang, Ruifu,Huang, Ting,Wang, Boren.

[15]Molecular characterization of enolase gene from Taenia multiceps. Li, W. H.,Qu, Z. G.,Zhang, N. Z.,Yue, L.,Jia, W. Z.,Luo, J. X.,Yin, H.,Fu, B. Q.,Jia, W. Z.,Luo, J. X.,Yin, H.,Fu, B. Q..

[16]CDNA cloning, expression, and enzymatic activity of a novel endogenous cellulase from the beetle Batocera horsfieldi. Xia, Dingguo,Xiang, Zhonghuai,Lu, Cheng,Xia, Dingguo,Wei, Yadong,Zhang, Guozheng,Zhao, Qiaoling,Zhang, Yeshun.

[17]Functional characterization of X-prolyl aminopeptidase from Toxoplasma gondii. Yang, Mingfa,Song, Mingxin,Yang, Mingfa,Zheng, Jun,Jia, Honglin. 2016

[18]Cloning, silencing, and prokaryotic expression of strawberry sucrose synthase gene FaSus1. Hua, L. N.,Zang, M.,Wang, S. F.,Shen, Y. Y.,Guo, J. X.,Li, Y. Z..

[19]Involvement of three putative glucosyltransferases from the UGT72 family in flavonol glucoside/rhamnoside biosynthesis in Lotus japonicus seeds. Yin, Qinggang,Shen, Guoan,Pang, Yongzhen,Yin, Qinggang,Chang, Zhenzhan,Tang, Yuhong,Gao, Hongwen.

[20]Mycoplasma synoviae enolase is a plasminogen/fibronectin binding protein. Bao, Shijun,Yu, Shengqing,Tan, Lei,Zhang, Fanqin,Sun, Yingjie,Qiu, Xusheng,Ding, Chan,Bao, Shijun,Guo, Xiaoqin,Ding, Jiabo,Chen, Guanghua. 2014

作者其他论文 更多>>