Prediction of atrazine degradation in soil based on XGBoost model

doi:10.13287/j.1001-9332.202403.016

Abstract

Abstract: We established the optimal model by using the automatic machine learning method to predict the degradation efficiency of herbicide atrazine in soil, which could be used to assess the residual risk of atrazine in soil. We collected 494 pairs of data from 49 published articles, and selected seven factors as input features, including soil pH, organic matter content, saturated hydraulic conductivity, soil moisture, initial concentration of atrazine, incubation time, and inoculation dose. Using the first-order reaction rate constant of atrazine in soil as the output feature, we established six models to predict the degradation efficiency of atrazine in soil, and conducted comprehensive analysis of model performance through linear regression and related evaluation indicators. The results showed that the XGBoost model had the best performance in predicting the first-order reaction rate constant (k). Based on the prediction model, the feature importance ranking of each factor was in an order of soil moisture > incubation time > pH > organic matter > initial concentration of atrazine > saturated hydraulic conductivity > inoculation dose. We used SHAP to explain the potential relationship between each feature and the degradation ability of atrazine in soil, as well as the relative contribution of each feature. Results of SHAP showed that time had a negative contribution and saturated hydraulic conductivity had a positive contribution. High values of soil moisture, initial concentration of atrazine, pH, inoculation dose and organic matter content were generally distributed on both sides of SHAP=0, indicating their complex contributions to the degradation of atrazine in soil. The XGBoost model method combined with the SHAP method had high accuracy in predicting the performance and interpretability of the k model. By using machine learning method to fully explore the value of historical experimental data and predict the degradation efficiency of atrazine using environmental parameters, it is of great significance to set the threshold for atrazine application, reduce the residual and diffusion risks of atrazine in soil, and ensure the safety of soil environment.

Key words: XGBoost model, prediction, atrazine, soil, degradation

LI Xiangling, CHEN Fengxian, CHEN Xijuan. Prediction of atrazine degradation in soil based on XGBoost model[J]. Chinese Journal of Applied Ecology, 2024, 35(3): 789-796.

References

[1] 陆长鸣, 李想, 徐明恺, 等. 一株高效广谱莠去津降解菌SB5的生长和降解特性. 应用生态学报, 2022, 33(1): 229-238
[2] Hansen SP, Messer TL, Mittelstet AR. Mitigating the risk of atrazine exposure: Identifying hot spots and hot times in surface waters across Nebraska, USA. Journal of Environmental Management, 2019, 250: 109424
[3] Bayati M, Numaan M, Kadhem A, et al. Adsorption of atrazine by laser induced graphitic material: An efficient, scalable and green alternative for pollution abatement. Journal of Environmental Chemical Engineering, 2020, 8: 104407
[4] Sun JT, Pan LL, Zhan Y, et al. Atrazine contamination in agricultural soils from the Yangtze River Delta of China and associated health risks. Environmental Geochemistry and Health, 2017, 39: 369-378
[5] Cerejeira MJ, Viana P, Batista S, et al. Pesticides in Portuguese surface and ground waters. Water Research, 2003, 37: 1055-1063
[6] Ge J, Cong J, Sun Y, et al. Determination of endocrine disrupting chemicals in surface water and industrial wastewater from Beijing, China. Bulletin of Environmental Contamination and Toxicology, 2010, 84: 401-405
[7] Wang YH, An XH, Shen WF, et al. Individual and combined toxic effects of herbicide atrazine and three insecticides on the earthworm, Eisenia fetida. Ecotoxicology, 2016, 25: 991-999
[8] Chen JY, Liu J, Wu S, et al. Atrazine promoted epithelial ovarian cancer cells proliferation and metastasis by inducing low dose reactive oxygen species (ROS). Iranian Journal of Biotechnology, 2021, 19: 89-100
[9] Liu JT, Zhou JH, Guo QN, et al. Physiochemical assessment of environmental behaviors of herbicide atrazine in soils associated with its degradation and bioavailability to weeds. Chemosphere, 2021, 262: 127830
[10] Wei T, Huang F, Li H, et al. Effects of biochar from different raw materials on atrazine removal and microbial community structure in farmland soil. Journal of Southern Agriculture, 2022, 53: 2457-2467
[11] Fan Z, Li Y, Chen S, et al. Isolation and identification of atrazine-degrading bacterial strain W24 and its remediation effect on soil. Journal of Maize Science, 2021, 29: 172-177
[12] 苗辉, 冯莉, 姚强, 等. 环境因素对华南地区土壤中莠去津降解的影响. 江西农业大学学报, 2016, 38(5): 884-889
[13] Gao TC, Tian HX, Wang ZQ, et al. Effects of atrazine on microbial metabolic limitations in black soils: Evidence from enzyme stoichiometry. Chemosphere, 2023, 334: 139045
[14] Ngigi A, Dorfler U, Scherb H, et al. Effect of fluctuating soil humidity on in situ bioavailability and degradation of atrazine. Chemosphere, 2011, 84: 369-375
[15] Boopathy R. Anaerobic degradation of atrazine. International Biodeterioration & Biodegradation, 2017, 119: 626-630
[16] Cycoń M, Mrozik A, Piotrowska-Seget Z. Bioaugmentation as a strategy for the remediation of pesticide-polluted soil: A review. Chemosphere, 2017, 172: 52-71
[17] Li Z, Long ZL, Lei S, et al. Evaluating the corrosion resistance of marine steels under different exposure environments via machine learning. Physica Scripta, 2023, 98: 015402
[18] Zhang K, Zhong SF, Zhang HC. Predicting aqueous adsorption of organic compounds onto biochars, carbon nanotubes, granular activated carbons, and resins with machine learning. Environmental Science & Technology, 2020, 54: 7008-7018
[19] Yang HR, Huang K, Zhang K, et al. Predicting heavy metal adsorption on soil with machine learning and mapping global distribution of soil adsorption capacities. Environmental Science & Technology, 2021, 55: 14316-14328
[20] Prado B, Duwig C, Hidalgo C, et al. Transport, sorption and degradation of atrazine in two clay soils from Mexico: Andosol and Vertisol. Geoderma, 2014, 232: 628-639
[21] Sun Y, Zhang YY, Lu L, et al. The application of machine learning methods for prediction of metal immobilization remediation by biochar amendment in soil. Science of the Total Environment, 2022, 829: 154668
[22] LeDell E, Poirier S. H2O Auto ML: Scalable Automatic Machine Learning[EB/OL]. (2023-08-30) [2023-08-30]. https://www.automl.org/wp-content/uploads/2020/07/AutoML_2020_paper_61.pdf
[23] Chen TQ, Guestrin C. XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, California,USA, 2016:785-794
[24] Lundberg SP, Lee SI. A Unified Approach to Interpreting model Predictions[EB/OL]. (2023-08-30)[2023-11-25].http://arxiv.org/abs/1705.07874
[25] 宋佳, 潘妍, 王皙玮, 等. 除草剂阿特拉津在土壤中降解方式的研究现状. 中国农学通报, 2022, 38(25): 90-95
[26] Qu MJ, Liu GL, Zhao JW, et al. Fate of atrazine and its relationship with environmental factors in distinctly different lake sediments associated with hydrophytes. Environmental Pollution, 2020, 256: 113371
[27] Schaap MG, Leij FJ,van Genuchten MT. Rosetta: A computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions.Journal of Hydrology,2001, 251: 163-176
[28] 何海龙, 齐雁冰, 吕家珑, 等. 中国土壤质地分类系统的发展与建议修订方案. 农业资源与环境学报, 2023, 40(3): 501-510
[29] Chowdhury IF, Rohan M, Stodart BJ, et al. Persistence of atrazine and trifluralin in a clay loam soil undergoing different temperature and moisture conditions. Environmental Pollution, 2021, 276: 116687
[30] Li W, Meng PQ, Hong Y, et al. Using deep learning to preserve data confidentiality. Applied Intelligence, 2020, 50: 341-353
[31] Aggelopoulos CA, Tataraki D, Rassias G. Degradation of atrazine in soil by dielectric barrier discharge plasma: Potential singlet oxygen mediation. Chemical Engineering Journal, 2018, 347: 682-694
[32] Yang FS, Yang SY, Xu JL, et al. Dynamic response of soil enzymes and microbial diversity to continuous application of atrazine in black soil of a cornfield without rotation in northeast China. Diversity,2021, 13: 259
[33] Zhao Y, Li X, Li YY, et al. Rapid biodegradation of atrazine by a novel Paenarthrobacter ureafaciens ZY and its effects on soil native microbial community dynamic. Frontiers in Microbiology, 2023, 13: 1103168
[34] Fan XZ, Lu B, Gong AJ. Dynamics of solar light photodegradation behavior of atrazine on soil surface. Journal of Hazardous Materials, 2005, 117: 75-79
[35] Zablotowicz RM, Krutz LJ, Reddy KN, et al. Rapid development of enhanced atrazine degradation in a dundee silt loam soil under continuous corn and in rotation with cotton. Journal of Agricultural and Food Chemistry, 2007, 55: 852-859
[36] Wang QF, Xie SG. Isolation and characterization of a high-efficiency soil atrazine-degrading Arthrobacter sp. strain. International Biodeterioration & Biodegradation, 2012, 71:61-66
[37] 乔雄梧, 马利平. 阿特拉津在土壤中的降解途径及其对持留性的影响. 农村生态环境, 1995, 11(4): 5-8
[38] Nogueira JMF, Sandra T, Sandra P. Multiresidue screening of neutral pesticides in water samples by high performance liquid chromatography-electrospray mass spectrometry. Analytica Chimica Acta, 2004, 505: 209-215
[39] Abigail M, Lakshmi, Das N. Biodegradation of atrazine by Cryptococcus laurentii isolated from contaminated agricultural soil. Journal of Microbiology and Biotechnology Research, 2017, 2: 450-457
[40] Zhao XY, Wang L, Ma F, et al. Pseudomonas sp. ZXY-1, a newly isolated and highly efficient atrazine-degrading bacterium, and optimization of biodegradation using response surface methodology. Journal of Environmental Sciences, 2017, 54: 152-159
[41] 赵昕悦, 马放, 杨基先, 等. 阿特拉津降解菌Pseudomonas sp. ZXY-1的分离鉴定及降解动力学. 哈尔滨工业大学学报, 2018, 50(2): 82-88
[42] 杨立杰, 施德志, 彭湃, 等. 阿特拉津降解菌ATR3的分离鉴定与土壤修复. 微生物学杂志, 2021, 41(5): 37-42
[43] 南超. 阿特拉津降解菌Arthrobacter sp. DNS10在黑土中定殖能力与基因表达情况研究. 硕士论文. 哈尔滨: 东北农业大学, 2015