Prediction of greenhouse gas emissions from agricultural fields with and without cover crops

被引:5
作者
Kotlar, Ali Mehmandoost [1 ,2 ]
Singh, Jasdeep [3 ]
Kumar, Sandeep [4 ]
机构
[1] Flanders Res Inst Agr Fisheries & Food ILVO, Plant Sci Unit, B-9090 Melle, Belgium
[2] Catholic Univ Louvain, Earth & Life Inst, Croix Sud 2, B-1348 Louvain La Neuve, Belgium
[3] Texas A&M AgriLife Res & Extens Ctr, Vernon, TX 76385 USA
[4] South Dakota State Univ, Dept Agron Hort & Plant Sci, Brookings, SD 57007 USA
关键词
N2O EMISSIONS; SOYBEAN ROTATION; CLIMATE-CHANGE; FLUXES; MANAGEMENT; TILLAGE; SYSTEMS; CORN; IMPACTS; MODEL;
D O I
10.1002/saj2.20429
中图分类号
S15 [土壤学];
学科分类号
0903 ; 090301 ;
摘要
The significant contribution of greenhouse gas (GHG) emissions to global climate change and stratospheric ozone depletion has been calling the attention to assess the effect of agricultural management on them. Although machine learning (ML) methods have been widely used for the quantification of various inherent and dynamic soil properties, the accuracy of these techniques in the prediction of agricultural soil GHG emissions remains unclear. Therefore, this study aims at evaluating the performance of six different ML methods including simple linear regression, Cubist, support vector machines (SVM) with three different kernel functions, and random forest (RF) for the prediction of CO2 and N2O fluxes from plots managed with and without cover cropping. The input parameters include typical meteorological data as well as soil temperature and soil water content. Results show that the daily flux of CO2 is positively correlated with soil temperature and solar radiation and negatively with soil water content, whereas daily N2O flux is positively correlated with soil water content. For plots without cover cropping, Cubist and SVM with polynomial kernel function outperformed in the prediction of the testing dataset with RMSE of 14.18 kg ha(-1) d(-1) and 11.52 g ha(-1) d(-1) for daily CO2 and N2O emissions, respectively. Where cover cropping was considered, SVM with radial basis function and Cubist were the best models in the prediction of daily CO2 and N2O fluxes with respective RMSE values of 15.71 kg ha(-1) d(-1) and 14.12 g ha(-1) d(-1). Considering the ranking of the models for all scenarios and both GHGs, SVM with nonlinear kernel functions and Cubist method surpassed other ML techniques.
引用
收藏
页码:1227 / 1240
页数:14
相关论文
共 50 条
  • [21] Agricultural greenhouse gas emissions of an Indian village-Who's to blame: crops or livestock?
    Hemingway, Charlotte
    Vigne, Mathieu
    Aubron, Claire
    [J]. SCIENCE OF THE TOTAL ENVIRONMENT, 2023, 856
  • [22] Effect of cover crops on greenhouse gas emissions in an irrigated field under integrated soil fertility management
    Guardia, Guillermo
    Abalos, Diego
    Garcia-Marco, Sonia
    Quemada, Miguel
    Alonso-Ayuso, Maria
    Cardenas, Laura M.
    Dixon, Elizabeth R.
    Vallejo, Antonio
    [J]. BIOGEOSCIENCES, 2016, 13 (18) : 5245 - 5257
  • [23] Dissolved greenhouse gas emissions from agricultural groundwater irrigation in the Guanzhong Basin of China
    Huo, Pan
    Li, Hao
    Huang, Xunrong
    Ma, Xuzhe
    Liu, Lin
    Ji, Wei
    Liu, Yike
    Gao, Pengcheng
    [J]. ENVIRONMENTAL POLLUTION, 2022, 309
  • [24] A stochastic optimization approach to reduce greenhouse gas emissions from buildings and transportation
    Karan, Ebrahim
    Asadi, Somayeh
    Ntaimo, Lewis
    [J]. ENERGY, 2016, 106 : 367 - 377
  • [25] Machine learning for predicting greenhouse gas emissions from agricultural soils
    Hamrani, Abderrachid
    Akbarzadeh, Abdolhamid
    Madramootoo, Chandra A.
    [J]. SCIENCE OF THE TOTAL ENVIRONMENT, 2020, 741
  • [26] Greenhouse Gas Emissions from Pecan Orchards in Semiarid Southern New Mexico
    Kellum, Darby S.
    Shukla, Manoj K.
    Mexal, John
    Deb, Sanjit
    [J]. HORTSCIENCE, 2018, 53 (05) : 704 - 709
  • [27] Greenhouse Gas Emissions from Agricultural Soils: Sources and Mitigation Potential
    Benbi, Dinesh K.
    [J]. JOURNAL OF CROP IMPROVEMENT, 2013, 27 (06) : 752 - 772
  • [28] Assessing uncertainties and discrepancies in agricultural greenhouse gas emissions estimation in China: A comprehensive review
    Li, Hanbing
    Jin, Xiaobin
    Zhao, Rongqin
    Han, Bo
    Zhou, Yinkang
    Tittonell, Pablo
    [J]. ENVIRONMENTAL IMPACT ASSESSMENT REVIEW, 2024, 106
  • [29] Exploring the role of high-value crops to reduce agricultural greenhouse gas emissions in New Zealand
    Thomas, Steve M.
    Ausseil, Anne-Gaelle
    Guo, Jing
    Herzig, Alexander
    Khaembah, Edith
    Renwick, Alan
    Teixeira, Edmar
    van der Weerden, Tony
    Wakelin, Steve J.
    Vetharaniam, Indrakumar
    [J]. REGIONAL ENVIRONMENTAL CHANGE, 2024, 24 (03)
  • [30] Effects of water management on greenhouse gas emissions from farmers' rice fields in Bangladesh
    Islam, S. M. Mofijul
    Gaihre, Yam Kanta
    Islam, Md Rafiqul
    Akter, Mahmuda
    Al Mahmud, Abdullah
    Singh, Upendra
    Sander, Bjoern Ole
    [J]. SCIENCE OF THE TOTAL ENVIRONMENT, 2020, 734