基于不同机器学习方法的典型冬小麦-夏玉米农田CO2 通量模拟研究

打开文本图片集
关键词: CO2 通量;机器学习模型;影响因素;模拟能力;冬小麦;夏玉米;农田 中图分类号:X71;S512.11;S513文献标志码:A文章编号:2095-6819(2025)05-1172-12doi:10.13254/j.jare.2024.0347
Simulation of CO2 fluxes in a typical winter wheat-summer maize cropland based on different machine learningmethods
TANGHuan’,YEJian1,YINHua',GAO Zhenxiang1,WANGJinjie1,LICheng2 (1.Suqianellea;latoeUsio)
Abstract:In order to investigate the influencing factors ofCO -2 fluxes in the typical winter wheat-summer maize cropland and assess the simulationabilityofdiferentmachineleaingmodels,awinterwheatsummermaizecroplandatYuchengComprehensiveExperiental StationfChinaEcossteReseachetworkwassectedasacasestudy.Webtainedtheataofmeteorologysoil,andopgothnd usedsixmachinelearningalgoritsincludingtheCategoicalBosting(CATBost),ExtremeGradientBoosting(XGBost)ort Vector Machines(SV),ArtificialNeuralNetwork(AN),RandomForest(RF)andKNearestNeighborMethod(KNN),toaalyzethe accuracyof theirsimulationsofdailynetcosystem exchange(NEE),grossprimary productivity(GPP)andecosystemrespiratio(Re). Theresultsshowedtatfordiferentmacinelearingmodels,teCATBostmodelhadeteraccuracythantheothermodelsinsiulating cropland NEE, GPP and Re andhad the strongest generalization ability;the XGBoost model ranked second.For diffrent combinations of inputariables,thimulationefetofchmachinelearngmodelwasestwhenitincudedmeteorologicalvarables,soilarablesand cropvariables,folowedbyteinclusionofmeteorologicalvariablesandopvariables,whilethesimulationfectofteinclusionof meteorologicalvariablesandsoilvariableswasrelativelyweak.Fordiferentcoplandtypes,teperformanceofthesixmachineleaing models with different combinations of input variables was better for NEE , GPP and Re for the winter wheat field than for the corresponding summer maize field, respectively. Among them,the simulation accuracy of GPP and Re for the winter wheat field was similar and better thanNEE,while thesimulationreadinessof NEE and GPP for summer maize field was similar and better than Re.
Keywords:COzflux;machinelearming model; influencing factor;simulationability; winterwheat;summer maize;cropland
农田是陆地生态系统的重要组分之一,由于其受人为干扰和环境条件等因素的影响较大,是较为活跃的碳库,对维持生态系统碳平衡具有重要作用。(剩余17068字)