基于随机森林的作物模型光温产量潜力模拟优化方法  

The crop light temperature yield potential simulation optimization method based on random forest

作　　者：徐浩 宋华鲁 张海波 张小虎[3] 王帅 XU Hao;SONG Hua-lu;ZHANG Hai-bo;ZHANG Xiao-hu;WANG Shuai(Institute of Agricultural Information and Economics,Shandong Academy of Agricultural Sciences,Jinan 250100,China;Agricultural Economic Service Center of Zhaoyuan Agricultural and Rural Bureau,Zhaoyuan 265400,Shandong,China;National Engineering and Technology Center for Information Agriculture,Nanjing Agricultural University,Nanjing 210095,China)

机构地区：[1]山东省农业科学院农业信息与经济研究所,济南250100 [2]招远市农业农村局农经服务中心,山东招远265400 [3]南京农业大学国家信息农业工程技术中心,南京210095

出　　处：《湖北农业科学》2024年第8期132-139,共8页Hubei Agricultural Sciences

基　　金：山东省自然科学基金项目(ZR2021QC183);山东省农业科学院农业科技创新工程项目(CXGC2023A34)。

摘　　要：为有效降低作物模拟所需数据量,提高计算效率,基于机器学习建立冬小麦光温产量潜力估算模型。以中国冬麦区129个农业气象站点1980—2009年光温产量潜力为研究对象,选择影响光温产量潜力模拟较大的温度、日照时数、经纬度等构建特征变量。选择生长季与月份2个时间范围,基于WheatGrow模型输入输出数据建立生长季变量的随机森林模型(RF_GS)与月份变量的随机森林模型(RF_Mon),最后利用均方根误差(RMSE)评价随机森林模型的性能。结果表明,随机森林模型可在保证模拟精度的前提下降低数据需求量,且RF_GS精度优于RF_Mon;变量重要性检验与部分依赖图分析结果表明,纬度、生长季日照时数、5月日照时数、3月最低温度对光温产量潜力模拟影响较大;若模型验证数据的范围超出训练数据的范围,利用随机森林模型无法保证建模精度。In order to effectively reduce the amount of data required for crop simulation and improve computing efficiency,a model for estimating the light-temperature yield potential of winter wheat was established based on machine learning.Taking 129 agro-meteoro⁃logical stations in the winter wheat region of China from 1980 to 2009 as the research object,the characteristic variables of tempera⁃ture,sunshine hours,latitude and longitude,etc.,which had a great influence on the simulation of photoperiod yield potential were selected.Based on the input and output data of WheatGrow model,the random forest model(RF_GS)and the random forest model(RF_Mon)with the variables of growing season and month were established.Finally,the performance of the random forest model was evaluated by root mean square error(RMSE).The results showed that the random forest model could reduce the data requirement un⁃der the premise of ensuring the simulation accuracy,and the accuracy of RF_GS was better than that of RF_Mon.The results of the variable importance test and partial dependence plots showed that latitude,sunshine duration in the growing season,sunshine dura⁃tion in May and minimum temperature in March had a great influence on photoperiod yield potential simulation.If the range of model validation data exceeded the range of training data,the random forest model’s accuracy could not be guaranteed.

关 键 词：作物模型 WheatGrow模型 随机森林 光温产量潜力 模拟优化方法 

分 类 号：S512.1[农业科学—作物学] S127