• ▶ 2008-2024年被中国情报信息研究所评价中心评为“中国科技核心期刊”
  • ▶ 2019-2024年连续三届被中国科学院文献情报中心中国科学引文数据库CSCD(核心库)收录
  • ▶ 2021、2023年入编北京大学图书馆《中文核心期刊要目总览》
  • ▶ 2020-2024连续四年入选《科技期刊世界影响力指数(WJCI)报告》
卓 越, 严海军.基于梯度提升树算法的玉米施肥模型构建水资源与水工程学报[J].,2020,31(4):223-228
基于梯度提升树算法的玉米施肥模型构建
Construction of maize fertilization model based on gradient boosting decision tree algorithm
  
DOI:10.11705/j.issn.1672-643X.2020.04.32
中文关键词:  施肥模型  梯度提升树算法  施肥量  产量  玉米
英文关键词:fertilization model  gradient boosting decision tree algorithm  fertilizer application rate  yield  maize
基金项目:国家重点研发计划项目(2017YFD0201502); 国家自然科学基金项目(51939005)
作者单位
卓 越, 严海军 (中国农业大学 水利与土木工程学院 北京 100083) 
摘要点击次数: 795
全文下载次数: 344
中文摘要:
      为了模拟作物的土壤养分含量、施肥量与产量之间的非线性关系,利用玉米“3414”试验数据进行插值,以土壤养分含量和施肥量作为输入量,产量作为输出量,使用梯度提升树(GBDT)算法建立施肥模型,并与BP神经网络(BPNN)、支持向量回归(SVR)、随机森林(RF)算法建立的施肥模型进行对比。结果表明:应用构建的GBDT模型得到的玉米产量平均相对误差、平均绝对误差和均方根误差分别为0.46%、48.7和62.2 kg/hm2,优于其他3种算法。基于GBDT算法的施肥模型在模拟土壤养分含量、施肥量与产量之间关系时具有较高精度,对于指导精准施肥具有较强的应用价值。
英文摘要:
      In order to simulate the nonlinear relationship between soil nutrient, fertilizer application rate and crop yield, a fertilization model based on the gradient boosting decision tree (GBDT) algorithm was established taking soil nutrient content and fertilization application rate as input, crop yield as output with the interpolation of the “3414”maize experiment data. Meanwhile the back propagation neural network (BPNN) model, support vector regression (SVR) model and random forest (RF) model were taken as the reference models. The results showed that the average relative error, the mean absolute error and the root mean square error of the GBDT algorithm were 0.46%, 48.7 kg/hm2 and 62.2 kg/hm2 respectively, which are better than the other three algorithms. It indicates that the fertilization model based on GBDT algorithm can achieve higher precision in simulating the relationship between soil nutrient, fertilizer application rate and crop yield, and can be widely applied in the guidance of precision fertilization.
查看全文  查看/发表评论  下载PDF阅读器
关闭