融合随机森林-递归特征消除的冬黑麦产量预测模型的建立

吕林有; 李佳慧; 赵艳; 马艳; 何梓源

doi:10.13300/j.cnki.hnlkxb.2026.03.005

您当前的位置：

首页 >

文章列表页 >

融合随机森林-递归特征消除的冬黑麦产量预测模型的建立

农业人工智能专题 | 更新时间：2026-11-05

- 融合随机森林-递归特征消除的冬黑麦产量预测模型的建立
- Establishment of a model for predicting yield of winter rye with a hybrid random forest-recursive feature elimination
- 华中农业大学学报 2026年45卷第3期页码：56-67
- 作者机构：
  
  1.辽宁工程技术大学环境科学与工程学院，阜新 123000
  2.辽宁省沙地治理与利用研究所，阜新 123000
- 作者简介：
- 基金信息：
  
  国家重点研发计划项目(2024YFD1501405);辽宁省科技攻关专项(2023JH1/10400001)
- DOI：10.13300/j.cnki.hnlkxb.2026.03.005
  中图分类号： S512.5
- 收稿：2025-11-23，
  
  纸质出版：2026-05-25
- 稿件说明：
移动端阅览
吕林有，李佳慧，赵艳，等.融合随机森林-递归特征消除的冬黑麦产量预测模型的建立［J］.华中农业大学学报，2026，45（3）：56‐67.

.Establishment of a model for predicting yield of winter rye with a hybrid random forest-recursive feature elimination[J].Journal of Huazhong Agricultural University,2026,45(03):56-67.
吕林有，李佳慧，赵艳，等.融合随机森林-递归特征消除的冬黑麦产量预测模型的建立［J］.华中农业大学学报，2026，45（3）：56‐67. DOI： 10.13300/j.cnki.hnlkxb.2026.03.005.

.Establishment of a model for predicting yield of winter rye with a hybrid random forest-recursive feature elimination[J].Journal of Huazhong Agricultural University,2026,45(03):56-67. DOI： 10.13300/j.cnki.hnlkxb.2026.03.005.

摘要

针对传统模型难以解析行距-播种量互作非线性效应的问题，通过双因素田间梯度试验，系统测定冬黑麦关键生育期生物学性状与产量构成要素指标，解析关键生育期群体动态与产量构成的互作效应，构建融合随机森林-递归特征消除的冬黑麦产量预测模型。田间试验结果显示，40 cm行距×600 g/40 m

播种量处理组合能够优化冠层透光率、平衡“源-库”关系及提升抗逆性，实现冬黑麦高产稳产的协同调控；在冬黑麦完全成熟期，系统采集不同处理组的植株样本，并采用标准化试验流程对关键农艺性状，包括穗长、穗质量、穗节数、株高、根长、有效分蘖数、叶片数以及单株种子数进行量化表征，共获得540组有效数据，以单株种子数为预测目标，构建了包含播种行距、播种量、穗长、穗质量、穗节数、株高、根长、有效分蘖数、叶片数等原始变量及6个衍生特征的多维特征集，构建递归特征消除的随机森林（random forest-recursive feature elimination，RF-RFE）模型，模型表现出优异的预测性能（

²=0.951，RMSE=2.28）和泛化能力（OOB-RMSE=4.33）。通过产量预测模型反演获得行距-播种量三维响应曲面，确定了高产参数为行距35~49 cm、播种量535~680 g/40 m

；边际效应揭示行距

45 cm时每增加1 cm减产1.23 kg，播种量

650 g/40 m

时边际收益递减。因此，建议生产实践中将行距控制在40~45 cm，播种量控制在600~650 g/40 m

，既可保证高产又留出操作容错空间。

Abstract

A two-factor field gradient experiment was conducted to solve the problems of traditional models being difficult to analyze the nonlinear effects of interaction between row spacing and sowing rate. The biological traits and yield components at the stages of key growth in winter rye were systematically measured. The patterns of interaction between population dynamics and yield

components during these stages were analyzed to construct a recursive gradient fusion-based random forest model for predicting the yield of winter rye. The results of field experiment showed that the combination of a row spacing of 40 cm and a sowing rate of 535-680 g/40 m

can optimize the light transmittance of canopy， balance the “source sink” relationship， and improve the resistance to stress， achieving coordinated regulation of high and stable yield of winter rye. Samples of plant were systematically collected from different treatment groups at the stage of full maturity in winter rye. A standardized experimental procedure was used to quantitatively characterize key agronomic traits including spike length， spike mass， number of spike nodes， plant height， root length， effective tiller count， leaf count， and seeds per plant. 540 sets of valid data were obtained. A multidimensional feature set encompassing sowing row spacing， seeding rate， spike length， spike mass， number of spike nodes， plant height， root length， effective tiller count， leaf count， and six derived features was constructed using seeds per plant as the prediction target. A hybrid random forest-recursive feature elimination （RF-RFE） with excellent predictive performance （

²=0.951， RMSE=2.28） and generalization ability （OOB-RMSE=4.33） was constructed. The model for predicting yield was used to invert and obtain a three-dimensional response surface for row spacing and seeding rate to identify the high-yield parameters as row spacing ranging from 35 to 49 cm and seeding rate between 535 and 680 g/40 m

. The results of marginal effect showed that a 1 cm increase in row spacing beyond 45 cm led to a yield decrease of 1.23 kg， and the marginal benefit decreased as the seeding rate exceeded 650 g/40 m

. Therefore， it is recommended to control the row spacing within 40-45 cm and the seeding rate between 600-650 g/40 m

in the practice of production， which can ensure high yield and leave room f

or the tolerance of operational error.

关键词

Keywords

references

CHIKMAWATI T，MIFTAHUDIN M，SKOVMAND B，et al.Amplified fragment length polymorphism-based genetic diversity among cultivated and weedy rye （ Secale cereale L.） accessions［J］.Genetic resources and crop evolution，2012，59（8）：1743-1752.

KOISTINEN V M，HANHINEVA K.Microbial and endogenous metabolic conversions of rye phytochemicals［J/OL］.Molecular nutrition & food research，2017，61（7）：1600627［2025-11-23］.https：//doi.org/10.1002/mnfr.201600627.

BAZHENOV M，LITVINOV D，KARLOV G，et al.Evaluation of phosphate rock as the only source of phosphorus for the growth of tall and semi-dwarf durum wheat and rye plants using digital phenotyping［J/OL］.PeerJ，2023，11：e15972［2025-11-23］. https：//doi.org/10.7717/peerj.15972.

王毓，李奇铮，马小东，等.播种期及收获期对饲用小黑麦生产性能和营养品质的影响［J］.草地学报，2024，32（2）：637-645. WANG Y，LI Q Z，MA X D，et al.Effects of different sowing and cutting periods study on the production performance and nutritional value of Triticosecale wittmack in rain-fed area of Ningxia［J］.Acta agrestia sinica，2024，32（2）：637-645 （in Chinese with English abstract） .

孔广超，曹连莆，艾尼瓦尔，等.高产优质小黑麦新品种：新小黑麦3号［J］.麦类作物学报，2005，25（2）：149. KONG G C，CAO L P，AIN，et al.New Triticale No.3：a new Triticale variety with high yield and good quality［J］.Acta tritical crops，2005，25（2）：149 （in Chinese） .

王汇涵，张泽，康孝岩，等.基于Sentinel-2A的棉花种植面积提取及产量预测［J］.农业工程学报，2022，38（9）：205-214. WANG H H，ZHANG Z，KANG X Y，et al.Cotton planting area extraction and yield prediction based on Sentinel-2A［J］.Transactions of the CSAE，2022，38（9）：205-214 （in Chinese with English abstract） .

王莺，巩垠熙.遥感光谱技术在农作物估产中的应用研究进展［J］.中国农学通报，2019，35（3）：69-75. WANG Y，GONG Y X.Spectral remote sensing technology applied in crop yield estimation：research progress［J］.Chinese agricultural science bulletin，2019，35（3）：69-75 （in Chinese with English abstract） .

CLAUSS K，OTTINGER M，LEINENKUGEL P，et al.Estimating rice production in the Mekong Delta，Vietnam，utilizing time series of Sentinel-1 SAR data［J］.International journal of applied earth observation and geoinformation，2018，73：574-585.

BATTUDE M，AL BITAR A，MORIN D，et al.Estimating maize biomass and yield over large areas using high spatial and temporal resolution Sentinel-2 like remote sensing data［J］.Remote sensing of environment，2016，184：668-681.

TAŞAN S，CEMEK B，TAŞAN M，et al.Estimation of eggplant yield with machine learning methods using spectral vegetation indices［J/OL］.Computers and electronics in agriculture，2022，202：107367［2025-11-23］.https：//doi.org/10.1016/j.compag.2022.107367.

兰铭，费帅鹏，禹小龙，等.多光谱与热红外数据融合在冬小麦产量估测中的应用［J］.麦类作物学报，2021，41（12）：1564-1572. LAN M，FEI S P，YU X L，et al.Application of multispectral and thermal infrared data fusion in estimation of winter wheat yield［J］.Journal of triticeae crops，2021，41（12）：1564-1572 （in Chinese with English abstract） .

甄佳宁，蒋侠朋，赵德梅，等.利用Sentinel-2影像超分辨率重建的红树林冠层氮含量反演［J］.遥感学报，2022，26（6）：1206-1219. ZHEN J N，JIANG X P，ZHAO D M，et al.Retrieving canopy nitrogen content of mangrove forests from Sentinel-2 super-resolution reconstruction data［J］.National remote sensing bulletin，2022，26（6）：1206-1219 （in Chinese with English abstract） .

郭晗，陆洲，徐飞飞，等.基于全局敏感性分析与机器学习的冬小麦叶面积指数估算［J］.浙江农业学报，2022，34（9）：2020-2031. GUO H，LU Z，XU F F，et al.Leaf area index estimation of winter wheat based on global sensitivity analysis and machine learning［J］.Acta agriculturae Zhejiangensis，2022，34（9）：2020-2031 （in Chinese with English abstract） .

PANEK-CHWASTYK E，PARADOWSKI K，RUTKOWSKA B，et al.Advancing early-stage plant phosphorus assessment for winter rye via hyperspectral data：a model-based approach harnessing feedforward neural networks［J/OL］.European journal of agronomy，2025，169：127667［2025-11-23］.https：//doi.org/10.1016/j.eja.2025.127667.

HANSEN V，ENGEDAL T，RASMUSEN J，et al.Quantifying cover crop-derived above- and belowground carbon inputs including rhizodeposition［J/OL］.Agriculture，ecosystems & environment，2025，389：109668［2025-11-23］.https：//doi.org/10.1016/j.agee.2025.109668.

李涛宇，许秀春，杨轩，等.利用机器学习预测华北地区冬小麦农田氮淋失［J］.中国环境科学，2025，45（1）：343-354. LI T Y，XU X C，YANG X，et al.Prediction of nitrogen leaching from winter-wheat production in North China based on random forest and XGBoost［J］.China environmental science，2025，45（1）：343-354 （in Chinese with English abstract） .

JOHNSON M D，HSIEH W W，CANNON A J，et al.Crop yield forecasting on the Canadian Prairies by remotely sensed vegetation indices and machine learning methods［J］.Agricultural and forest meteorology，2016，218/219：74-84.

刘峻明，和晓彤，王鹏新，等.长时间序列气象数据结合随机森林法早期预测冬小麦产量［J］.农业工程学报，2019，35（6）：158-166. LIU J M，HE X T，WANG P X，et al.Early prediction of winter wheat yield with long time series meteorological data and random forest method［J］.Transactions of the CSAE，2019，35（6）：158-166 （in Chinese with English abstract） .

HUBER F，YUSHCHENKO A，STRATMANN B，et al.Extreme gradient boosting for yield estimation compared with deep learning approaches［J/OL］.Computers and electronics in agriculture，2022，202：107346［2025-11-23］.https：//doi.org/10.1016/J.COMPAG.2022.107346.

NYÉKI A，KEREPESI C，DARÓCZY B，et al.Application of spatio-temporal data in site-specific maize yield prediction with machine learning methods［J］.Precision agriculture，2021，22（5）：1397-1415.

CAI Y P，GUAN K Y，LOBELL D，et al.Integrating satellite and climate data to predict wheat yield in Australia using machine learning approaches［J］.Agricultural and forest meteorology，2019，274：144-159.

CĂLIN A D，COROIU A M，MUREŞAN H B.Analysis of preprocessing techniques for missing data in the prediction of sunflower yield in response to the effects of climate change［J/OL］.Applied sciences，2023，13（13）：7415［2025-11-23］.https：//doi.org/10.3390/app13137415.

BANERJEE S，NANDI T，SATI V P，et al.Integrating remote sensing，landscape metrics，and random forest algorithm to analyze crop patterns，factors，diversity，and fragmentation in a kharif agricultural landscape［J/OL］.Land，2025，14（6）：1203［2025-11-23］.https：//doi.org/10.3390/land14061203.

MENG X Y，ZHANG S，WANG G Q，et al.Decoding agricultural drought resilience：a triple-validated random forest framework integrating multi-source remote sensing for high-resolution monitoring in the North China plain［J/OL］.Remote sensing，2025，17（8）：1404［2025-11-23］.https：//doi.org/10.3390/RS17081404.

LUO D，QIAO X Q.Regional agricultural drought vulnerability prediction based on interpretable random forest［J/OL］.Environmental monitoring and assessment，2024，196（11）：1123［2025-11-23］.https：//doi.org/10.1007/S10661-024-13203-Y.

DHANOA M S，SANDERSON R，LISTER S J，et al.Decision tree learning with random forest models using agricultural and ecological field data incorporating multi-factor studies and covariate structure［J/OL］.CABI reviews，2024：cabireviews，2024.0030［2025-11-23］.https：//doi.org/10.1079/CABIREVIEWS.2024.0030.

王俊，吴振伟，姜海，等.基于随机森林及遥感植被指数的无人农场水稻产量预测研究［J］.智能化农业装备学报（中英文），2025，6（2）：97-104. WANG J，WU Z W，JIANG H，et al.Rice yield prediction of unmanned farm based on random forest and remote sensing vegetation index［J］.Journal of intelligent agricultural mechanization，2025，6（2）：97-104 （in Chinese with English abstract） .

徐浩，宋华鲁，张海波，等.基于随机森林的作物模型光温产量潜力模拟优化方法［J］.湖北农业科学，2024，63（8）：132-139. XU H，SONG H L，ZHANG H B，et al.The crop light temperature yield potential simulation optimization method based on random forest［J］.Hubei agricultural sciences，2024，63（8）：132-139 （in Chinese with English abstract） .

MADDONNI G A，OTEGUI M E.Leaf area，light interception，and crop development in maize［J］.Field crops research，1996，48（1）：81-87.

POORTER H，NIKLAS K J，REICH P B，et al.Biomass allocation to leaves，stems and roots：meta-analyses of interspecific variation and environmental control［J］.New phytologist，2012，193（1）：30-50

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

高湿高脂废弃物产富氢水热油过程的智能建模与响应行为解析

不同杀菌剂对百合炭腐病菌的毒力和防效评价

芥菜自交系重要农艺性状的遗传多样性分析

大黄素对重组毒株rPRRSV-DV-EGFP的抑制作用研究

沼液源绿色氨水回收及其CO2吸收特性