Research on County‑Level Yield Simulation of Winter Wheat in Henan Province Based on Machine Learning Algorithms

doi:10.15933/j.cnki.1004-3268.2025.08.017

Abstract

Abstract: Henan is a major province for winter wheat cultivation，and simulating winter wheat yield is of great significance for ensuring national food security. This study analyzed the performance of machine learning models in winter wheat yield simulation using ten‑day scale meteorological data and county‑level winter wheat yield data from 16 counties（cities）in Henan Province from 2000 to 2019.The dataset was divided into a test set（2000—2015） and a training set（2016—2019）.Based on multiple stepwise regression，random forest，and random forest OOB methods，county‑level yield simulation models for winter wheat in Henan Province were constructed，and the simulation effects of different models were verified and compared. The results showed that，from 2000 to 2019，the winter wheat yield in Henan Province fluctuated between 2 001 and 7 980 kg/ha，with an average of 5 675 kg/ha and a coefficient of variation ranging from 3.75% to 26.58%.A multiple stepwise regression model was constructed based on 19 ten‑day scale meteorological factors that passed the 95% significance test.The multiple stepwise regression model was validated with a determination coefficient（R²）of 0.620 9 and a root mean square error（RMSE）of 907.06 kg/ha；The random forest model constructed using all the characteristic factors was validated with the R² of 0.772 5，and the RMSE of 664.36 kg/ha.A total of 68 key ten‑day scale meteorological characteristic factors were screened based on random forest OOB importance analysis，among which，the ten‑day scale meteorological factors in November last year，March，April and June had particularly significant impacts on winter wheat yield.The validation determination coefficient of the random forest OOB model for simulating county‑level winter wheat yield was 0.860 5，and the RMSE was 636.58 kg/ha.The random forest OOB model performed better than the multiple stepwise regression model and the random forest model，with R²increased by 38.59% and 11.39%，respectively，and RMSE decreased by 29.82% and 4.18%，respectively.This study utilized limited meteorological data and county‑level yield data to achieve reliable and accurate winter wheat yield simulation，providing a methodological reference for regional winter wheat yield simulation.

Key words: Winter wheat, Yield prediction, Random forest, Meteorological factors, OOB analysis, Ten?day scale

摘要： 河南省是冬小麦种植大省，精准评估冬小麦产量对保障国家粮食安全意义重大。基于2000—2019年河南省16个县（市）的旬尺度气象数据与河南省县级冬小麦产量数据，分析机器学习模型在冬小麦产量模拟中的性能。将数据集分为测试集（2000—2015年）与训练集（2016—2019年），基于多元逐步回归、随机森林和随机森林OOB方法，构建河南省县级冬小麦产量模拟模型，并对比验证不同模型模拟效果。结果表明，2000—2019年河南省县级冬小麦产量在2 001~7 980 kg/hm²波动，平均值为5 675 kg/hm²，变异系数区间为3.75%~26.58%。基于通过95%显著性检验的19个旬尺度气象因子构建多元逐步回归模型，验证R² 为0.620 9，RMSE为907.06 kg/hm²；使用全部特征因子构建的随机森林模型验证R² 为0.772 5，RMSE 为664.36 kg/hm²。基于随机森林OOB重要性分析，共筛选68个关键旬尺度气象特征因子，其中，11月、3月、4月、6月的旬尺度气象因子对冬小麦产量的影响尤为显著。随机森林OOB模型模拟县级冬小麦产量的验证R²为0.860 5，RMSE为636.58 kg/hm²。随机森林OOB模型表现优于多元逐步回归模型与随机森林模型，R²分别提高38.59%和11.39%，RMSE分别降低29.82%和4.18%。利用有限的气象数据和县尺度产量数据，实现了可靠且较高精度的冬小麦产量模拟，为区域冬小麦产量模拟提供了方法参考。

关键词: 冬小麦, 产量模拟, 随机森林, 气象因子, OOB分析, 旬尺度

CLC Number:

S126

LIU Xinglin, LIU Yuan, YANG Fan, LIU Buchun, HAN Rui. Research on County‑Level Yield Simulation of Winter Wheat in Henan Province Based on Machine Learning Algorithms[J]. Journal of Henan Agricultural Sciences, 2025, 54(8): 167-180.

刘星麟, 刘园, 杨凡, 刘布春, 韩锐. 基于机器学习算法的河南省县级冬小麦产量模拟研究[J]. 河南农业科学, 2025, 54(8): 167-180.

Figures/Tables 12

References

［1］刘璐，周亚兰，孟婷.“十五五”粮食安全视域下中国粮食产需匹配度研究［J］. 农林经济管理学报，2024，23（5）：545‑557.
LIU L，ZHOU Y L，MENG T. Research on the matching degree between grain production and demand in China from the perspective of food security during the“15th Five‑Year Plan” period［J］. Journal of Agro‑Forestry Economics and Management，2024，23（5）：545‑557.

［2］FRANCH B，VERMOTE E，SKAKUN S，et al. The ARYA crop yield forecasting algorithm：Application to the main wheat exporting countries［J］. International Journal of Applied Earth Observation and Geoinformation，2021，104：102552.

［3］周丽涛，孙爽，郭尔静，等. 干旱条件下APSIM模型修正及华北冬小麦产量模拟效果［J］. 农业工程学报，2023，39（6）：92‑102.

ZHOU L T，SUN S，GUO E J，et al. APSIM modified model under drought conditions to simulate winter wheat yield in North China［J］. Transactions of the Chinese Society of Agricultural Engineering，2023，39（6）：92‑102.

［4］武洪涛，郭佳伟，郑朋涛. 河南省冬小麦产量的干旱脆弱性研究［J］. 地域研究与开发，2018，37（5）：170‑175.

WU H T，GUO J W，ZHENG P T. Drought vulnerability of winter wheat in Henan Province［J］.Areal Research and Development，2018，37（5）：170‑175.

［5］XU X Y，GAO P，ZHU X K，et al. Design of an integrated climatic assessment indicator（ICAI）for wheat production：A case study in Jiangsu Province，China［J］.Ecological Indicators，2019，101：943‑953.

［6］李炳军，王天慧. 冬小麦不同生长阶段气象因素对产量影响的双重量化分析［J］. 麦类作物学报，2018，38（4）：487‑492.
LI B J，WANG T H. Double quantification analysis of the effect of meteorological factors on yield in winter wheat at different growth stages［J］.Journal of Triticeae Crops，2018，38（4）：487‑492.

［7］LESK C，ROWHANI P，RAMANKUTTY N. Influence of extreme weather disasters on global crop production［J］.Nature，2016，529（7584）：84‑87.

［8］BECKER‑RESHEF I，JUSTICE C，BARKER B，et al.Strengthening agricultural decisions in countries at risk of food insecurity：The GEOGLAM Crop Monitor for Early Warning［J］. Remote Sensing of Environment，2020，237：111553.

［9］EINI M R，SALMANI H，PINIEWSKI M. Comparison of process‑based and statistical approaches for simulation and projections of rainfed crop yields［J］.Agricultural Water Management，2023，277：108107.

［10］张雪芬，毛留喜，陈怀亮. 河南省夏玉米农学模式产量预报［J］.河南气象，1996，19（2）：22‑23.
ZHANG X F，MAO L X，CHEN H L. Yield forecast of summer maize agronomic model in Henan Province［J］.Meteorology Journal of Henan，1996，19（2）：22‑23.

［11］郑秀琴，冯利平，刘荣花. 冬小麦产量形成模拟模型研究［J］.作物学报，2006，32（2）：260‑266.
ZHENG X Q，FENG L P，LIU R H. A simulation model for yield components and final yield in winter wheat［J］. Acta Agronomica Sinica，2006，32（2）：260‑266.

［12］马战林，文枫，周颖杰，等. 基于作物生长模型与机器学习算法的区域冬小麦估产［J］. 农业机械学报，2023，54（6）：136‑147.
MA Z L，WEN F，ZHOU Y J，et al. Regional winter‑wheat yield estimation based on coupling of machine learning algorithm and crop growth model［J］.Transactions of the Chinese Society for Agricultural Machinery，2023，54（6）：136‑147.

［13］李菲菲，汤军，高贤君，等. 基于GEE的气候变化对豫北地区冬小麦播种面积与产量影响研究［J］.河南农业科学，2022，51（8）：150‑165.
LI F F，TANG J，GAO X J，et al. Analysis of climate change effects on winter wheat sowing area and yield in northern Henan based on GEE［J］. Journal of Henan Agricultural Sciences，2022，51（8）：150‑165.

［14］张德权，杜崇，庞超，等. 遥感和作物模型技术耦合现状和发展趋势［J］.农业与技术，2022，42（11）：53‑57.
ZHANG D Q，DU C，PANG C，et al. Status and trends in the coupling of remote sensing and crop modelling techniques［J］. Agriculture and Technology，2022，42 （11）：53‑57.

［15］李炳军，张一帆. 不同生育期气候变化对河南省冬小麦产量影响的量化分析［J］.江苏农业科学，2022，50（12）：238‑246.
LI B J，ZHANG Y F. Quantitative analysis of impact of climate change at different growth stages on winter wheat yield in Henan Province［J］.Jiangsu Agricultural Sciences，2022，50（12）：238‑246.

［16］王来刚，郑国清，郭燕，等.融合多源时空数据的冬小麦产量预测模型研究［J］.农业机械学报，2022，53（1）：198‑204.
WANG L G，ZHENG G Q，GUO Y，et al. prediction of winter wheat yield based on Fusing Multi‑source Spatio‑temporal Data［J］. Transactions of the Chinese Society for Agricultural Machinery，2022，53（1）：198‑204.

［17］娄正方，李国清，张向军，等. 一种顾及多参数的冬小麦遥感估产方法与应用［J］. 测绘通报，2021（S1）：154‑158.
LOU Z F，LI G Q，ZHANG X J，et al. A method of winter wheat yield estimation by considering multiple parameters and its application［J］. Bulletin of Surveying and Mapping，2021（S1）：154‑158.

［18］MITCHELL P J，WALDNER F，HORAN H，et al. Data fusion using climatology and seasonal climate forecasts improves estimates of Australian national wheat yields［J］.Agricultural and Forest Meteorology，2022，320：108932.

［19］KHAKI S，WANG L Z. Crop yield prediction using deep neural networks［J］.Frontiers in Plant Science，2019，10：621.

［20］SAJID S S，SHAHHOSSEINI M，HUBER I，et al.County‑scale crop yield prediction by integrating crop simulation with machine learning models［J］.Frontiers in Plant Science，2022，13：1000224.

［21］YANG S R，LI L，FEI S P，et al. Wheat yield prediction using machine learning method based on UAV remote sensing data［J］.Drones，2024，8（7）：284.

［22］EVERINGHAM Y，SEXTON J，SKOCAJ D，et al.Accurate prediction of sugarcane yield using a random forest algorithm ［J］. Agronomy for Sustainable Development，2016，36（2）：27.

［23］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 Chinese Society of Agricultural Engineering，2019，35（6）：158‑166.

［24］林滢，邵怀勇. 基于随机森林算法的河南省冬小麦产量预测最佳时间窗和影响因子研究［J］.麦类作物学报，2020，40（7）：874‑880.
LIN Y，SHAO H Y. Study on optimal time and influencing factors for winter wheat yield prediction in Henan based on random forest algorithm［J］. Journal of Triticeae Crops，2020，40（7）：874‑880.

［25］CRANE‑DROESCH A. Machine learning methods for crop yield prediction and climate change impact assessment in agriculture［J］. Environmental Research Letters，2018，13（11）：114003.

［26］李彤霄. 气候变化对河南省冬小麦生育影响的研究［D］.郑州：河南农业大学，2010.

LI T X. Research on the impact of climate change on winter wheat fertility in Henan Province［D］.Zhengzhou：Henan Agricultural University，2010.

［27］BREIMAN L. Random forests［J］. Machine Learning，2001，45（1）：5‑32.

［28］HOFFMAN A L，KEMANIAN A R，FOREST C E.Analysis of climate signals in the crop yield record of sub‑Saharan Africa［J］. Global Change Biology，2018，24（1）：143‑157.

［29］SHEN J X，HUETE A，TRAN N N，et al. Diverse sensitivity of winter crops over the growing season to climate and land surface temperature across the rainfed cropland‑belt of eastern Australia［J］.Agriculture，Ecosystems &Environment，2018，254：99‑110.

［30］ABDEL‑RAHMAN E M，AHMED F B，ISMAIL R.Random forest regression and spectral band selection for estimating sugarcane leaf nitrogen concentration using EO‑1 Hyperion hyperspectral data［J］.International Journal of Remote Sensing，2013，34（2）：712‑728.

［31］殷美祥，罗瑞婷，朱平，等. 基于两种数据集构建广东县级尺度龙眼产量模型效果对比［J］.中国农业气象，2023，44（6）：502‑512.
YIN M X，LUO R T，ZHU P，et al. Effect comparison of county‑scale model of Longan yield in Guangdong based on two datasets［J］. Chinese Journal of Agrometeorology，2023，44（6）：502‑512.

［32］张明捷，王运行，赵桂芳，等. 濮阳冬小麦生育期气候变化及其对小麦产量的影响［J］. 中国农业气象，2009，30（2）：223‑229.
ZHANG M J，WANG Y H，ZHAO G F，et al. Climate change during winter wheat growing period and its impacts on wheat yield in Puyang of Henan Province［J］.Chinese Journal of Agrometeorology，2009，30（2）：223‑229.

［33］刘峻明，周舟，和晓彤，等. 频率直方图与植被指数结合的冬小麦遥感产量估测［J］.农业工程学报，2021，37（23）：145‑152.
LIU J M，ZHOU Z，HE X T，et al. Estimating winter wheat yield under frequency histogram and vegetation index using remote sensing［J］.Transactions of the Chinese Society of Agricultural Engineering，2021，37 （23）：145‑152.

［34］谭凯炎，杨晓光，任三学，等. 高温胁迫对华北地区冬小麦灌浆及产量的影响［J］.生态学报，2015，35（19）：6355‑6361.
TAN K Y，YANG X G，REN S X，et al. Impact of high temperature stress at the grain‑filling stage on winter wheat yield［J］. Acta Ecologica Sinica，2015，35（19）：6355‑6361.

［35］肖登攀，陶福禄，沈彦俊，等. 华北平原冬小麦对过去30年气候变化响应的敏感性研究［J］.中国生态农业学报，2014，22（4）：430‑438.
XIAO D P，TAO F L，SHEN Y J，et al. Sensitivity of response of winter wheat to climate change in the North China Plain in the last three decades［J］.Chinese Journal of Eco‑Agriculture，2014，22（4）：430‑438.

［36］吴冰洁，王靖，唐建昭，等. 华北平原冬小麦产量变异的气象影响因子分析［J］.中国农业气象，2018，39（10）：623‑635.
WU B J，WANG J，TANG J Z，et al. Meteorological influencing factors on variation in winter wheat yield in the North China Plain［J］.Chinese Journal of Agrometeorology，2018，39（10）：623‑635.

［37］GISLASON P O，BENEDIKTSSON J A，SVEINSSON J R. Random forests for land cover classification［J］.Pattern Recognition Letters，2006，27（4）：294‑300.

［38］SIDHU B S，MEHRABI Z，RAMANKUTTY N，et al.How can machine learning help in understanding the impact of climate change on crop yields？［J］.Environmental Research Letters，2023，18（2）：024008.

［39］LI L C，ZHANG Y，WANG B，et al. Integrating machine learning and environmental variables to constrain uncertainty in crop yield change projections under climate change［J］. European Journal of Agronomy，2023，149：126917.

［40］BAI H Z，XIAO D P，TANG J Z，et al. Evaluation of wheat yield in North China Plain under extreme climate by coupling crop model with machine learning［J］. Computers and Electronics in Agriculture，2024，217：108651.

［41］ZHUANG H M，ZHANG Z，CHENG F，et al. Integrating data assimilation，crop model，and machine learning for winter wheat yield forecasting in the North China Plain［J］.Agricultural and Forest Meteorology，2024，347：109909.

[1]	MA Shangying, XIA Tingting, HAN Pengbin, ZHANG Mengjiao, MAO Yingjie, WANG Zhiqiang, XIN Zeyu, LIN Tongbao, LIAN Yanhao, REN Yongzhe. Effects of Application Rate and Method of Nitrogen on Winter Wheat Nitrogen Uptake and Utilization，Yield and Soil Nitrate Nitrogen Residue under Wide‑Narrow Row Planting [J]. Journal of Henan Agricultural Sciences, 2025, 54(8): 38-50.
[2]	WANG Haiyang, JIN Haiyang, SONG Hang, PAN Xiuyan, YAN Yaqian, YANG Xiwen, ZENG Zhaohai, ZANG Huadong, ZHENG Nian, LI Xiangdong, HE Dexian. Effects of Different Preceding Crops on Dry Matter Accumulation and Transportation，Nitrogen Absorption and Utilization and Yield of Winter Wheat [J]. Journal of Henan Agricultural Sciences, 2025, 54(6): 1-10.
[3]	WANG Yingying, DUAN Liangxia, ZHAO Yining, SUN Guangrui, YANG Lihong, ZHOU Qing, XIE Hongxia. Identification of Rice in Southern Mountainous Area Based on Object‐Oriented and Machine Learning Methods [J]. Journal of Henan Agricultural Sciences, 2025, 54(4): 144-154.
[4]	ZHAO Lishang 1, YANG Tiancong 2, ZHANG Xiaomei2, SONG Quanhao 1, MA Zhiyao 2, FENG Wei 2, DUAN Jianzhao2. Effects of Tillage and Straw Returning Methods on Yield and N₂O Emission of Winter Wheat [J]. Journal of Henan Agricultural Sciences, 2025, 54(4): 27-36.
[5]	HAN Ruifeng, REN Rongkui, DONG Xiangyang, HU Zebin, GUO Fangjun, FANG Tiantian, MA Wenhao, ZHANG Shuhong. Effects of Application Depth and Amount of Different Types of Fertilizers on Growth and Development of Winter Wheat [J]. Journal of Henan Agricultural Sciences, 2025, 54(2): 30-39.
[6]	GUO Hui, LIAN Yanhao, ZHAO Zhibo, REN Yongzhe, WANG Zhiqiang, LIN Tongbao. Effects of Soybean and Maize Stubbles on Bacterial Community Structure and Function in Winter Wheat Rhizosphere Soil [J]. Journal of Henan Agricultural Sciences, 2024, 53(7): 79-89.
[7]	HAO Yonghui, JIN Haiyang, YAN Yaqian, LI Xiangdong, ZHENG Fei, YUE Junqin, ZHANG Deqi, FANG Baoting, YANG Cheng, CHENG Hongjian, LI Chunxi. Effects of Nitrogen Topdressing Rates on Yield and Nitrogen Uptake and Utilization of Winter Wheat under Long⁃Term Straw Returning [J]. Journal of Henan Agricultural Sciences, 2024, 53(4): 9-19.
[8]	XU Chunyan, ZHANG Qian, WANG Yaxian, WANG Hongyu, SHENG Kai, WANG Yilun. Effects of Commercial Organic Fertilizers on Physical and Chemical Properties of Sandy Fluvo⁃Aquic Soil，Yield and Nutrient#br# Accumulation of Winter Wheat [J]. Journal of Henan Agricultural Sciences, 2024, 53(2): 56-64.
[9]	LIU Linye, WANG Zhuangzhuang, GU Fengxu, DUAN Jianzhao, WANG Yonghua. Effects of Seeding Methods on Population Photosynthetic Characteristics，Nitrogen Accumulation and Transport and Yield of Winter Wheat [J]. Journal of Henan Agricultural Sciences, 2024, 53(10): 28-36.
[10]	LIAN Yanhao, DU Feibo, XUE Bo, WANG Zhiqiang, REN Yongzhe, LIN Tongbao, LI Sen. Effect of Bed Planting Combined with One‑time Nitrogen Fertilizer Application on Nitrogen Utilization and Economic Benefit of Winter Wheat（Triticum aestivum L.） [J]. Journal of Henan Agricultural Sciences, 2023, 52(9): 56-65.
[11]	FU Bo, YANG Yongfeng, LIU Xiangzhen, ZHAO Sensen, LIU Maolin, JIA Guotao, NIU Yangyang, ZHANG Kunfang, YU Jianjun, PENG Guixin, JI Xiaoming. Study on Aroma Type Classification Model Based on Near Infrared Spectra of Flue⁃cured Tobacco [J]. Journal of Henan Agricultural Sciences, 2023, 52(7): 163-171.
[12]	ZHANG Keqian, CHENG Gang, WU Wei, SONG Xiangyang, ZHANG Ziqian, YAO Shun, WU Shuai. Extraction of Winter Wheat Planting Area Based on Fused Active and Passive Remote Sensing Images [J]. Journal of Henan Agricultural Sciences, 2023, 52(6): 160-171.
[13]	RONG Yasi, LI Guoqiang, ZHANG Jie, ZHANG Jiantao, WANG Meng, ZHENG Guoqing, FENG Wei. Irrigation Strategies Optimization for Winter Wheat in Henan Province Based on AquaCrop Model [J]. Journal of Henan Agricultural Sciences, 2023, 52(2): 151-161.
[14]	GUO Yan, JING Yuhang, HE Jia, ZHANG Huifang, JIA Dewei, WANG Laigang. Winter Wheat Aboveground Biomass and Yield Estimation Based on Multi‐Source Information from UAV Imagery [J]. Journal of Henan Agricultural Sciences, 2023, 52(12): 149-161.
[15]	LI Feifei, TANG Jun, GAO Xianjun, YANG Yuanwei, ZHAN Yangying. Analysis of Climate Change Effects on Winter Wheat Sowing Area and Yield in Northern Henan Based on GEE [J]. Journal of Henan Agricultural Sciences, 2022, 51(8): 150-165.