To develop an accurate prediction model for maize ear weight, and provide a certain level of decision support for high-yield maize breeding and precision field management, in this study, 32 phenotypic(agronomic) traits-covering four categories(flowering time, plant morphology, ear-leaf traits, and ear characteristics)-were measured across 281 maize recombinant inbred lines. Multiple linear regression(MLR), random forest(RF), support vector machine(SVM), and artificial neural networks(ANN) were employed to construct a prediction model for maize ear weight. Models were optimized through hyper-parameter tuning under different training–testing splits and evaluated for their performance. An ensemble-mean model was subsequently generated to integrate the individual predictions, which was also applied for analyzing the key contributing factors in maize ear-weight predictions. The results showed that model performance varied after hyper-parameter tuning: RF and SVM remained robust between training and test sets, whereas ANN relied on sample size, which was prone to over-fitting at smaller training sizes(50%-70%) but showed markedly reduced errors at an 80% of training fraction. Although MLR generally achieved lower goodness-of-fit than the non-linear models, it still delivered reasonable predictive power. Across all splits, the ensemble-mean model outperformed or matched the best single model. With an 80% training fraction, the ensemble-mean model based on ear traits-where grain weight was the dominant contributing factor-achieved the best performance(R²=0.95; RMSE=7.6 g; Relative RMSE=5%). Models constructed from plant morphology traits(e.g., plant height, tassel length, ear height) showed moderate accuracy(R² is about 0.34), but could support early-stage prediction of ear weight. Models relying solely on flowering or ear-leaf traits had limited predictive ability(R²≤0.11).
MENGZ Y, WANGY H, GUOD,et al. Effects of different planting densities on yield and agronomic traits of summer maize[J]. Journal of Shanxi Agricultural Sciences,2025,53(3):50-57.
LIZ, LUH R, YANGG G,et al. Spatial and temporal distribution characteristics of heat damage at flowering stage of summer maize in Henan Province[J]. Journal of Henan Agricultural Sciences,2024,53(7):10-20.
ZHANGL G, YANGY X, FANY Q,et al. Effects of different film mulching methods on yield and soil physical and chemical prop⁃ erties of dryland maize[J]. Journal of Shanxi Agricultural Sciences,2025,53(4):11-19.
WANGT X. Impacts of climate change on spring and summer maize yields of main planting zone in China in recent 30 years[D]. Yangling:Northwest A&F University,2021.
[11]
WUJ Z, ZHANGJ, GEZ M,et al. Impact of climate change on maize yield in China from 1979 to 2016[J]. Journal of Integrative Agriculture,2021,20(1):289-299.
WANGY K, LIH P, XUZ Z,et al. Effects of combined stress of high temperature and drought on photosynthetic physiology of maize[J]. Journal of Henan Agricultural Sciences,2023,52(5):17-23.
TANJ, CHENH M, HANX L,et al. Correlation and path analysis on yield and yield component traits of maize hybrid[J]. Acta Agriculturae Boreali-Sinica,2009,24(S2):155-158.
[16]
YUANY B, CAIRNSJ E, BABUR,et al. Genome-wide association mapping and genomic prediction analyses reveal the genetic architecture of grain yield and flowering time under drought and heat stress conditions in maize[J]. Frontiers in Plant Science,2019,9:1919.
HAOR X, WANGJ, WUB Y,et al. Path analysis of yield and its component traits of different spring maize varieties[J]. Heilongjiang Agricultural Sciences,2020(1):9-11.
GAOH R, ZHANGZ L L, YUEH F,et al. Estimation method of lettuce crop coefficient based on Bayesian-XGBoost[J]. Journal of Shanxi Agricultural Sciences,2022,50(10):1482-1488.
[24]
邹扬锋. 基于机器学习的中国玉米产量预测研究[D]. 南京:南京信息工程大学,2024.
[25]
ZOUY F. Research on maize yield prediction in China based on machine learning[D]. Nanjing:Nanjing University of Information Science & Technology,2024.
[26]
金佳宣. 基于数据挖掘的玉米产量预测模型的研究[D]. 长春:吉林农业大学,2020.
[27]
JINJ X. Research on the prediction model of corn yield based on data mining[D]. Changchun:Jilin Agricultural University,2020.
[28]
SHAWONS M, EMAF B, MAHIA K,et al. Crop yield prediction using machine learning:an extensive and systematic literature review[J]. Smart Agricultural Technology,2025,10:100718.
WANGP X, QIX, LIL,et al. Estimation of maize yield based on random forest regression[J]. Transactions of the Chinese Society for Agricultural Machinery,2019,50(7):237-245.
FANGH M, ZHANGS T, DINGW K. Study on forecasting the yield in maize regional test based on BP neural network[J]. Journal of Anhui Agricultural Sciences,2007,35(34):10969-10970.
[33]
GAWDIYAS, KUMARD, AHMEDB,et al. Field scale wheat yield prediction using ensemble machine learning techniques[J]. Smart Agricultural Technology,2024,9:100543.
[34]
DAS P, JHAG K, LAMAA,et al. Crop yield prediction using hybrid machine learning approach:a case study of lentil (Lens culinaris Medik.)[J]. Agriculture,2023,13(3):596.
[35]
SÁNCHEZJ C M, ACOSTA MESAH G, ESPINOSAA T,et al. Improving wheat yield prediction through variable selection using support vector regression,random forest,and extreme gradient boosting[J]. Smart Agricultural Technology,2025,10:100791.
LUOZ Y, TANGY. The prediction analysis on maize yield changes in Heilongjiang Province:empirical research based on support vector machine(SVM)[J]. Journal of Agricultural Mechanization Research,2013,35(2):30-34.
SHENZ, HANT F, QUX L,et al. Spatial-temporal variation of relative yield gap of wheat and maize and its response to nitrogen fertilizer in China[J]. Scientia Agricultura Sinica,2023,56(14):2724-2737.
[40]
姚玉霞. 中国西南地区玉米蒸散发遥感估算及其对干旱的响应[D]. 重庆:西南大学,2023.
[41]
YAOY X. Remote sensing estimation of maize evapotranspiration in southwest China and its response to drought[D]. Chongqing:Southwest University,2023.
QINX W. Research on identification of parcel-scale crop types based on time series remote sensing images[D]. Lanzhou:Lanzhou Jiatong University,2023.
[44]
MIAOL J, ZOUY F, CUIX F,et al. Predicting China's maize yield using multi-source datasets and machine learning algorithms[J]. Remote Sensing,2024,16(13):2417.
[45]
钱莹,方秀男. 多元线性回归模型及实例应用[J]. 中国科技信息,2022(4):73-74.
[46]
QIANY, FANGX N. Multivariate linear regression model and its application[J]. China Science and Technology Information,2022(4):73-74.
[47]
MATSUMURAK, GAITANC F, SUGIMOTOK,et al. Maize yield forecasting by linear regression and artificial neural networks in Jilin,China[J]. The Journal of Agricultural Science,2015,153(3):399-410.
[48]
PROBSTP, WRIGHTM N, BOULESTEIXA L. Hyperparameters and tuning strategies for random forest[J]. WIREs Data Mining and Knowledge Discovery,2019,9(3):e1301.
[49]
YANGL, SHAMIA. On hyperparameter optimization of machine learning algorithms:Theory and practice[J]. Neurocomputing,2020,415:295-316.
[50]
NEMATZADEHS, KIANIF, TORKAMANIAN-AFSHARM,et al. Tuning hyperparameters of machine learning algorithms and deep neural networks using metaheuristics:a bioinformatics study on biomedical and biological cases[J]. Computational Biology and Chemistry,2022,97:107619.
[51]
GAURIAUO, GALÁRRAGAL, BRUNF,et al. Comparing machine-learning models of different levels of complexity for crop protection:a look into the complexity-accuracy tradeoff[J]. Smart Agricultural Technology,2024,7:100380.
[52]
MORA-POBLETEF, MALDONADOC, HENRIQUEL,et al. Multi-trait and multi-environment genomic prediction for flowering traits in maize:a deep learning approach[J]. Frontiers in Plant Science,2023,14:1153040.
[53]
OLIVOTOT, NARDINOM, CARVALHOI R,et al. REML/BLUP and sequential path analysis in estimating genotypic values and interrelationships among simple maize grain yield-related traits[J]. Genetics and Molecular Research,2017,16(1):1-19.
LIQ C, MAL L, WENQ,et al. Correlation and path analysis of yield and yield characteristics of maize hybrids[J]. Chinese Agricultural Science Bulletin,2015,31(27):59-62.
WANGJ L. Phenotypic interaction network construction and genetic analysis of "source-flow-sink" traits in maize ear[D]. Wuhan:Huazhong Agricultural University,2024.
[58]
SHAOR X, YUK K, LIH W,et al. The effect of elevating temperature on the growth and development of reproductive organs and yield of summer maize[J]. Journal of Integrative Agriculture,2021,20(7):1783-1795.
[59]
WANGH Q, LIUP, ZHANGJ W,et al. Endogenous hormones inhibit differentiation of young ears in maize(Zea mays L.) under heat stress[J]. Frontiers in Plant Science,2020,11:533046.
CUNY J, ZHENGD S, WANGR. Effects of nitrogen on root characteristics and yield formationin drought-stressed maize during the flowering stage[J]. Agricultural Research in the Arid Areas,2025,43(1):139-150.
WANGH T, YUANL Z, LIUJ Y,et al. Research progress on effect of high temperature on maize at flowering stage[J]. Journal of Henan Agricultural Sciences,2022,51(9):1-9.