Grain yield prediction in southern China based on Stacking ensemble algorithm

doi:10.14088/j.cnki.issn0439-8114.2025.05.024

Abstract

Abstract: Based on the grain yield data and 11-dimensional relevant factors from Anhui, Hubei, Hunan, Jiangsu, and Sichuan provinces in southern China between 1998 and 2022,the BP-SVR-Stacking grain yield prediction model based on the Stacking ensemble algorithm was developed and comparatively analyzed with the BP neural network model and SVR model. The results indicated that the mean absolute error (MAE) and mean absolute percentage error (MAPE) of the BP-SVR-Stacking model were significantly lower than those of the BP neural network model and SVR model,which demonstrated the superior prediction capability of the BP-SVR-Stacking model over single machine learning models. Compared with the BP neural network model and SVR model, the coefficient of determination (R²) of the BP-SVR-Stacking model increased by 0.124 and 0.122 respectively,suggesting that the BP-SVR-Stacking model possessed excellent fitting capability and prediction performance.

Key words: Stacking ensemble algorithm, grain yield, southern China, prediction

CLC Number:

F326.11
S126

MA Dian-jing, ZHAO Jia-song, YAN Wei-yu, DUAN Guang-jun, LIU Zhen-yang, WU Shao-tian. Grain yield prediction in southern China based on Stacking ensemble algorithm[J]. HUBEI AGRICULTURAL SCIENCES, 2025, 64(5): 155-159.

References

[1] 刘浩然,吴克宁,宋文,等.黑龙江粮食产能及其影响因素研究[J].中国农业资源与区划,2019,40(7): 164-170.
[2] 宋洪远,江帆.基于稳产视角的粮食安全:现实基础、主要问题和对策建议[J].中国工程科学, 2024,24(5): 178-189.
[3] 蔡承智,杨春晓,莫洪兰,等.基于ARIMA模型的中国水稻单产预测分析[J].杂交水稻,2018,33(2): 62-66.
[4] 李修华,李婉,张木清,等.基于田间环境及气象数据的甘蔗产量预测方法[J].农业机械学报,2019,50(S1):233-236.
[5] 赵桂芝,赵华洋,李理,等.基于混沌-SVM-PSO的粮食产量预测方法研究[J].中国农机化学报,2019,40(1):179-183.
[6] KHAKI S,WANG L Z,ARCHONTOULIS S V.A CNN-RNN framework for crop yield prediction[J].Frontiers in plant science, 2019, 10:1750.
[7] 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.
[8] 于珍珍,邹华芬,于德水,等.融合田间水热因子的甘蔗产量GA-BP预测模型[J].农业机械学报,2022, 53(10):277-283.
[9] 郑颖颖,李鑫,陈延旭,等.基于Stacking多模型融合的极端天气短期风电功率预测方法[J].高电压技术,2024,50(9): 3871-3882.
[10] 史佳琪,张建华.基于多模型融合Stacking集成学习方式的负荷预测方法[J].中国电机工程学报,2019,39(14):4032-4042.
[11] HE Y Y, XIAO J L, AN X L, et al.Short-term power load probability density forecasting based on GLRQ-Stacking ensemble learning method[J].International journal of electrical power and energy systems,2022,142:108243.
[12] HANKGOD O,OMAIR M S.CARD-B: A stacked ensemble learning technique for classification of encrypted network traffic[J].Computer communications,2022,190:110-125.
[13] QU N, LI Z Z, LI X X, et al.Multi-parameter fire detection method based on feature extraction and stacking ensemble learning model[J].Fire safety journal,2022,128: 103541.
[14] KARTHIK R, MENAKA R, KATHIRESAN G S, et al.Gaussian dropout based stacked ensemble CNN for classification of breast tumor in ultrasound images[J].IRBM,2022,43(6):715-733.
[15] 李想,戴维,高红菊,等.基于BP神经网络的粮食产量与化肥用量相关性研究[J].农业机械学报,2017,48(S1):186-192.
[16] 曾庆扬,丁楚衡,谷战英,等.基于BP神经网络的油茶产量预测模型构建[J].经济林研究,2022,40(3): 87-95.
[17] 窦文豪,孙三民,徐鹏翔.基于Stacking集成学习的枣树智能灌溉系统设计与试验[J].中国农机化学报,2024,45(6):270-276.
[18] 张海洋,张瑶,李民赞,等.基于BSO-SVR的香蕉遥感时序估产模型研究[J].农业机械学报,2021,52(S1):98-107.
[19] 孟春阳,谢劭峰,魏朋志,等.利用AO-SVR模型预测PM_2.5浓度[J].大地测量与地球动力学,2023,43(3):269-274.
[20] 李晋泽,赵素娟,李宁,等.基于主成分分析的果蝇算法优化支持向量机回归的红枣产量预测[J].科学技术与工程,2024,24(4):1425-1432.
[21] YU J H, PAN R S, ZHAO Y M.High-dimensional, small-sample product quality prediction method based on MIC-Stacking ensemble learning[J].Applied sciences, 2022,12(1):23.
[22] WU T A, ZHANG W, JIAO X Y, et al.Evaluation of stacking and blending ensemble learning methods for estimating daily reference evapotranspiration[J].Computers and electronics in agriculture, 2021, 184: 106039.
[23] 王德营,胡威,吴通,等.基于Stacking集成学习的CANDU堆通道功率预测研究[J].核动力工程,2024,45(S1):72-77.
[24] 史佳琪. 区域综合能源系统供需预测及优化运行技术研究[D].北京:华北电力大学,2019.
[25] 姜宇,马廷淮.基于CNN-LSTM-Attention网络的河南省冬小麦产量预测[J].麦类作物学报,2024,44(10) :1352-1359.