基于GA-BP神经网络的鲜食玉米产量预测

doi:10.13733/j.jcam.issn.2095-5553.2024.06.024

摘要/Abstract

摘要：

鲜食玉米因其营养丰富、用途广泛、市场潜力大等优势而备受关注，目前，我国鲜食玉米种植面积逐渐扩大，鲜食玉米产量的高效预测对制定其生长期间的精准管理决策具有重要意义。针对传统BP神经网络在预测中存在测试精度低、鲁棒性差等问题，利用遗传算法(Genetic Algorithm，GA)对BP神经网络模型进行优化，构建GABP神经网络模型。基于2010—2021年间田间物联网获取的气象因子(大气湿度、大气温度、降雨量)、田间水热因子及鲜食玉米实际产量，分别采用BP神经网络、GABP神经网络模型及粒子群优化算法(Particle Swarm Optimization，PSO)优化BP神经网络(PSOBP)对所选地区鲜食玉米产量进行预测与相关性分析。结果表明，鲜食玉米产量与月最低土壤温度、月平均土壤温度、月大气最高温度和月平均大气湿度相关性极显著，相关系数高于0.8，与月最高温度、月土壤平均含水率、月大气平均温度、月降雨量相关性显著，与月大气最低温度相关性较弱。GABP神经网络模型精度明显高于PSOBP及BP神经网络模型，R2达到0.956 4。因此，通过GABP神经网络模型可以更科学、合理地对鲜食玉米的产量进行预测，从而对鲜食玉米生产及管理措施的调整具有重要的指导意义。

关键词: 鲜食玉米, 产量预测, 神经网络, 遗传算法, 全局寻优, 粒子群优化算法

Abstract:

Fresh corn has attracted much attention because of its advantages such as rich nutrition, wide use and large market potential. At present, the fresh corn planting area in China is gradually expanding, and the efficient prediction of fresh corn yield is of great significance to make accurate management decisions during its growth period. Aiming at the problems of low testing accuracy and poor robustness of traditional BP neural network in yield prediction, the BP neural network model is optimized by using Genetic Algorithm (GA) and the GABP neural network model is constructed. In this study, based on meteorological factors (atmospheric humidity, atmospheric temperature, rainfall), field water and heat factors and fresh maize yield obtained from field IOTs during 2010—2021 at the South Asia Institute of Tropical Crops in Guangdong Province, BP neural network, GABP neural network model and PSO (particle swarm optimization algorithm) were used to predict and correlate the fresh maize yield in the selected areas. The results showed that the fresh maize yield was significantly correlated with monthly minimum soil temperature, monthly average soil temperature, monthly maximum atmospheric temperature and monthly average atmospheric humidity. and the correlation coefficients was higher than 0.8, and the correlation coefficient was significantly correlated with monthly maximum temperature, monthly average soil water content, monthly average atmospheric temperature and monthly rainfall, and the correlation was weak with monthly minimum atmospheric temperature, as shown by Pearson correlation coefficients. The accuracy of the GABP neural network model was significantly higher than that of the PSOBP and BP neural network models, with R2 reaching 0.956 4 and a high degree of fit between the predicted and experimental values. Therefore, the GABP neural network model can be used to predict the yield of fresh corn more scientifically and rationally, which is an important guidance for the adjustment of fresh maize production and management measures.

Key words: fresh maize, yield prediction, neural network, genetic algorithm, global optimization search, particle swarm optimization algorithm

中图分类号:

S513

王宏轩, 于珍珍, 李海亮, 汪春, 严晓丽, 邹华芬. 基于GA-BP神经网络的鲜食玉米产量预测[J]. 中国农机化学报, 2024, 45(6): 156-162.

Wang Hongxuan, Yu Zhenzhen, Li Hailiang, Wang Chun, Yan Xiaoli, Zou Huafen. Fresh corn yield prediction based on GA-BP neural network[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(6): 156-162.

参考文献

［1］　王闵. 鄢陵县鲜食玉米产业发展现状和对策研究［D］. 武汉: 武汉轻工大学, 2021.

Wang Min. Research on the development status and countermeasures of fresh corn industry in Yanling County ［D］. Wuhan: Wuhan Polytechnic University, 2021.

［2］　曹艺腾, 王艳华. 基于DEMATELISM模型的鲜食玉米产业发展制约因素分析［J］. 玉米科学, 2022, 30(1): 182-190.

Cao Yiteng, Wang Yanhua. Analysis of restricting factors of fresh corn industry development based on DEMATELISM method ［J］. Journal of Maize Sciences, 2022, 30(1): 182-190.

［3］　韩学伟. 种植结构调整背景下河北省鲜食玉米种植经济效益研究［D］. 保定: 河北农业大学, 2020.

Han Xuewei. Study on the economic efficiency of fresh maize cultivation in Hebei Province under the background of planting structure adjustment ［D］. Baoding: Hebei Agricultural University, 2020.

［4］　范荣尚, 康琪. 罗甸县鲜食玉米产量与主要农艺性状的灰色关联度分析［J］. 现代农业科技, 2021(22): 4-6.

［5］　刘萍. 中国鲜食甜、糯玉米品种试验产量与品质评价体系的建设［D］. 扬州: 扬州大学, 2007.

Liu Ping. Construction of a yield and quality evaluation system for fresh sweet and glutinous maize variety trials in China ［D］. Yangzhou: Yangzhou University, 2017.

［6］　Maimaitijiang M, Sagan V, Sidike P, et al. Vegetation index weighted canopy volume model (CVM VI) for soybean biomass estimation from unmanned aerial systembased RGB imagery ［J］. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 151: 27-41.

［7］　Juliane B, Andreas B, Simon B, et al. Estimating biomass of barley using crop surface models (CSMs) derived from UAV-based RGB imaging ［J］. Remote Sensing, 2014, 6(11): 10395-10412.

［8］　戴冕, 杨天乐, 姚照胜, 等. 基于无人机图像颜色与纹理特征的小麦不同生育时期生物量估算［J］. 智慧农业(中英文), 2022, 4(1): 71-83.

Dai Mian, Yang Tianle, Yao Zhaosheng, et al. Wheat biomass estimation in different growth stages based on color and texture features of UAV images ［J］. Smart Agriculture, 2022, 4(1): 71-83.

［9］　Mavromatis T. Preseason prediction of regional rainfed wheat yield in northern Greece with CERESwheat ［J］. Theoretical & Applied Climatology, 2014, 117(3-4): 653-665.

［10］　Sharabian V R, Noguchi N, Ishi K. Significant wavelengths for prediction of winter wheat growth status and grain yield using multivariate analysis ［J］. Engineering Agricultural, Environment Food, 2014, 7(1): 14-21.

［11］　Anwar M R, Liu D L, Farquharson R, et al. Climate change impacts on phenology and yields of five broadacre crops at four climatologically distinct locations in Australia ［J］. Agricultural Systems, 2015, 132: 133-144.

［12］　Kumar M. Impact of climate change on crop yield and role of model for achieving food security ［J］. Environmental Monitoring and Assessment, 2016, 188(8): 465

［13］　衡亚蓉, 李晓, 贺利, 等. 基于上部叶片叶绿素荧光参数的小麦产量预测与评价［J］. 麦类作物学报, 2018, 38(6): 701-709.

Heng Yarong, Li Xiao, He Li, et al.Prediction and evaluation of yield using Chlorophyll Fluorescence parameters of the upper leaves in wheat ［J］. Journal of Triticeae Crops, 2018, 38(6): 701-709.

［14］　田苗, 王鹏新, 张树誉, 等. 基于条件植被温度指数的冬小麦产量预测［J］. 农业机械学报, 2014, 45(2): 239-245.

Tian Miao, Wang Pengxin, Zhang Shuyu, et al. Winter wheat yield forecasting based on vegetation temperature condition index ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(2): 239-245.

［15］　陈上, 窦子荷, 蒋腾聪, 等. 基于聚类法筛选历史相似气象数据的玉米产量DSSATCERESMaize预测［J］. 农业工程学报, 2017, 33(19): 147-155.

Chen Shang, Dou Zihe, Jiang Tengcong, et al. Maize yield forecast with DSSATCERESMaize model driven by historical meteorological data of analogue years by clustering algorithm ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(19): 147-155.

［16］　曾妍, 王迪, 赵小娟. 基于支持向量回归的关中平原冬小麦估产研究［J］. 中国农业信息, 2019, 31(6): 10-20.

Zeng Yan, Wang Di, Zhao Xiaojuan, et al. Study on yield prediction of winter wheat in Guanzhong Plain based on SVR ［J］. China Agricultural Informatics, 2019, 31(6): 10-20.

［17］　李毅念, 杜世伟, 姚敏, 等. 基于小麦群体图像的田间麦穗计数及产量预测方法［J］. 农业工程学报, 2018, 34(21): 185-194.

Li Yinian, Du Shiwei, Yao Min, et al. Method for wheatear counting and yield prediction based on image of wheatear population in field ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(21): 185-194.

［18］　宗宸生, 郑焕霞, 王林山. 改进粒子群优化BP神经网络粮食产量预测模型［J］. 计算机系统应用, 2018, 27(12): 204-209.

Zong Chensheng, Zheng Huanxia, Wang Linshan. Grain yield prediction based on BP neural network optimized by improved particle swarm optimization ［J］. Computer Systems & Applications, 2018, 27(12): 204-209.

［19］　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 Junming, He Xiaotong, Wang Pengxin, 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.

［20］　徐敏, 束美艳, 陈向阳, 等. 基于高光谱数据的玉米叶面积指数和生物量评估［J］. 智慧农业(中英文), 2021, 3(1): 29-39.

Xu Min, Shu Meiyan, Chen Xiangyang. Estimation of maize leaf area index and aboveground biomass based on hyperspectral data ［J］. Smart Agriculture, 2021, 3(1): 29-39.

［21］　马梓臻. 基于遥感与WOFOST模型耦合的大庆市玉米产量预测研究［D］. 哈尔滨: 黑龙江大学, 2021.

Ma Zizhen. Research on maize yield prediction in Daqing City based on coupling remote sensing and WOFOST model ［D］.Harbin: Heilongjiang University, 2021.

［22］　刘金宇, 王兴环, 刘洋宸, 等. 气象因子对宝清县大豆和玉米产量的影响及预测［J］. 农业灾害研究, 2022, 12(2): 107-109.

［23］　何修君. 基于机器学习的玉米产量预测模型研究［D］. 长春: 吉林农业大学, 2021.

He Xiujun. Research on maize yield prediction model based on machine learning ［D］. Changchun: Jilin Agricultural University, 2021.

［24］　谭先明, 张佳伟, 王仲林, 等. 基于PLS的不同水氮条件下带状套作玉米产量预测［J］. 中国农业科学, 2022, 55(6): 1127-1138.

Tan Xianming, Zhang Jiawei, Wang Zhonglin, et al.Prediction of maize yield in relay strip intercropping under different water and nitrogen conditions based on PLS ［J］. Scientia Agricultura Sinica, 2022, 55(6): 1127-1138.

［25］　胡业红, 何梦, 周参军, 等. 基于GABP神经网络的毫秒延时爆破振动速度预测研究［J］. 中国矿业, 2022, 31(2): 72-77.Hu Yehong, He Meng, Zhou Senjun, et al. Study on vibration velocity prediction of millisecond delayed blasting based on GABP neural network ［J］. China Mining Magazine, 2022, 31(2): 72-77.

[1]	黄亦其, 鹿林飞, 沈豪, 王福宽, 乔曦, . 基于卷积神经网络的入侵昆虫识别研究[J]. 中国农机化学报, 2024, 45(7): 222-227.
[2]	张延军, 赵建鑫, . 基于多路神经网络的黄花菜关节点检测算法研究[J]. 中国农机化学报, 2024, 45(7): 228-234.
[3]	邹宇航, 王明飞, 张馨, 王利春, 魏晓明, 郑文刚. 基于模型预测控制的工厂化菇房空调调控方法[J]. 中国农机化学报, 2024, 45(6): 98-105.
[4]	陈晓玲, 张聪, 黄晓宇. 基于Bayesian-LightGBM模型的粮食产量预测研究[J]. 中国农机化学报, 2024, 45(6): 163-169.
[5]	张国渊, 王豪, 李栋, 廉佳汝, 闫超. 四自由度串联嫁接机器人架构约束模块识别可视化方法[J]. 中国农机化学报, 2024, 45(6): 191-200.
[6]	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.
[7]	毛恩荣, 王皓洁, 杜岳峰, 朱忠祥, 翟志强, 张丽榕. 大功率拖拉机多工况换挡自适应控制策略[J]. 中国农机化学报, 2024, 45(5): 122-127.
[8]	薛霞, 刘鹏, 周文. 基于改进YOLOv8算法的实时细粒度植物病害检测[J]. 中国农机化学报, 2024, 45(5): 188-194.
[9]	郭宏杰, 马睿, 王佳, 赵威, 马德新. 基于卷积神经网络的苹果叶部病害图像识别研究[J]. 中国农机化学报, 2024, 45(5): 239-245.
[10]	林燕翔, 沈印, 李光林. 基于改进InceptionV3算法的小麦杂质识别研究[J]. 中国农机化学报, 2024, 45(4): 108-116.
[11]	张慧蒙, 何超, 徐嘉雯, 罗鑫, 荣剑, 刘学渊. 基于SCGYOLOv5n的收获期澳洲坚果检测算法[J]. 中国农机化学报, 2024, 45(4): 214-221.
[12]	纪元浩, 许金普, 严蓓蓓, 薛俊龙. 基于改进ResNet50模型的咖啡生豆质量和缺陷检测方法[J]. 中国农机化学报, 2024, 45(4): 237-243.
[13]	徐静, , 朱玉, 戴盼倩, , 姚冠新, . 生鲜农产品冷链物流过程优化研究[J]. 中国农机化学报, 2024, 45(2): 115-121.
[14]	田丁伊, , 石洪康, , 祝诗平, , 陈肖, 张剑飞. 基于改进残差神经网络的家蚕日龄识别模型[J]. 中国农机化学报, 2024, 45(2): 259-266.
[15]	王吉权, 宋丽, 宋豪豪, 张攀利, 王福林. 基于改进实数遗传算法的桑叶采摘机结构参数优化[J]. 中国农机化学报, 2024, 45(1): 14-20.