摘要
选取贵州中东部烟叶种植区域2010-2021年47个区(县)气象和烤烟单叶重数据,分析气象要素对烤烟单叶重的影响,运用线性和非线性4种方式基于年尺度4个气象要素(四要素)和旬尺度多个气象要素(多要素)分别建立烤烟单叶重模型,并验证模型的准确性和稳定性,探究不同模型在贵州中东部区域评估单叶重的优劣。结果表明:(1)贵州中东部烟区近12a下部叶单叶重平均为5.7g,中部叶单叶重平均为9.2g,上部叶单叶重平均为10.8g,下部叶单叶重变幅小于中部叶和上部叶。(2)基于四要素建模,下部叶单叶重BP神经网络算法模型的模拟效果最优,R^(2)为0.26,RMSE为0.84g;中、上两部叶单叶重的随机森林算法模型的模拟效果最优,中部叶R^(2)为0.33,RMSE为1.08g,上部叶R^(2)为0.16,RMSE为1.59g。基于多要素建模,下、上两部叶单叶重的随机森林算法模型的模拟效果最优,下部叶R^(2)为0.22,RMSE为0.85g,上部叶R^(2)为0.16,RMSE为1.57g;中部叶单叶重的BP神经网络算法模型的模拟效果最优,R^(2)为0.18,RMSE为1.14g。(3)基于多要素的逐步回归算法在下部叶的准确率为34.86%,其他算法对同叶位的模拟准确性普遍在70%以上,多要素BP神经网络模型预测下部叶单叶重准确率最高,为86.24%,四要素随机森林模型中部叶单叶重准确率最高,为89.91%;多要素随机森林算法预测上部叶单叶重准确率最高,为84.4%。(4)基于四要素算法模型对贵州中东部2021年单叶重预测,中下部叶单叶重四种算法模型准确率差别不大,上部叶单叶重随机森林算法的准确率最高,为91%,明显高于其余三种算法模型;基于多要素情况下,各模型下、中、上部位平均模拟准确率为81%、74%和85%。(5)在市州维度四要素条件下,下部叶单叶重模拟结果BP神经网络平均准确率为84%;四种算法模型对中部叶模拟结果无显著差异;上部叶模拟结果随机森林算法平均准确率最高,为92%。多要素条件下,下部叶单叶重模拟结果线性回归平均准确率为91%;上部叶单叶重模拟结果线性回归平均准确率最高,为88%。综上,针对贵州中东部平均烟叶单叶重,采用四要素运用BP神经网络和随机森林算法能较好地模拟气象因素对烟叶单叶重的影响,为烟叶生产的调控提供科学依据。
The meteorological and tobacco leaf weight data from 53 districts(counties)in the tobacco-growing region of central and eastern Guizhou from 2010 to 2021 were selected to analyze the influence of meteorological factors on the leaf weight of flue-cured tobacco.Four linear and non-linear models were established using four meteorological factors on an annual scale(four-factor model)and multiple meteorological factors on a ten-day scale(multi-factor model),respectively.The accuracy and stability of the models were validated to explore the advantages and disadvantages of different models in the central and eastern regions of Guizhou.The results indicated:(1)the average single leaf weight of the lower,cutters,and upper leaves in the tobacco-growing areas of central and eastern Guizhou in the past 12 years were 5.7g,9.2g,and 10.8g,respectively.The variation range in single leaf weight was smaller in the lower leaves than in the cutters and upper leaves.(2)Based on the modeling with four factors,the BP neural network algorithm model for the single leaf weight of lower leaves showed the best simulation effect,with R^(2) of 0.26 and RMSE of 0.84g.The simulation effect of the random forest algorithm model exhibited the best simulation performance,with R^(2) of 0.33 and RMSE of 1.08g for single leaf weight in the cutters leaf,and R^(2) of 0.16 and RMSE of 1.59g for single leaf weight in the upper leaf.When model with multiple factors,the random forest algorithm model for the single leaf weight of the lower and upper leaves performed best,with R^(2) of 0.22 and RMSE of 0.85g for the lower leaves and R^(2) of 0.16 and RMSE of 1.57g for the upper leaves.For the cutters leaves,the BP neural network algorithm model demonstrated the optimal simulation effect,with R^(2) of 0.18 and RMSE of 1.14g.(3)The accuracy of the multiple-factor stepwise regression algorithm for predicting the single-leaf weight of the lower leaves was 34.86%,while the simulation accuracy of other algorithms for the same leaf position was generally above 70%.The multi-factor BP neural network model predicted the highest accuracy of 86.24%in the lower single leaf weights,while the random forest model predicted the highest accuracy of 89.91%in the cutters single leaf weights under four-factor.The random forest algorithm with multifactor had the highest prediction accuracy of 84.4%for the upper leaf weight.(4)Based on the four-factor algorithm model for predicting the single-leaf weight in the central and eastern regions of Guizhou in 2021,the accuracy of the four algorithmic models for predicting the single-leaf weight of the cutters and lower leaves showed little difference.The accuracy of the random forest algorithm for predicting the single-leaf weight of the upper leaves was the highest,reaching 91%,which was significantly higher than the other three algorithmic models.Under the multi-factor condition,the average simulated accuracy of the various models for the lower,middle,and upper parts was 81%,74%,and 85%respectively.(5)At the city-level dimension,under the condition of four factors,the average accuracy of the BP neural network model for simulating the single-leaf weight of the lower leaves was 84%.There was no significant difference in the simulation results of the four algorithmic models for the cutters leaves.The upper single leaf weight simulation resulted in the highest average accuracy of 92%with the random forest algorithm.Under the condition of multiple factors,the average accuracy of the linear regression model for simulating the single leaf weight of the lower leaves was 91%,while for the upper leaves,the linear regression model also had the highest average accuracy of 88%.In summary,for the average single-leaf weight of tobacco leaves in the central and eastern regions of Guizhou,using the four-factor BP neural network and random forest algorithm can better simulate the impact of meteorological factors on the single-leaf weight of tobacco leaves,providing scientific basis for the regulation of tobacco leaf production.
作者
李想
夏晓玲
刘艳霞
刘涛
曾莉萍
陈丽萍
徐健
王骏飞
伍洲
王克敏
LI Xiang;XIA Xiao-ling;LIU Yan-xia;LIU Tao;ZENG Li-ping;CHEN Li-ping;XU Jian;WANG Jun-fei;WU Zhou;WANG Ke-min(China National Tobacco Corporation Guizhou Company,Guiyang 550005,China;Guizhou Meteorological Service Center/Guizhou New Meteorological Technology Co.,Ltd,Guiyang 550002;Guizhou Mountain Meteorological Science Research Institute,Guiyang 550002)
出处
《中国农业气象》
CSCD
2024年第9期1012-1026,共15页
Chinese Journal of Agrometeorology
基金
中国烟草公司重点研发项目(2022XM12)
贵州省气象局省市联合科研基金项目[黔气科合SS(2023)12号]
福建中烟项目[闽烟工合作(2021)9号]。
关键词
烤烟单叶重
气象要素
算法模型
BP神经网络
随机森林
Single leaf weigh of flue-cured tobacco
Meteorological factors
Algorithmic model
BP neural network
Random forest
