基于无人机光谱图像多数据融合的大豆地上生物量估测研究

doi:10.13733/j.jcam.issn.2095-5553.2025.01.023

摘要/Abstract

摘要： 为提高大豆地上生物量（AGB）估测精度，提出基于无人机遥感技术的多数据融合估测AGB方法。使用多光谱无人机获取大豆始花期、始粒期冠层光谱图像，利用9种植被指数分别构建基于偏最小二乘回归（PLSR）和Lasso回归的叶面积指数（LAI）估测模型，并通过数字表面模型（DSM）估测大豆株高。将株高、LAI和9种植被指数作为模型参数，构建大豆AGB估测模型，分别对比PLSR与Lasso在始花期与始粒期的模型精度，确定最优AGB估测模型。结果表明：株高估测模型始花期R2=0.81，始粒期R2=087，株高拟合效果良好；LAI估测模型PLSR方法优于Lasso方法，始花期R2=0.81，始粒期R2=0.82；利用PLSR和Lasso回归两种方法构建AGB估测模型，通过对比分析PLSR的估测精度高于Lasso回归，始花期R2=0.65，始粒期R2=0.66；通过相关性分析，株高、LAI和植被指数与AGB呈现显著水平，在不同时期利用PLSR方法估测AGB的效果均优于Lasso方法，始花期和始粒期的R2、RMSE分别为0.80、0.17和0.82、1.26；利用不同时期估测模型验证不同大豆品种AGB精度均为85%以上。

关键词: 大豆, 地上生物量, 多光谱, 植被指数, 株高, 叶面积指数

Abstract: In order to improve the accuracy of aboveground biomass （AGB） estimation in soybean, a multi-data fusion method based on UAV remote sensing technology was proposed to estimate AGB. A multispectral UAV was used to acquire canopy spectral images of soybean at the flowering and grain initiation stages, and nine vegetation indices were used to construct leaf area index （LAI） estimation models based on partial least squares regression （PLSR） and Lasso regression, and the height of soybean plants was estimated by digital surface modeling （DSM）. The plant height, LAI, and 9 vegetation indexes were used as model parameters to construct a soybean AGB estimation model, and the model accuracy of PLSR and Lasso during the initial flowering and grain stages was compared respectively to determine the optimal AGB estimation model. The results showed that the plant height estimation model had R2=0.81 at the beginning of flowering and R2=087 at the beginning of grain stage, which was a good fit for plant height. The PLSR method of LAI estimation was better than the Lasso method, with R2=081 at the beginning of flowering and R2=0.82 at the beginning of grain stage. The AGB estimation model was constructed by using the two methods of regression of PLSR and Lasso. The estimation accuracy of PLSR was higher than that of Lasso regression, with R2=0.65 at the beginning flower stage and R2=066 at the beginning grain stage. Through correlation analysis, plant height, LAI and vegetation index showed significant levels with AGB, and the estimation of AGB by using the PLSR method was better than that of the Lasso method at different periods, with R2 and RMSE at the beginning flower stage and the beginning grain stage, respectively, being 0.80, 0.17 and 0.82, 1.26 at the beginning flower and beginning grain stages, respectively. The accuracy of AGB of different soybean varieties was more than 85% by using the estimation models at different periods.

Key words: soybeans, aboveground biomass, multispectral, vegetation index, plant height, leaf area index

中图分类号:

张庆, 李金阳, 石文强, 亓立强, 张伟, . 基于无人机光谱图像多数据融合的大豆地上生物量估测研究[J]. 中国农机化学报, 2025, 46(1): 151-156.

Zhang Qing, Li Jinyang, Shi Wenqiang, Qi Liqiang, Zhang Wei, . Study on estimation of soybean aboveground biomass based on multi data fusion of unmanned aerial vehicle spectral images#br#[J]. Journal of Chinese Agricultural Mechanization, 2025, 46(1): 151-156.

参考文献

［1］　Board J E, Modali H. Dry matter accumulation predictors for optimal yield in soybean ［J］. Crop Science, 2005, 45: 1790-1799.
［2］　黄中文, 赵团结, 喻德跃, 等. 大豆产量有关性状QTL的检测［J］. 中国农业科学, 2009, 42（12）: 4155-4165.
Huang Zhongwen, Zhao Tuanjie, Yu Deyue, et al. Detection of QTLs of yield related traits in soybean ［J］. Scientia Agricultura Sinica, 2009, 42（12）: 4155-4165.
［3］　李金阳, 张伟, 康烨, 等. 基于无人机遥感技术的大豆苗数估算研究［J］. 中国农机化学报, 2022, 43（4）: 83-89.
Li Jinyang, Zhang Wei, Kang Ye, et al. Research on soybean seedling number estimation based on UAV remote sensing technology ［J］. Journal of Chinese Agricultural Mechanization, 2022, 43（4）: 83-89.
［4］　刘杨, 冯海宽, 孙乾, 等. 不同分辨率无人机数码影像的马铃薯地上生物量估算研究［J］. 光谱学与光谱分析, 2021, 41（5）: 1470-1476.Liu Yang, Feng Haikuan, Sun Qian, et al. Estimation study of above ground biomass in potato based on UAV digital images with different resolutions ［J］. Spectroscopy and Spectral Analysis, 2021, 41（5）: 1470-1476.
［5］　Han Liang, Yang Gujun, Dai Huayang, et al. Modeling maize aboveground biomass based on machine learning approaches using UAV remotesensing data ［J］. Plant Methods, 2019, 15（1）:10.
［6］　邓江, 谷海斌, 王泽, 等. 基于无人机遥感的棉花主要生育时期地上生物量估算及验证［J］. 干旱地区农业研究, 2019, 37（5）: 55-61, 69.
Deng Jiang, Gu Haibin, Wang Ze, et al. Estimation and validation of above ground biomass of cotton duringmain growth period using Unmanned Aerial Vehicle （UAV）［J］. Agricultural Research in the Arid Areas, 2019, 37（5）: 55-61, 69.
［7］　徐新娟, 张晋玉, 晁毛妮, 等. 基于冠层反射光谱的大豆生物量预测模型研究［J］. 黑龙江农业科学, 2017（9）: 119-123.Xu Xinjuan, Zhang Jinyu, Chao Maoni, et al. Study on soybean biomass forecasting model based on canopy reflectance spectra ［J］. Heilongjiang Agricultural Sciences, 2017（9）: 119-123.
［8］　陶惠林, 徐良骥, 冯海宽, 等. 基于无人机数码影像的冬小麦株高和生物量估算［J］. 农业工程学报, 2019, 35（19）: 107-116.
Tao Huilin, Xu Liangji, Feng Haikuan, et al. Estimation of plheight and biomass of winter wheat based on UAV digital image ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35（19）: 107-116.
［9］　刘杨, 孙乾, 黄珏, 等. 无人机多光谱影像的马铃薯地上生物量估算［J］. 光谱学与光谱分析, 2021, 41（8）: 2549-2555.Liu Yang, Sun Qian, Huang Jue, et al. Estimation of potato above ground biomass based on UAV multispectral images ［J］. Spectroscopy and Spectral Analysis, 2021, 41（8）: 2549-2555.
［10］　Shu Meiyan, Shen Mengyuan, Dong Qizhou, et al. Estimating the maize aboveground biomass by constructing the tridimensional concept model based on UAVbased digital and multispectral images ［J］. Field Crop Research, 2022, 282: 108491.
［11］　陆国政, 杨贵军, 赵晓庆, 等. 基于多载荷无人机遥感的大豆地上鲜生物量反演［J］. 大豆科学, 2017, 36（1）: 41-50.
Lu Guozheng, Yang Guijun, Zhao Xiaoqing, et al. Inversion of sovbean fresh biomass based on multipayload unmanned aerial vehicles （UAVs）［J］. Soybean Science, 2017, 36（1）: 41-50.

［12］　陈海涛, 李桐辉, 王洪飞, 等. 气吸滚筒式垄上三行大豆密植排种器设计与参数优化［J］. 农业工程学报, 2018, 34（17）: 16-24.

Chen Haitao, Li Tonghui, Wang Hongfei, et al. Design andparameter optimization of pneumatic cylinder ridge threerow close planting seedmetering device for soybean ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34（17）: 16-24.
［13］　赵龙才, 李粉玲, 常庆瑞. 农作物遥感识别与单产估算研究综述［J］. 农业机械学报, 2023, 54（2）: 1-19.
Zhao Longcai, Li Fenling, Chang Qingrui. Review on crop type identification and yield forecasting using remote sensing ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54（2）: 1-19.
［14］　李旭, 陈柏林, 周保平, 等. 利用叶片高光谱反射率预测棉花叶绿素含量［J］. 华中农业大学学报, 2023, 42（3）: 195-202.
Li Xu, Chen Bolin, Zhou Baoping, et al.Predicting the content of chlorophyll in cotton using hyperspectral reflectance of leaves ［J］. Agricultural Mechanization Research, 2023， 42（3）： 195-202.
［15］　王来刚, 贺佳, 郑国清, 等. 基于无人机多光谱遥感的玉米FPAR估算［J］. 农业机械学报, 2022, 53（10）: 202-210.
Wang Laigang, He Jia, Zheng Guoqing, et al. Estimation of maize FPAR based on UAV multispectral remote sensing ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53（10）: 202-210.
［16］　刘冰峰, 李军, 贺佳, 等. 基于高光谱植被指数的夏玉米地上干物质量估算模型研究［J］. 农业机械学报, 2016, 47（3）: 254-262.
Liu Bingfeng, Li Jun, He Jia, et al. Estimation models of aboveground dry matter accumulation of summer maize based on hyperspectral remote sensing vegetation indexes ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2016, 47（3）: 254-262.
［17］　贾学勤, 冯美臣, 杨武德, 等. 基于多植被指数组合的冬小麦地上干生物量高光谱估测［J］. 生态学杂志, 2018, 37（2）: 424-429.〖JP2〗Jia Xueqin, Feng Meichen, Yang Wude, et al. Hyperspectral estimation of aboveground dry biomass of winter wheat based on the combination of vegetation indices ［J］. Chinese Journal of Ecology, 2018, 37（2）: 424-429.

[1]	王林, 孔东升, 王靓敏, 顾秀艳, 杨龙, 温玉雷 . 影响制种玉米机械化去雄的农艺因子[J]. 中国农机化学报, 2024, 45(9): 15-20.
[2]	吴宇通, 张伟, 石文强, 李金阳, 亓立强, . 基于无人机遥感的大豆倒伏识别研究[J]. 中国农机化学报, 2024, 45(9): 209-214.
[3]	连潇, 王建吉, 朱砚. 大豆收获机割台关键技术及损失研究现状分析[J]. 中国农机化学报, 2024, 45(8): 8-13.
[4]	郑金松, 谷海红, 蒋庆刚, 赵靖杰, 王贤, 韩增光. 基于局部特征和视觉词袋模型的大豆叶片病害识别[J]. 中国农机化学报, 2024, 45(8): 204-209.
[5]	王宝梁, 王政, 孟为国, 陆凯, 贾寿良, 薛金林. 基于大豆玉米带状复合种植下的分带式喷杆喷药机设计与试验[J]. 中国农机化学报, 2024, 45(7): 60-67.
[6]	岳耀华, 张伟, 亓立强, . 基于改进YOLOv5的田间大豆花朵生长状态检测方法研究[J]. 中国农机化学报, 2024, 45(7): 188-193.
[7]	李运良, 赵明岩, 王鑫, 闫泓硕, 李育蝉. 基于改进ResNet的带孔蛋胚裂纹检测方法#br#[J]. 中国农机化学报, 2024, 45(7): 201-208.
[8]	单海勇, 严旖旎, 张晋, 刘旭杰, 韩笑, 刘建. 大豆—玉米带状复合种植耕种机械化研究进展[J]. 中国农机化学报, 2024, 45(6): 42-52.
[9]	周良富, 宋海潮, 周彬彬, 于鹏, 代祥. 基于二维激光雷达的果树冠层结构信息检测方法研究[J]. 中国农机化学报, 2024, 45(5): 147-153.
[10]	罗翔, 曹晓林, 药林桃, 吴罗发, 曹中盛, 舒时富. 基于无人机影像的井冈蜜柚果树树形信息提取及产量估测[J]. 中国农机化学报, 2024, 45(5): 161-167.
[11]	王鹏, 谢守勇, , 李明生, , 陈行政, , 张小亮, 刘伟. 大豆玉米带状种植模式下玉米摘穗机设计与试验[J]. 中国农机化学报, 2024, 45(2): 7-12.
[12]	赵胜利, , , 王国宾, , , 胡连槟, , , 徐海钰, , , 巩道财, , , 兰玉彬, , . 基于无人机多光谱遥感的棉花生长参数和产量估算[J]. 中国农机化学报, 2024, 45(2): 227-234.
[13]	张长明, 高祺, 朱冠雄, 高凤菊, 太荣建. 大豆玉米带状复合种植一体化播种机作业质效试验与探究[J]. 中国农机化学报, 2024, 45(12): 21-29.
[14]	贾金豹, 朱成娟, 汪家全, 周鹏. 基于机器学习结合多因子组合的玉米估产研究[J]. 中国农机化学报, 2024, 45(10): 206-214.
[15]	李娜, 顾莉丽. 生产者补贴政策下黑龙江省农户大豆种植行为研究[J]. 中国农机化学报, 2023, 44(7): 273-280.