数字农科院2.0

Bridging the gap between hyperspectral imaging and crop breeding: soybean yield prediction and lodging classification with prototype contrastive learning

文献类型： 外文期刊

作者： Guangyao Sun;Yong Zhang;Lei Wang;Longyu Zhou;Shuaipeng Fei;Shiteng Han;Shunfu Xiao;Yingpu Che;Long Yan;Yun Xu;Yinghui Li;Lijuan Qiu;Yuntao Ma

作者机构：

关键词： Deep Learning;Resnet;Soybean Yield and Lodging Prediction;Unmanned Aerial Vehicle

期刊名称： Computers and Electronics in Agriculture

ISSN： 0168-1699

年卷期： 2025 年 230 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Yield and lodging are crucial indicators in soybean breeding. The development of unmanned aerial vehicle (UAV) equipped with hyperspectral imaging technologies provides high-throughput data for estimating these factors. Previous studies have primarily focused on using hand-crafted band reflectance information, vegetation indices, and texture features to construct empirical models for yield and lodging estimation. However, few studies have directly employed deep learning techniques to automatically extract features from raw hyperspectral images in this context. The objectives were to investigate the potential of combining hyperspectral images with deep learning for soybean yield and lodging prediction, and to avoid the complex process of traditional feature extraction. A novel Prototype Contrastive Learning (PCL) network was proposed to learn representations from raw images. For comparison, hand-crafted vegetation indices and texture features, selected for their effectiveness in crop growth monitoring, were extracted and input into the same machine learning model. The impact of different growth stages on yield and lodging prediction was then investigated. Results demonstrated that the PCL network can effectively capture the similarities within the same class and the differences between different classes. The PCL representations exhibited more distinct clusters according to class labels compared to hand-crafted features. At 86 days after emergence (DAE), the PCL method achieved optimal yield prediction accuracy (R2 = 0.65, RMSE = 507.56 kg/ha) and was significantly higher than the hand-crafted features method (R2 = 0.55, RMSE = 581.37 kg/ha). The highest performance of lodging grades classification was achieved at 65 DAE, and the PCL representations (F1-score = 0.80) achieved a 48 % accuracy improvement compared to hand-crafted features (F1-score = 0.54). This study pioneered the use of deep learning for automatic hyperspectral feature extraction in real-world breeding scenarios, providing valuable insights and strategies to improve yield prediction and lodging classification, thereby more effectively supporting soybean breeding and field management.

分类号：

  • 相关文献

[1]Deep-Learning-Based Rice Phenological Stage Recognition. Jiale Qin,Tianci Hu,Jianghao Yuan,Qingzhi Liu,Wensheng Wang,Jie Liu,Leifeng Guo,Guozhu Song. 2023

[2]Automatic counting of rapeseed inflorescences using deep learning method and UAV RGB imagery. Li J.,Li Y.,Qiao J.,Li L.,Wang X.,Yao J.,Liao G.. 2023

[3]Pretrained Deep Learning Networks and Multispectral Imagery Enhance Maize LCC, FVC, and Maturity Estimation. Jingyu Hu,Hao Feng,Qilei Wang,Jianing Shen,Jian Wang,Yang Liu,Haikuan Feng,Hao Yang,Wei Guo,Hongbo Qiao,Qinglin Niu,Jibo Yue. 2024

[4]基于SAM的田块提取方法在田块平整成效评价中的应用研究. 郝雪丽,李会宾,段玉林,尚国琲,余强毅. 2023

[5]Two-step ResUp&Down generative adversarial network to reconstruct multispectral image from aerial RGB image. Yanchao Zhang,Wen Yang,Wenbo Zhang,Jiya Yu,Jianxin Zhang,Yongjie Yang,Yongliang Lu,Wei Tang. 2022

[6]Identification Method of Cotton Leaf Diseases Based on Bilinear Coordinate Attention Enhancement Module. Shao M.,He P.,Zhang Y.,Zhou S.,Zhang N.,Zhang J.. 2023

[7]Numerical Simulation And Analysis On S.pray Drift Movement Of M ultirotor Plant Protection Unmanned Aerial Vehicle. Yang, Fengbo,Sun, Zhu,Zhou, Qingqing,Cai, Chen,Xue, Xinyu,Yang, Fengbo. 2018

[8]Droplet deposition and control effect of insecticides sprayed with an unmanned aerial vehicle against plant hoppers. Qin, Wei-Cai,Qiu, Bai-Jing,Qin, Wei-Cai,Xue, Xin-Yu,Chen, Chen,Xu, Zhu-Feng,Zhou, Qing-Qing.

[9]Comparison Of Spray Deposition, Control E.fficacy On Wheat Aphids A nd Working Efficiency In The Wheat Field Of The Unmanned Aerial Vehicle With Boom Sprayer And Two Conventional Knapsack Sprayers. Lan, Yubin,Wang, Guobin,Yuan, Huizhu,Ouyang, Fan,Chen, Pengchao,Han, Yuxing,Qi, Haixia. 2019

[10]Estimation Of Land Surface Temperature F.rom Unmanned Aerial Vehicle L oaded Thermal Imager Data. Si, M, Tang, BH, Li, ZL. 2018

[11]Estimating maize seedling number with UAV RGB images and advanced image processing methods. Liu, Shuaibing,Yin, Dameng,Feng, Haikuan,Li, Zhenhai,Xu, Xiaobin,Shi, Lei,Jin, Xiuliang. 2022

[12]Control effect on cotton aphids of insecticides sprayed with unmanned aerial vehicles under different flight heights and spray volumes. Hongyan Hu, Xiangliang Ren, Xiaoyan Ma, Huanhuan Li, Yajie Ma,Dan Wang, Xianpeng Song, Yanhua Meng, Yan Ma. 2021

[13]Estimation of Maize LAI Using Ensemble Learning and UAV Multispectral Imagery under Different Water and Fertilizer Treatments. Cheng, Qian,Xu, Honggang,Fei, Shuaipeng,Li, Zongpeng,Chen, Zhen. 2022

[14]Comparison of Different Dimensional Spectral Indices for Estimating Nitrogen Content of Potato Plants over Multiple Growth Periods. Fan Y.,Feng H.,Yue J.,Liu Y.,Jin X.,Xu X.,Song X.,Ma Y.,Yang G.. 2023

[15]Detecting spatial variability of soil compaction using soil apparent electrical conductivity and maize traits. Ren, Lidong,D'Hose, Tommy,Borra-Serrano, Irene,Lootens, Peter,Hanssens, Daan,De Smedt, Philippe,Cornelis, Wim M.,Ruysschaert, Greet. 2022

[16]Faba Bean (Vicia faba L.) Yield Estimation Based on Dual-Sensor Data. Cui, Yuxing,Ji, Yishan,Liu, Rong,Li, Weiyu,Liu, Yujiao,Liu, Zehao,Zong, Xuxiao,Yang, Tao. 2023

[17]Above-Ground Biomass Estimation And Yield Prediction In Potato By Using Uav-Based Rgb And Hyperspectral Imaging. Li, B, Xu, XM, Zhang, L, Han, JW, Bian, CS, Li, GC, Liu, JG, Jin, LP. 2020

[18]Deep convolutional neural networks for estimating maize above-ground biomass using multi-source UAV images: a comparison with traditional machine learning algorithms. Yu, Danyang,Zha, Yuanyuan,Sun, Zhigang,Li, Jing,Jin, Xiuliang,Zhu, Wanxue,Bian, Jiang,Ma, Li,Zeng, Yijian,Su, Zhongbo. 2022

[19]Dynamic Harvest Index Estimation of Winter Wheat Based on UAV Hyperspectral Remote Sensing Considering Crop Aboveground Biomass Change and the Grain Filling Process. Jianqiang Ren,Ningdan Zhang,Xingren Liu,Shangrong Wu,Dandan Li. 2022

[20]UAV-based multi-sensor data fusion and machine learning algorithm for yield prediction in wheat. Fei, Shuaipeng,Hassan, Muhammad Adeel,Xiao, Yonggui,Su, Xin,Chen, Zhen,Cheng, Qian,Duan, Fuyi,Chen, Riqiang,Ma, Yuntao. 2022

作者其他论文 更多>>