数字农科院2.0

Diagnostic study of defoliation and boll opening effects on machine-harvested cotton using multi-source UAV remote sensing data

文献类型： 外文期刊

作者： Huiyang Zhao;Chenning Ren;Xiaojuan Li;Pengzhong Zhang;Jianping Cui;Yabin Li;Shuyuan Zhang;Tao Lin

作者机构：

关键词： Defoliation and boll opening;Feature selection;Machine learning;Machine-harvested cotton;Remote sensing data fusion;UAV

期刊名称： Industrial Crops and Products

ISSN： 0926-6690

年卷期： 2025 年 236 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Accurate assessment of cotton defoliation (DF) and boll opening (BO) is essential for optimizing yield and fiber quality during mechanized harvesting, as improper timing can reduce yield and impair fiber quality. Unmanned aerial vehicle (UAV)-based remote sensing has become an effective tool for monitoring these indicators, but most current methods rely on single-sensor data, limiting diagnostic accuracy and generalizability. To address this limitation, we propose a multi-source data fusion framework integrating RGB, multi-spectral (MS), and thermal infrared (TIR) sensors for comprehensive canopy information. The fused dataset includes vegetation indices (VIs), color indices (CIs), texture features (Tex), and canopy temperature (TC). Feature selection was performed using pearson correlation coefficients (PCCs), recursive feature elimination with cross-validation (RFECV), and the Boruta algorithm to identify key variables. Three machine learning models—partial least-squares regression (PLSR), random forest regression (RFR), and extreme gradient boosting regression (XGBR)—were developed and compared. The RFECV-selected RGB+MS+TIR features in the XGBR model achieved the highest predictive accuracy, with R² values of 0.918 for defoliation rate and 0.867 for boll opening rate, improving by 1.9 % and 4.3 %, respectively, over single-sensor models. Root mean square error (RMSE) and relative RMSE (rRMSE) were reduced by 1.11 %-1.99 % and 1.66 %-2.28 %, respectively. These findings demonstrate that multi-source UAV data fusion, combined with advanced machine learning techniques, significantly enhances the accuracy and robustness of cotton defoliation and boll opening diagnosis. This approach offers a practical solution for precision agriculture to improve harvest scheduling and defoliant management.

分类号：

  • 相关文献

[1]UAV imaging hyperspectral for barnyard identification and spatial distribution in paddy fields. Yanchao Zhang,Ziyi Yan,Junfeng Gao,Yiyang Shen,Haozhe Zhou,Wei Tang,Yongliang Lu,Yongjie Yang. 2024

[2]Classification of different gluten wheat varieties based on hyperspectral preprocessing, feature screening, and machine learning. Xinghui Qi,Shaohua Zhang,Liyang Wang,Xuexu Hu,Haiyan Zhang,Wei Feng,Chenyang Wang,Tiancai Guo,Li He. 2025

[3]PlantMine: A Machine-Learning Framework to Detect Core SNPs in Rice Genomics. Kai Tong,Xiaojing Chen,Shen Yan,Liangli Dai,Yuxue Liao,Zhaoling Li,Ting Wang. 2024

[4]Estimating LAI for Cotton Using Multisource UAV Data and a Modified Universal Model. Yan, Puchen,Han, Qisheng,Feng, Yangming,Kang, Shaozhong. 2022

[5]Entropy Weight Ensemble Framework for Yield Prediction of Winter Wheat Under Different Water Stress Treatments Using Unmanned Aerial Vehicle-Based Multispectral and Thermal Data. Shuaipeng Fei,Muhammad Adeel Hassan,Yuntao Ma,Meiyan Shu,Qian Cheng,Zongpeng Li,Zhen Chen,Yonggui Xiao. 2021

[6]Estimation of soybean yield parameters under lodging conditions using RGB information from unmanned aerial vehicles. Bai D.,Li D.,Zhao C.,Wang Z.,Shao M.,Guo B.,Liu Y.,Wang Q.,Li J.,Guo S.,Wang R.,Li Y.-H.,Qiu L.-J.,Jin X.. 2023

[7]Water Chlorophyll a Estimation Using UAV-Based Multispectral Data and Machine Learning. Zhao X.,Li Y.,Chen Y.,Qiao X.,Qian W.. 2023

[8]Combining vegetation, color, and texture indices with hyperspectral parameters using machine-learning methods to estimate nitrogen concentration in rice stems and leaves. Dunliang Wang,Rui Li,Tao Liu,Shengping Liu,Chengming Sun,Wenshan Guo. 2023

[9]Comprehensive degradation index for monitoring desert grassland using UAV multispectral imagery. Shu han Gao,Yong zhi Yan,Yuan Yuan,Ning Zhang,Le Ma,Qing Zhang. 2024

[10]Multi-Feature Fusion for Estimating Above-Ground Biomass of Potato by UAV Remote Sensing. Guolan Xian,Jiangang Liu,Yongxin Lin,Shuang Li,Chunsong Bian. 2024

[11]UAV-based LiDAR and multispectral sensors fusion for cotton yield estimation: Plant height and leaf chlorophyll content as a bridge linking remote sensing data to yield. Bin Wu,Liqiang Fan,Bowei Xu,Jiajie Yang,Rumeng Zhao,Qiong Wang,Xiantao Ai,Huixin Zhao,Zuoren Yang. 2025

[12]Estimation of Leaf, Spike, Stem and Total Biomass of Winter Wheat Under Water-Deficit Conditions Using UAV Multimodal Data and Machine Learning. Jinhang Liu,Wenying Zhang,Yongfeng Wu,Juncheng Ma,Yulin Zhang,Binhui Liu. 2025

[13]Identification of Cotton Leaf Mite Damage Stages Using UAV Multispectral Images and a Stacked Ensemble Method. Fan, Shifeng,He, Qiang,Chen, Yongqin,Xu, Xin,Guo, Wei,Lu, Yanhui,Liu, Jie,Qiao, Hongbo. 2025

[14]Surface Soil Moisture Retrieval over Winter Wheat Fields Based on Fused Multispectral and L-Band MiniSAR Data. Ziyi Luo,Xianyu Zhang,Yonghui Wang,Chengcai Zhang,Mingliang Jiang,Xingxing Zhu. 2025

[15]Effects Of Planting Patterns On Y.ield, Quality, And Defoliation I n Machine-Harvested Cotton. Wang Fang:yong,Kong Xian:hui,Yu Yu,Han Huan:yong,Liu Jing:de,Lin Hai,Wang Xu:wen,Chen Bing,Ning Xin:zhu. 2019

[16]Improved Detection and Location of Small Crop Organs by Fusing UAV Orthophoto Maps and Raw Images. Huaiyang Liu,Huibin Li,Haozhou Wang,Chuanghai Liu,Jianping Qian,Zhanbiao Wang,Changxing Geng. 2025

[17]A Phenology-Based Spectral And Temporal F.eature Selection Method For C rop Mapping From Satellite Time Series. Hu, Q, Sulla, D, Xu, BD, Yin, H, Tang, HJ, Yang, P, Wu, WB. 2019

[18]Soil Organic Carbon Prediction Based on Different Combinations of Hyperspectral Feature Selection and Regression Algorithms. Chang, Naijie,Jing, Xiaowen,Zeng, Wenlong,Zhang, Yungui,Li, Zhihong,Chen, Di,Jiang, Daibing,Zhong, Xiaoli,Dong, Guiquan,Liu, Qingli. 2023

[19]A Classification Feature Optimization Method for Remote Sensing Imagery Based on Fisher Score and mRMR. Lv, Chengzhe,Lu, Yuefeng,Lu, Miao,Feng, Xinyi,Fan, Huadan,Xu, Changqing,Xu, Lei. 2022

[20]Combining novel feature selection strategy and hyperspectral vegetation indices to predict crop yield. Fei S.,Li L.,Han Z.,Chen Z.,Xiao Y.. 2022

作者其他论文 更多>>