A Radiative Transfer-Driven Deep Learning Framework for Accurate Estimation of Rice Growth Parameters Using Multisource UAV Data
文献类型：期刊论文
| 作者 | Zou, Yaopeng3; Pei, Jie3; Liu, Yibo3; Tan, Shaofeng3; Fang, Huajun1,2,4; Zheng, Xiaopo3; Wang, Tianxing3 |
| 刊名 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
 |
| 出版日期 | 2025 |
| 卷号 | 63页码:4424116 |
| 关键词 | Crops Filling Autonomous aerial vehicles Monitoring Hyperspectral imaging Booting Accuracy Estimation Data models Adaptation models Crop growth monitoring deep learning PROSAIL model rice unmanned aerial vehicle (UAV) data |
| ISSN号 | 0196-2892 |
| DOI | 10.1109/TGRS.2025.3643447 |
| 产权排序 | 3 |
| 文献子类 | Article |
| 英文摘要 | Leaf area index (LAI) and leaf chlorophyll content (LCC) are key indicators for monitoring rice growth dynamics. While unmanned aerial vehicle (UAV)-based hyperspectral data is widely used, its high redundancy poses challenges for efficient information extraction. To address this, we propose a twostep generic framework. First, synthetic spectra generated by a field-constrained PROSAIL model are used to train a 1-D convolutional neural network (1D-CNN) with a self-attention mechanism that derives spectral composite variables (SCVs) from redundant hyperspectral data. Then, the SCVs are combined with canopy temperature (from thermal infrared (TIR) sensors) and crop height (derived from UAV-based light detection and ranging (LiDAR) and red green blue (RGB) imagery) to develop a retrieval model, validated through both within-site and cross-site strategies. Results showed that the SCVs generated exhibited strong correlations with LAI and LCC, averaging 0.83 and 0.85, respectively. Moreover, the proposed framework achieved high retrieval accuracy across all growth stages (e.g., booting, heading, and filling), with mean R-2 values of 0.76 for LAI and 0.71 for LCC. Specifically, both estimations reached peak performance during the heading stage, with an R-2 of 0.83 and RMSE of 0.47 m(2)/m(2) for LAI, and an R-2 of 0.77 and RMSE of 4.13 mu g/cm(2) for LCC. Cross-site validation confirmed the model's robustness and transferability, with the best performance consistently observed during the heading stage. Benefiting from this framework, spatial predictions of LAI and LCC at centimeter-level resolution closely aligned with observed patterns, enabling precise monitoring of rice growth. Overall, this study presents a robust and transferable solution for overcoming hyperspectral redundancy and enhancing crop growth estimation accuracy. |
| URL标识 | 查看原文 |
| WOS关键词 | LAI ; SIMULATION ; VEGETATION ; TRADE ; MODEL |
| WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001643463900036 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/219408]  |
| 专题 | 千烟洲站森林生态系统研究中心_外文论文 |
| 通讯作者 | Pei, Jie |
| 作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China; 2.Zhongke Jian Inst Ecoenvironm Sci, Jian 343000, Peoples R China 3.Sun Yat Sen Univ, Sch Geospatial Engn & Sci, Zhuhai 519082, Peoples R China; 4.Chinese Acad Sci, Key Lab Ecosyst Network Observat & Modeling, Beijing 100101, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Zou, Yaopeng,Pei, Jie,Liu, Yibo,et al. A Radiative Transfer-Driven Deep Learning Framework for Accurate Estimation of Rice Growth Parameters Using Multisource UAV Data[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2025,63:4424116. |
| APA | Zou, Yaopeng.,Pei, Jie.,Liu, Yibo.,Tan, Shaofeng.,Fang, Huajun.,...&Wang, Tianxing.(2025).A Radiative Transfer-Driven Deep Learning Framework for Accurate Estimation of Rice Growth Parameters Using Multisource UAV Data.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,63,4424116. |
| MLA | Zou, Yaopeng,et al."A Radiative Transfer-Driven Deep Learning Framework for Accurate Estimation of Rice Growth Parameters Using Multisource UAV Data".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 63(2025):4424116. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。