Inversion of winter wheat canopy chlorophyll content using angle-insensitive UAV-based spectral indices

•Two-band spectral indices, which has higher accuracy and stability in multi-angle estimation of CCC.•The angle at hotspot demonstrated the highest accuracy for CCC estimation.•The PSO-BP algorithm has better results in the multi-angle study of monitoring CCC. Canopy chlorophyll content (CCC) is a v...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computers and electronics in agriculture Ročník 230; s. 109902
Hlavní autoři: Ye, Sumeng, Zhang, Zhitao, Chen, Junying, Chen, Haiying, Zhang, Bei, Bai, Xuqian, Yang, Ning, Du, Ruiqi, Yang, Xiaofei, Xu, Qi, Qian, Long, Chen, Yinwen, Zhang, Siying
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.03.2025
Témata:
agriculture
canopy
Canopy Chlorophyll Content
chlorophyll
electronics
Hotspot
information retrieval
Machine Learning
Multi-angle Multispectral Information
orthophotography
Solar Principal Plane
unmanned aerial vehicles
winter wheat
Canopy Chlorophyll Content
Multi-angle Multispectral Information
Hotspot
Machine Learning
Solar Principal Plane
ISSN:0168-1699
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Two-band spectral indices, which has higher accuracy and stability in multi-angle estimation of CCC.•The angle at hotspot demonstrated the highest accuracy for CCC estimation.•The PSO-BP algorithm has better results in the multi-angle study of monitoring CCC. Canopy chlorophyll content (CCC) is a vital indicator of crop growth. Timely, efficient and non-destructive estimation of CCC is crucial for field management. However, current methods for constructing CCC inversion models based on orthophoto information face challenges, such as limited accuracy and inadequate information retrieval. To address these problems, this study adopted multi-angle image information. During the main growth period of winter wheat (February to May), CCC measurements and high-resolution multi-angle multispectral remote sensing images were collected. The angle-insensitive spectral indices were screened by correlation and deviation analysis. Using these spectral indices and measured CCC date, four CCC estimation models were constructed: Partial Least Squares Regression (PLSR), Random Forest (RF), Extreme Gradient Boosting (XG-BOOST) and Particle Swarm Optimization-Backpropagation Neural Network (PSO-BP). The results were as follows: (1) Two-band spectral indices (SI) exhibited a stronger correlation with CCC and higher angle applicability. In particular, the near infrared band was the least affected by angle variations; (2) Among 13 observation angles, the overall performance of the four algorithms were basically consistent: the observation angles at the backward of the Solar Principal Plane (SPP) consistently outperformed others, with the optimal observation angle identified at the hotspot (VAA2-45°); (3) The PSO-BP model demonstrated the best performance and overall stability, achieving the highest accuracy at the optimal angle (R2 = 0.91, RMSE = 0.18 mg/g). These results provide valuable insights into selecting optimal observation angles and constructing CCC estimation models using UAV-based multi-angle multispectral remote sensing images.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0168-1699
DOI:10.1016/j.compag.2025.109902