.png){kind=icon}
.png){kind=icon}
Return
Integration of radiative transfer–machine learning for physiological mapping of leaf chlorophyll and anthocyanin in cotton
.png){kind=icon}
OA
AI
P
M
C
N
J
P
R
DOI：10.3389/frsen.2026.1813566.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate; non-invasive measurements of leaf biophysical parameters are crucial for assessing crop health and advancing precision agriculture. This study combined an uncrewed aerial system (UAS) drone with radiative transfer modeling and machine learning techniques to estimate two key cotton traits: Leaf Chlorophyll Content (LCC) and Anthocyanin (Anth). Ground-based leaf hyperspectral data collected with a PSR + Spectroradiometer and handheld multi-pigment to match the drone data and support validation. The PROSPECT-D model for leaf optical properties was utilized within the Automated Radiative Transfer Models Operator (ARTMO) framework to conduct forward simulations. Concurrently; inverse modeling was executed using the Machine Learning Regression Algorithms (MLRA) toolbox. During the calibration phase (70% of the dataset) and the validation phase (30% of the dataset); six machine learning algorithms were assessed under various spectral and parameter noise conditions. Among these; Gaussian kernel regression demonstrated the better relative performance; achieving correlation coefficients (r) of 0.82 and 0.78 for LCC and Anth; respectively. The parameter mapping derived from UAS data revealed spatial variability in LCC (0.2–0.6) and in Anth (0.01–0.09) across the study field. Validation results showed strong correlations with ground-truth data; with r values of 0.74 and 0.71 for LCC and Anth; respectively. These findings highlight the potential to integrate UAS data; radiative transfer models; and machine learning to non-invasively estimate crop biophysical parameters and spatially monitor crop physiological variability; thereby facilitating effective precision agriculture practices.
Keywords:
machine learning
precision agriculture
UAS
anthocyanin
chlorophyll
PROSPECT-D
radiative transfer modeling
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
F
IF:
3.7
Papers:
560
Citations:
993
Organization
Cited Papers