Synchronized UAV multi-angle inversion of canopy structure parameters in wheat breeding materials.

Abstract

Estimating canopy structure - leaf inclination distribution (LIDFa), leaf area index (LAI), and fractional vegetation cover (FCover) - is vital for breeding, yet the added value of multi-angular UAV sensing over nadir-only baselines remains insufficiently quantified. This study developed a UAV-based multi-angular inversion framework that derived high-resolution bidirectional reflectance factors (BRF) from oblique photogrammetry and fitted a kernel-driven BRDF model to characterize reflectance anisotropy. Using transfer learning across cultivars and dates, we compared the retrieval performance of multi-angle versus nadir-only baselines for LIDFa, LAI, and FCover. BRDF model simulations agreed well with airborne BRF (optimal R 2 > 0.80, RRMSE R 2 = 0.59 vs. 0.38 for the best MA and NAD models, respectively) and LIDFa ( R 2 = 0.46 vs. 0.37). For FCover, both configurations achieved high accuracy ( R 2 ≥ 0.73), with MA models providing marginal gains ( R 2 = 0.75). Methodologically, CNN-based transfer learning proved most effective for LAI and FCover, while a Random Forest model using raw multi-angle spectra yielded the best results for LIDFa. Optimal viewing configurations were trait-dependent, generally favoring forward scattering directions with zenith angles between 15° and 45°. These results indicate that kernel-driven BRDF modeling effectively captures spectral anisotropy in dense wheat canopies, and that multi-angular observations provide a distinct advantage for retrieving structural parameters with complex scattering behaviors, such as LAI and LIDFa.

Code and data availability

The paper's data availability statement explicitly deposits the complete source code for BRDF modeling and the transfer learning pipeline, plus a subset of preprocessed field data, in a public GitHub repository matching an allowed URL. Additional data are available only on request.