Estimation of Leaf Area Index Using A Newly Deployed UAV-Borne Narrow-Band Hyperspectral Imager: Initial Performance Evaluation

Abstract

Hyperspectral imaging sensors mounted on uncrewed aerial vehicles (UAVs) are increasingly utilised in precision agriculture applications. The deployment of a new hyperspectral imager necessitates a comprehensive evaluation of the entire data processing chain to ensure the reliability, accuracy, and relevance of the resulting insights for agricultural decision-making. This study provides an initial evaluation of the performance of a recently deployed narrow-band hyperspectral imager on UAV operating in the visible and near-infrared (VNIR) spectral region for estimating leaf area index (LAI). The study was carried out across a maize field, with plots receiving two distinct nitrogen rates to establish variability within the field. The optical radiative transfer routine of the Soil Canopy Observation of Photosynthesis and Energy (SCOPE) model was used to invert the top-of-canopy (TOC) reflectance spectra for estimating LAI. The estimated LAI was validated through comparison with in-situ LAI measurements and reflectance-derived enhanced vegetation index (EVI), which is sensitive to LAI variations. The estimated LAI demonstrated a robust correlation with in-situ measurements (R2 = 0.77; RMSE = 0.25) as well as with EVI (R2 = 0.93). The preliminary findings suggest that the hyperspectral imager yields reliable TOC reflectance values and accurately captures within-field variability.

Dr. Anirudh Belwalkar

Postdoctoral Researcher

My research interests include hyperspectral remote sensing of vegetation and precision agriculture.

Wuhua Wang

PhD student

My research focuses on inversion of crop canopy parameters (eg. canopy nitrogen concentration) and drone hyperspectral remote sensing.

Fei Wu

PhD Student

My research focuses on UAV remote sensing and precision agriculture.

Shuai Yang

PhD student

My research focuses on Deep learning, hyperspectral remote sensing, and radiative transfer model.

Chenghao Lu

Research assistant & Joint Phd student

My research interests are Agricultural Digital Twin and Smart Breeding. My project focuses on the construction of a Digital Twin system for maize, aiming to fuse Genetic x Environmental x Management data to construct a high-precision and dynamically updated maize growth virtual twin. By introducing a DNA language model with a multimodal fusion approach, I hope to achieve accurate simulation of maize phenotypes and breeding to support sustainable agricultural development.

Prof. Dr. Kang Yu

Professor of Precision Agriculture

My research interests include precision crop farming, hyperspectral remote sensing, and AI in agriculture.