Estimating Leaf Area Index in Row Crops Using Wheel-Based and Airborne Discrete Return Light Detection and Ranging...

Area of Science:

• Agricultural Science
• Remote Sensing
• Plant Physiology

Background:

• Leaf Area Index (LAI) is crucial for crop modeling, representing total leaf area per ground area.
• Traditional LAI estimation methods are often labor-intensive and time-consuming.
• Remote sensing technologies offer potential for efficient and accurate LAI assessment.

Purpose of the Study:

• To evaluate the efficacy of Light Detection and Ranging (LiDAR) data for estimating LAI in sorghum and maize.
• To compare LiDAR-derived LAI estimates across different crop treatments and growth stages.
• To investigate the performance of linear and nonlinear regression models using LiDAR features for LAI prediction.

Main Methods:

• LiDAR data acquired from ground-based (wheeled vehicle) and aerial (Unmanned Aerial Vehicles) platforms.
• Extraction of statistical and plant structure-based features from LiDAR point cloud data.
• Development and validation of regression models using in-field plant canopy analyzer data as ground truth.

Main Results:

• LiDAR-based LAI predictive models showed moderate to good performance, with R² values ranging from ~0.4 to 0.80.
• Model accuracy varied by crop (sorghum and maize) and growth stage, with higher coefficients of determination later in the season.
• Nonlinear regression models utilizing LiDAR features demonstrated effective LAI estimation for both crop types.

Conclusions:

• LiDAR technology is a viable tool for non-destructively estimating Leaf Area Index in sorghum and maize.
• The integration of LiDAR data and advanced regression techniques enhances crop canopy characterization for modeling.
• This approach provides valuable data for precision agriculture and crop management strategies.