A hyperspectral R based leaf area index estimator: model development and implementation using AVIRIS-NG

Abstract

Hyperspectral Remote Sensing (HRS) data is vital for crop growth monitoring due to availability of contiguous bands. This research work provides a new novel crop estimator model given the name “Crop Stage estimator” developed using the HRS data on an open-source R platform. The generic model structure provides an easy way to test and modify the importance of crop parameter namely Leaf Area Index to deduce crop growth stages of winter wheat (Triticum aestivum L.) particularly during –heading, tillering and booting. Further, to know the LAI variations at different agriculture sites, the best model was implemented using the AVIRIS-NG (Airborne Visible Near-Infrared Imaging Spectrometer - Next Generation) hyperspectral datasets. The analysis indicates that during tillering stage the performance was found best during calibration (r = 0.66, RMSE =0.40, and Bias =-0.80) and validation (r = 0.98, RMSE =0.20, and Bias =0.12) in comparison to the ground measurements. © 2022 Informa UK Limited, trading as Taylor & Francis Group.