Rice Leaf Chlorophyll Content Estimation Using UAV-Based Spectral Images in Different Regions

Estimation of crop biophysical and biochemical characteristics is the key element for growth monitoring with remote sensing. With application unmanned aerial vehicles (UAV) as a sensing platform worldwide, it has become important to develop general estimation models, which can interpret data crops by different sensors in agroclimatic regions into comprehensible agronomy parameters. Leaf chlorophyll content (LCC), be measured soil plant analysis development (SPAD) value using SPAD-502 Chlorophyll Meter, one parameters that are closely related production. This study compared rice (Oryza sativa L.) LCC two (Ningxia Shanghai) UAV-based spectral images. For Ningxia, images plots nitrogen biochar rates were acquired 125-band hyperspectral camera from 2016 2017, total 180 samples recorded. Shanghai, rates, straw returning, rotation systems 5-band multispectral 2017 2018, 228 The features each area analyzed results showed both had significant correlations reflectance at green, red, red-edge bands 8 vegetation indices such normalized difference index (NDVI). models built partial least squares regression (PLSR), support vector (SVR), artificial neural network (ANN) methods. PLSR tended more stable accurate than SVR ANN when applied R2 values higher 0.7 through validations. demonstrated canopy regions, cultivars, types sensor-based shared similar could estimated models. implied wider geographic extent accurately quantify LCC, helpful assessment production forecasts.