Scaling Effects on Chlorophyll Content Estimations with RGB Camera Mounted on a UAV Platform Using Machine-Learning Methods

Abstract

Timely monitoring and precise estimation of the leaf chlorophyll contents of maize are crucial for agricultural practices. The scale effects are very important as the calculated vegetation index (VI) were crucial for the quantitative remote sensing. In this study, the scale effects were investigated by analyzing the linear relationships between VI calculated from red–green–blue (RGB) images from unmanned aerial vehicles (UAV) and ground leaf chlorophyll contents of maize measured using SPAD-502. The scale impacts were assessed by applying different flight altitudes and the highest coefficient of determination (R2) can reach 0.85. We found that the VI from images acquired from flight altitude of 50 m was better to estimate the leaf chlorophyll contents using the DJI UAV platform with this specific camera (5472 × 3648 pixels). Moreover, three machine-learning (ML) methods including backpropagation neural network (BP), support vector machine (SVM), and random forest (RF) were applied for the grid-based chlorophyll content estimation based on the common VI. The average values of the root mean square error (RMSE) of chlorophyll content estimations using ML methods were 3.85, 3.11, and 2.90 for BP, SVM, and RF, respectively. Similarly, the mean absolute error (MAE) were 2.947, 2.460, and 2.389, for BP, SVM, and RF, respectively. Thus, the ML methods had relative high precision in chlorophyll content estimations using VI; in particular, the RF performed better than BP and SVM. Our findings suggest that the integrated ML methods with RGB images of this camera acquired at a flight altitude of 50 m (spatial resolution 0.018 m) can be perfectly applied for estimations of leaf chlorophyll content in agriculture.

Response of Vegetation Photosynthetic Phenology to Urbanization in Dongting Lake Basin, China

“…Linear relationships were employed in this study to characterize the response patterns of vegetation phenology and phenological climate sensitivity to nighttime light data; however, the complex nonlinear relationships between urbanization, climate factors, and phenology could not be excluded. Recent studies reported that machine learning methods such as support vector machines and random forests have achieved significant results in fitting climate factors to phenology, and it showed better performance than the linear method in the prediction of phenology [67][68][69][70], thereby provides new insights into the relationship between phenology and environmental factors. Furthermore, the method of classifying regional nighttime light levels focuses on the urbanization intensity as the sole classification criterion, so does not reflect differences in the topography or vegetation type.…”

Spatial Scale Effect of a Typical Polarized Remote Sensor on Detecting Ground Objects

“…In 2013, Angela Lausch et al [ 16 ] studied the effects of different spatial resolutions on the NDVI to obtain a suitable scale. In 2019, Guo et al [ 17 ] investigated the scale effects by analyzing the linear relationships between VI calculated from red-green-blue (RGB) images from unmanned aerial vehicles (UAV) and ground leaf chlorophyll contents of maize measured using SPAD-502.…”

Wheat Leaf Area Index Prediction Using Data Fusion Based on High-Resolution Unmanned Aerial Vehicle Imagery

“…Previous research has shown that images with different spatial resolutions have different effects on the accuracy of crop trait estimation. For example, Guo et al[51] used different flight altitudes to evaluate the impact of UAV images with different spatial resolutions on SPAD prediction. It was found that compared with images obtained with flight altitudes of 75m (2.1 cm/pixel), 100m (2.8 cm/pixel), and 125m (3.4 cm/pixel), imagery with a flying height of 50m (spatial resolution of 1.8 cm/pixel) can be used to estimate SPAD in leaves accurately.…”