Estimation of the Yield and Plant Height of Winter Wheat Using UAV-Based Hyperspectral Images

Abstract

Crop yield is related to national food security and economic performance, and it is therefore important to estimate this parameter quickly and accurately. In this work, we estimate the yield of winter wheat using the spectral indices (SIs), ground-measured plant height (H), and the plant height extracted from UAV-based hyperspectral images (HCSM) using three regression techniques, namely partial least squares regression (PLSR), an artificial neural network (ANN), and Random Forest (RF). The SIs, H, and HCSM were used as input values, and then the PLSR, ANN, and RF were trained using regression techniques. The three different regression techniques were used for modeling and verification to test the stability of the yield estimation. The results showed that: (1) HCSM is strongly correlated with H (R2 = 0.97); (2) of the regression techniques, the best yield prediction was obtained using PLSR, followed closely by ANN, while RF had the worst prediction performance; and (3) the best prediction results were obtained using PLSR and training using a combination of the SIs and HCSM as inputs (R2 = 0.77, RMSE = 648.90 kg/ha, NRMSE = 10.63%). Therefore, it can be concluded that PLSR allows the accurate estimation of crop yield from hyperspectral remote sensing data, and the combination of the SIs and HCSM allows the most accurate yield estimation. The results of this study indicate that the crop plant height extracted from UAV-based hyperspectral measurements can improve yield estimation, and that the comparative analysis of PLSR, ANN, and RF regression techniques can provide a reference for agricultural management.

Evaluation of RGB and Multispectral Unmanned Aerial Vehicle (UAV) Imagery for High-Throughput Phenotyping and Yield Prediction in Barley Breeding

“…The coefficient of variation of the yield measured in the field was highest in HAL and lowest in IPK and also the yield prediction of approach 1 revealed the highest predictive power in HAL and lowest in IPK (Figure 5a), indicating that a larger variation of the predicted trait may enable higher r 2 values. Similar correlations were also found in other yield modelling studies [28,29,128]. The indication that in some cases a more accurate yield prediction was achieved after precipitation shows a possible positive correlation between the water status of the plant represented by the VIs and the final plot yield.…”

“…This becomes especially important since breeding for yield improvement around the globe is based on the empirical selection criterion of yield itself, even though yield is known to be subject to low heritabilities and high genotype × environment inter-action [25][26][27]. Furthermore, the collected spectral and derived spatial data can be used for yield predictions already during the growth phase [28,29], which may assist decision making in agribusiness [30]. Traditional methods of measuring yield are destructive, timeand energy-intensive and cannot be applied to large areas [31].…”

A Review on Drone-Based Data Solutions for Cereal Crops

“…Yield estimation of cereals using plant height [137,138], CIs/VIs [18,65,75,81,82,132,138] derived from RGB, multispectral and/or hyperspectral sensors are available in the literature. An image processing method combined with the K-means clustering algorithm with a graph-cut (KCG) algorithm on RGB images collected using a multi-rotor drone is utilized to estimate rice yield [139].…”

“…The rice yield is predicted with single-stage and multi-temporal VIs derived from multispectral and digital (RGB) images [132]. Spectral indices, ground-measured plant height, and height derived from drone hyperspectral images were used to predict the winter wheat yield [138].…”

Assessing the Self-Recovery Ability of Maize after Lodging Using UAV-LiDAR Data

“…At present, it focuses on crop monitoring under non-lodging conditions. Compared with wheat [22,23], rice [24,25], and other crops with a low height, the canopy height of maize is easier to monitor by UAV, which can be mainly divided into optical sensors and laser radar sensors. There are mainly two methods for extracting canopy height based on the UAV platform.…”