Lodging stress seriously affects the yield, quality, and mechanical harvesting of maize, and is a major natural disaster causing maize yield reduction. The aim of this study was to obtain light detection and ranging (LiDAR) data of lodged maize using an unmanned aerial vehicle (UAV) equipped with a RIEGL VUX-1UAV sensor to analyze changes in the vertical structure of maize plants with different degrees of lodging, and thus to use plant height to quantitatively study maize lodging. Based on the UAV-LiDAR data, the height of the maize canopy was retrieved using a canopy height model to determine the height of the lodged maize canopy at different times. The profiles were analyzed to assess changes in maize plant height with different degrees of lodging. The differences in plant height growth of maize with different degrees of lodging were evaluated to determine the plant height recovery ability of maize with different degrees of lodging. Furthermore, the correlation between plant heights measured on the ground and LiDAR-estimated plant heights was used to verify the accuracy of plant height estimation. The results show that UAV-LiDAR data can be used to achieve maize canopy height estimation, with plant height estimation accuracy parameters of R² = 0.964, RMSE = 0.127, and nRMSE = 7.449%. Thus, it can reflect changes of plant height of lodging maize and the recovery ability of plant height of different lodging types. Plant height can be used to quantitatively evaluate the lodging degree of maize. Studies have shown that the use of UAV-LiDAR data can effectively estimate plant heights and confirm the feasibility of LiDAR data in crop lodging monitoring.

Crop traits such as aboveground biomass (AGB), total leaf area (TLA), leaf chlorophyll content (LCC), and thousand kernel weight (TWK) are important indices in maize breeding. How to extract multiple crop traits at the same time is helpful to improve the efficiency of breeding. Compared with digital and multispectral images, the advantages of high spatial and spectral resolution of hyperspectral images derived from unmanned aerial vehicle (UAV) are expected to accurately estimate the similar traits among breeding materials. This study is aimed at exploring the feasibility of estimating AGB, TLA, SPAD value, and TWK using UAV hyperspectral images and at determining the optimal models for facilitating the process of selecting advanced varieties. The successive projection algorithm (SPA) and competitive adaptive reweighted sampling (CARS) were used to screen sensitive bands for the maize traits. Partial least squares (PLS) and random forest (RF) algorithms were used to estimate the maize traits. The results can be summarized as follows: The sensitive bands for various traits were mainly concentrated in the near-red and red-edge regions. The sensitive bands screened by CARS were more abundant than those screened by SPA. For AGB, TLA, and SPAD value, the optimal combination was the CARS-PLS method. Regarding the TWK, the optimal combination was the CARS-RF method. Compared with the model built by RF, the model built by PLS was more stable. This study provides guiding significance and practical value for main trait estimation of maize inbred lines by UAV hyperspectral images at the plot level.

Hyperspectral images collected by unmanned aerial vehicles (UAVs) can provide fine, narrowband spectral information and help realize the accurate estimation of physiological and biochemical crop parameters at the plot scale. However, exposure to different backgrounds will negatively affect crop chlorophyll diagnosis. This research investigated the impact of the background and its degree of influence on the accuracy estimation of soil and plant analyser development (SPAD) values. UAV-based hyperspectral images of 498 maize inbred lines were obtained during the grain filling stage. Twenty vegetation indices (VIs) were calculated. VIs that were sensitive to the SPAD value were screened out by the Boruta algorithm. Estimation accuracies of the SPAD values before and after removing the background were compared and analysed. The results showed that Pearson’s correlation coefficient (r) between VIs with background removal and the SPAD value was higher than that without background removal. The SPAD value estimated with sensitive VIs after removing the background was significantly closer to the measured value than that estimated before removing the background. The verification accuracy of the model with background removal was higher than that without background removal. With background removal, the coefficient of determination (R²), root mean square error (RMSE) and mean absolute error (MAE) increased by 60.87%, 48.39% and 40.89%, respectively. This study indicates that removal of the background improves the estimation accuracy of the SPAD value for maize leaves. Maize growth parameters could be quickly obtained from UAV hyperspectral images.

Maize is a globally important cereal and fodder crop. Accurate monitoring of maize planting densities is vital for informed decision-making by agricultural managers. Compared to traditional manual methods for collecting crop trait parameters, approaches using unmanned aerial vehicle (UAV) remote sensing can enhance the efficiency, minimize personnel costs and biases, and, more importantly, rapidly provide density maps of maize fields. This study involved the following steps: (1) Two UAV remote sensing-based methods were developed for monitoring maize planting densities. These methods are based on (a) ultrahigh-definition imagery combined with object detection (UHDI-OD) and (b) multispectral remote sensing combined with machine learning (Multi-ML) for the monitoring of maize planting densities. (2) The maize planting density measurements, UAV ultrahigh-definition imagery, and multispectral imagery collection were implemented at a maize breeding trial site. Experimental testing and validation were conducted using the proposed maize planting density monitoring methods. (3) An in-depth analysis of the applicability and limitations of both methods was conducted to explore the advantages and disadvantages of the two estimation models. The study revealed the following findings: (1) UHDI-OD can provide highly accurate estimation results for maize densities (R² = 0.99, RMSE = 0.09 plants/m²). (2) Multi-ML provides accurate maize density estimation results by combining remote sensing vegetation indices (VIs) and gray-level co-occurrence matrix (GLCM) texture features (R² = 0.76, RMSE = 0.67 plants/m²). (3) UHDI-OD exhibits a high sensitivity to image resolution, making it unsuitable for use with UAV remote sensing images with pixel sizes greater than 2 cm. In contrast, Multi-ML is insensitive to image resolution and the model accuracy gradually decreases as the resolution decreases.

The accurate estimation of nitrogen content in crop plants is the basis of precise nitrogen fertilizer management. Unmanned aerial vehicle (UAV) imaging technology has been widely used to rapidly estimate the nitrogen in crop plants, but the accuracy will still be affected by the variety, the growth stage, and other factors. We aimed to (1) analyze the correlation between the plant nitrogen content of winter wheat and spectral, texture, and structural information; (2) compare the accuracy of nitrogen estimation at single versus multiple growth stages; (3) assess the consistency of UAV multispectral images in estimating nitrogen content across different wheat varieties; (4) identify the best model for estimating plant nitrogen content (PNC) by comparing five machine learning algorithms. The results indicated that for the estimation of PNC across all varieties and growth stages, the random forest regression (RFR) model performed best among the five models, obtaining R², RMSE, MAE, and MAPE values of 0.90, 0.10%, 0.08, and 0.06%, respectively. Additionally, the RFR estimation model achieved commendable accuracy in estimating PNC in three different varieties, with R² values of 0.91, 0.93, and 0.72. For the dataset of the single growth stage, Gaussian process regression (GPR) performed best among the five regression models, with R² values ranging from 0.66 to 0.81. Due to the varying nitrogen sensitivities, the accuracy of UAV multispectral nitrogen estimation was also different among the three varieties. Among the three varieties, the estimation accuracy of SL02-1 PNC was the worst. This study is helpful for the rapid diagnosis of crop nitrogen nutrition through UAV multispectral imaging technology.