Many studies have achieved efficient and accurate methods for identifying crop lodging under homogeneous field surroundings. However, under complex field conditions, such as diverse fertilization methods, different crop growth stages, and various sowing periods, the accuracy of lodging identification must be improved. Therefore, a maize plot featuring different growth stages was selected in this study to explore an applicable and accurate lodging extraction method. Based on the Akaike information criterion (AIC), we propose an effective and rapid feature screening method (AIC method) and compare its performance using indexed methods (i.e., variation coefficient and relative difference). Seven feature sets extracted from unmanned aerial vehicle (UAV) images of lodging and nonlodging maize were established using a canopy height model (CHM) and the multispectral imagery acquired from the UAV. In addition to accuracy parameters (i.e., Kappa coefficient and overall accuracy), the difference index (DI) was applied to search for the optimal window size of texture features. After screening all feature sets by applying the AIC method, binary logistic regression classification (BLRC), maximum likelihood classification (MLC), and random forest classification (RFC) were utilized to discriminate among lodging and nonlodging maize based on the selected features. The results revealed that the optimal window sizes of the gray-level cooccurrence matrix (GLCM) and the gray-level difference histogram statistical (GLDM) texture information were 17 × 17 and 21 × 21, respectively. The AIC method incorporating GLCM texture yielded satisfactory results, obtaining an average accuracy of 82.84% and an average Kappa value of 0.66 and outperforming the index screening method (59.64%, 0.19). Furthermore, the canopy structure feature (CSF) was more beneficial than other features for identifying maize lodging areas at the plot scale. Based on the AIC method, we achieved a positive maize lodging recognition result using the CSFs and BLRC. This study provides a highly robust and novel method for monitoring maize lodging in complicated plot environments.

This study aims to develop an effective and reliable method for estimating rice quality indices and yield, addressing the growing need for rapid, non-destructive, and accurate predictions in modern agriculture. Field experiments were conducted in 2018 at the Suiling Water Conservancy Comprehensive Experimental Station (47°27′ N, 127°06′ E), using Longqingdao 3 as the test variety. Measurements included the leaf area index (LAI), chlorophyll content (SPAD), leaf nitrogen content (LNC), and leaf spectral reflectance during the tillering, jointing, and maturity stages. Based on these parameters, spectral indicators were calculated, and univariate linear regression models were developed to predict key rice quality indices. The results demonstrated that the optimal R² values for brown rice rate, moisture content, and taste value were 0.866, 0.913, and 0.651, with corresponding RMSE values of 0.122, 0.081, and 1.167. After optimizing the models, the R² values for the brown rice rate and taste value improved significantly to 0.95 (RMSE: 0.075) and 0.992 (RMSE: 0.179), respectively. Notably, the spectral index GM2 during the jointing stage achieved the highest accuracy for yield prediction, with an R² value of 0.822. These findings confirm that integrating multiple indicators across different growth periods enhances the accuracy of rice quality and yield predictions, offering a robust and intelligent solution for practical agricultural applications.

The objective of this study was to develop a low-cost method for rice growth information obtained quickly using digital images taken with smartphone. A new canopy parameter, namely, the canopy volume parameter (CVP), was proposed and developed for rice using the leaf area index (LAI) and plant height (PH). Among these parameters, the CVP was selected as an optimal parameter to characterize rice yields during the growth period. Rice canopy images were acquired with a smartphone. Image feature parameters were extracted, including the canopy cover (CC) and numerous vegetation indices (VIs), before and after image segmentation. A rice CVP prediction model in which the CC and VIs served as independent variables was established using a random forest (RF) regression algorithm. The results revealed the following. The CVP was better than the LAI and PH for predicting the final yield. And a CVP prediction model constructed according to a local modelling method for distinguishing different types of rice varieties was the most accurate (coefficient of determination (R²) = 0.92; root mean square error (RMSE) = 0.44). These findings indicate that digital images can be used to track the growth of crops over time and provide technical support for estimating rice yields.