Search

Regenerated rice, characterized by single planting and double harvesting, saves labor and costs, significantly contributing to global food security. Hyperspectral imaging technology, which integrates image and spectral data, provides comprehensive, non-destructive, and pollution-free vegetation canopy analysis, making it highly effective for crop nutrient diagnosis. In this study, we selected two varieties of regenerated rice for field trials. Hyperspectral images were captured during key growth stages (flush, grouting, and ripening) of both the first and regenerated seasons. Utilizing a two-dimensional convolutional neural network (2D-CNN) as a deep feature extractor and a fully connected layer for nitrogen content prediction, we developed a robust model suitable for estimating nitrogen content in regenerated rice. The experimental results demonstrate that our method achieves a mean squared error (MSE) of 0.0008, significantly outperforming the back-propagation (BP) network and multiple linear regression by reducing the MSE by 0.0151 and 0.0247, respectively. It also surpasses the one-dimensional convolutional neural network (1D-CNN) by 0.003. This approach ensures accurate nitrogen content prediction throughout the growth cycle of regenerated rice, aiding in yield and economic benefit enhancement. [ABSTRACT FROM AUTHOR]

Regenerated rice, characterized by single planting and double harvesting, saves labor and costs, significantly contributing to global food security. Hyperspectral imaging technology, which integrates image and spectral data, provides comprehensive, non-destructive, and pollution-free vegetation canopy analysis, making it highly effective for crop nutrient diagnosis. In this study, we selected two varieties of regenerated rice for field trials. Hyperspectral images were captured during key growth stages (flush, grouting, and ripening) of both the first and regenerated seasons. Utilizing a two-dimensional convolutional neural network (2D-CNN) as a deep feature extractor and a fully connected layer for nitrogen content prediction, we developed a robust model suitable for estimating nitrogen content in regenerated rice. The experimental results demonstrate that our method achieves a mean squared error (MSE) of 0.0008, significantly outperforming the back-propagation (BP) network and multiple linear regression by reducing the MSE by 0.0151 and 0.0247, respectively. It also surpasses the one-dimensional convolutional neural network (1D-CNN) by 0.003. This approach ensures accurate nitrogen content prediction throughout the growth cycle of regenerated rice, aiding in yield and economic benefit enhancement.

ABSTRACT Hyperspectral sensors and regression analysis have been used to analyze the most important spectral ranges for biophysical parameters of target crops, aiding in management decision-making. This study aimed to analyze the spectral response of Brachiaria brizantha cv. Marandú leaves to increasing rates of urea fertilization and predict leaf nitrogen content (LNC). Four rates of urea fertilization (0, 25, 50, and 75 kg of N ha-1) were applied. Eight leaves were collected per plot seven times at monthly intervals and subjected to hyperspectral analysis. Leaf spectral responses differed statistically within the visible region, particularly at 550 nm (green). The regression models achieved moderate to good R2 values (0.53 to 0.83) for predicting LNC and identified important wavelengths in the red edge region (715 to 720 nm). These findings demonstrate the potential of spectral analysis to detect changes and forecast leaf nitrogen content in B. brizantha cv. Marandú crops at different fertilization levels.

• Rice root phenotype characteristics can be effectively extracted from terahertz image. • Regression models were established between root phenotype and the actual nitrogen content. • SSA-SVR model with DCT-KPCA can quantitatively detect the actual nitrogen content of rice roots. Root phenotype detection is the basis for screening of dominant root and improving of seed breeding. The efficiency of root phenotype detection is restricted by the concealment and complexity of crop roots. In this paper, a new method based on terahertz imaging technology was proposed to detect the phenotypic characteristics of rice root and quantitatively predict root nitrogen content. First, the terahertz imaging spectral data of rice root were preprocessed with de-overlapping, reconstruction, enhancement, and segmentation. Then, the phenotypic characteristics of root length, diameter and surface area of rice roots were extracted according to the refinement algorithm. In addition, three linear regression models were fitted between root phenotype and root nitrogen content. Finally, Convolutional Neural Network (CNN), Genetic Algorithm-Back Propagation Neural Network (GA-BPNN), and Sparrow Search Algorithm-Support Vector Regression (SSA-SVR) were used to predict nitrogen content in rice roots by training and testing terahertz time domain data. Compared with two kinds of root phenotypic analysis software, the average errors of root length, diameter and root surface area calculated in this paper were 10.68 %, 7.29 % and 3.49 %, respectively. The fitting determination coefficients between root length, root surface area and the root nitrogen content were 0.88 and 0.87 after removing three groups of high-nitrogen data and one group of contrast data. The prediction accuracy of SSA-SVR model was 0.99 and the root mean square error was 0.05. Studies show that terahertz imaging technique can provide an effective analytical way for qualitative analysis of root phenotype. [ABSTRACT FROM AUTHOR]