Lignin is one of the building blocks of plant cell walls, and the study of the spectral characterization of its cleavage process can help to monitor the production and reuse of straw after decay. In this paper, four theoretical model structures of lignin formed by lignin G monomers and connected by β-O-4 bonding type were optimized and calculated based on the density functional theory using the B3LYP/3-21g and B3LYP/6-311g basis sets. The results showed that the theoretical infrared spectra of lignin increased sequentially in the absorption peaks of 1500 cm−1 blue shift and 2932 cm−1 and 1200 cm−1 red shift, while the latter three theoretical models showed new infrared absorption peaks of 716 cm−1 and 823 cm−1 due to the presence of the β-O-4 structure, which is of great value for the theoretical spectral study of organic macromolecules and also provides data support for the spectral change in lignin in the degradation of graminaceous plants.
Introduction: Monitoring the leaf area index (LAI), which is directly related to the growth status of rice, helps to optimize and meet the crop’s fertilizer requirements for achieving high quality, high yield, and environmental sustainability. The remote sensing technology of the unmanned aerial vehicle (UAV) has great potential in precision monitoring applications in agriculture due to its efficient, nondestructive, and rapid characteristics. The spectral information currently widely used is susceptible to the influence of factors such as soil background and canopy structure, leading to low accuracy in estimating the LAI in rice.Methods: In this paper, the RGB and multispectral images of the critical period were acquired through rice field experiments. Based on the remote sensing images above, the spectral indices and texture information of the rice canopy were extracted. Furthermore, the texture information of various images at multiple scales was acquired through resampling, which was utilized to assess the estimation capacity of LAI.Results and discussion: The results showed that the spectral indices (SI) based on RGB and multispectral imagery saturated in the middle and late stages of rice, leading to low accuracy in estimating LAI. Moreover, multiscale texture analysis revealed that the texture of multispectral images derived from the 680 nm band is less affected by resolution, whereas the texture of RGB images is resolution dependent. The fusion of spectral and texture features using random forest and multiple stepwise regression algorithms revealed that the highest accuracy in estimating LAI can be achieved based on SI and texture features (0.48 m) from multispectral imagery. This approach yielded excellent prediction results for both high and low LAI values. With the gradual improvement of satellite image resolution, the results of this study are expected to enable accurate monitoring of rice LAI on a large scale.
The origin of agricultural products significantly influences their quality and safety. Fluorescence spectroscopy was used to analyse Japonica rice 830, grown in different areas of Jilin Province, by examining rice seed, brown rice, and rice flour from 12 origins. Fluorescence spectra were pre-processed through normalisation and smoothing to remove noise. These processed spectra were input into decision trees, support vector machines (SVMs), K-nearest neighbour (KNN), and neural network models for classification. The analysis revealed that the combined four models achieved an average classification accuracy of 98.05% with a computation time of 180 s, while the reduced-scale models improved accuracy to 98.36% and reduced computation time to 11.25 s. Additionally, prediction models using standard rice starch content values across different states achieved R² values over 0.8. This method provides a rapid, precise approach for assessing rice quality and origin, demonstrating significant potential for application in rice analysis.
Thermal processing affects nutrient retention in fruits, yet quantitative in-process monitoring remains challenging. Excitation-emission matrix (EEM) fluorescence combined with principal component analysis (PCA) was used to track changes in nutritional components during apple boiling. Overlapped fluorescence bands were resolved using Gaussian multi-peak empirical function fitting to derive peak descriptors. re regions were screened using minimum redundancy-maximum relevance (mRMR) and tests; the synthetic minority over-sampling technique (SMOTE) was used for class balancing. Support vector machine (SVM) achieved 90.84–97.76% accuracy for boiling-stage classification ( = 0.9019–0.9761). Partial least squares (PLS) provided the best concentration prediction for both vitamin B (, root mean square error (RMSE) = 0.0239) and salicylic acid (, RMSE = 0.0187). Kinetics showed distinct maxima: salicylic acid (11.588–28.796 ng/mL) peaked at 30–35 min (75–88 °C), while vitamin B (2.164–6.001 ng/mL) peaked at 54–58 min at 100 °C. This peak-shape-aware EEM machine-learning framework supports non-destructive, quantitative process monitoring for nutrient retention during thermal processing.