Rice adulteration is a severe problem in agro-products and food regulatory agencies, suppliers, and consumers. In this study, to effectively distinguish whether high-quality rice is mixed with low-quality rice, detection and analysis of adulterated rice in five levels with different mixing proportions was conducted via terahertz spectroscopy and pattern recognition algorithms. Initially, samples were prepared and spectral data were acquired by using the terahertz transmission mode, and a principal component analysis (PCA) algorithm was applied to extract features from original spectrum information and reduce data dimensions. Subsequently, partial least squares-discriminant analysis (PLS-DA), support vector machine (SVM), and a back propagation neural network (BPNN) combined with the absorption spectra after different pretreatments, including standard normal variate (SNV) transformation, baseline correction (BC), and first derivative (1st derivative), were applied to establish the classification models. Results indicate that an SVM model employing the absorption spectra with a 1st derivative pretreatment exhibits the best discrimination ability, with an accuracy up to 97.33% in the prediction set. This result proves that terahertz spectroscopy combined with chemometric methods can be an effective tool to identify rice adulteration levels.

Non-destructive plant stress phenotyping begins with traditional one-dimensional (1D) spectroscopy, followed by two-dimensional (2D) imaging, three-dimensional (3D) or even temporal-three-dimensional (T-3D), spectral-three-dimensional (S-3D), and temporal-spectral-three-dimensional (TS-3D) phenotyping, all of which are aimed at observing subtle changes in plants under stress. However, a comprehensive review that covers all these dimensional types of phenotyping, ordered in a spatial arrangement from 1D to 3D, as well as temporal and spectral dimensions, is lacking. In this review, we look back to the development of data-acquiring techniques for various dimensions of plant stress phenotyping (1D spectroscopy, 2D imaging, 3D phenotyping), as well as their corresponding data-analyzing pipelines (mathematical analysis, machine learning, or deep learning), and look forward to the trends and challenges of high-performance multi-dimension (integrated spatial, temporal, and spectral) phenotyping demands. We hope this article can serve as a reference for implementing various dimensions of non-destructive plant stress phenotyping.

The activities of enzymes are the basis of evaluating the quality of honey. Beekeepers usually use concentrators to process natural honey into concentrated honey by concentrating it under high temperatures. Active enzymes are very sensitive to high temperatures and will lose their activity when they exceed a certain temperature. The objective of this work is to study the kinetic mechanism of the temperature effect on diastase activity and to develop a nondestructive approach for quick determination of the diastase activity of honey through a heating process based on visible and near-infrared (Vis/NIR) spectroscopy. A total of 110 samples, including three species of botanical origin, were used for this study. To explore the kinetic mechanism of diastase activity under high temperatures, the honey of three kinds of botanical origins were processed with thermal treatment to obtain a variety of diastase activity. Diastase activity represented with diastase number (DN) was measured according to the national standard method. The results showed that the diastase activity decreased with the increase of temperature and heating time, and the sensitivity of acacia and longan to temperature was higher than linen. The optimum temperature for production and processing is 60 °C. Unsupervised clustering analysis was adopted to detect spectral characteristics of these honeys, indicating that different botanical origins of honeys can be distinguished in principal component spaces. Partial least squares (PLS) and least squares-support vector machine (LS-SVM) algorithms were applied to develop quantitative relationships between Vis/NIR spectroscopy and diastase activity. The best result was obtained through Gaussian filter smoothing-standard normal variate (GF-SNV) pretreatment and the LS-SVM model, known as GF-SNV-LS-SVM, with a determination coefficient (R²) of prediction of 0.8872, and root mean square error (RMSE) of prediction of 0.2129. The overall results of this paper showed that the diastase activity of honey can be determined quickly and non-destructively with Vis/NIR spectral methods, which can be used to detect DN in the process of honey production and processing, and to maximize the nutrient content of honey.

Tea polyphenols are considered as an important indicator of tea quality. Rapid detection of tea polyphenol content plays a valuable role for tea breeding and quality inspection during tea production. In this work, a portable rapid non-destructive detection device of tea polyphenols in fresh tea leaves was developed, which integrated the fusion technology of visible/short-wave (400–1050 nm) and long-wave (1000–1650 nm) near-infrared spectroscopy (Vis/NIR). Experimental results indicated that the spectra within the overlapping region (1000–1050 nm) were assembled by applying the spectral data fusing method. Followed by spectral data preprocessing with the Savitzky–Golay smoothing (SG) method, least squares support vector regression (LS–SVR) models were established for detecting the tea polyphenol content of fresh tea leaves. Based on the fused Vis/NIR spectra (dual-band), the correlation coefficient of calibration (R_C), root mean square error of calibration (RMSEC), correlation coefficient of prediction (R_P), root mean square error of prediction (RMSEP), and residual predictive deviation (RPD) reached 0.976, 0.679%, 0.893, 0.897%, and 2.230, respectively, which were better than the visible/short-wave or long-wave near infrared spectral data (single-band). The sensitive spectral wavebands of tea polyphenols extracted using the random frog (RF) algorithm were distributed in 402–448 nm, 555–600 nm, 810–1042 nm, 1056–1103 nm, 1219–1323 nm, 1406–1416 nm, and 1499–1511 nm. This demonstrated that the prediction of tea polyphenol content using fused spectral data combined with the LS–SVR model depended on various functional groups such as auxochromes, chromogenic groups, and hydrogen-containing groups. The proposed device is capable of non-destructive detection of tea polyphenol content in fresh tea leaves, which can provide effective technical support for tea breeding and tea leaf quality control.

Salt stress is considered one of the primary threats to cotton production. Although cotton is found to have reasonable salt tolerance, it is sensitive to salt stress during the seedling stage. This research aimed to propose an effective method for rapidly detecting salt stress of cotton seedlings using multicolor fluorescence–multispectral reflectance imaging coupled with deep learning. A prototyping platform that can obtain multicolor fluorescence and multispectral reflectance images synchronously was developed to get different characteristics of each cotton seedling. The experiments revealed that salt stress harmed cotton seedlings with an increase in malondialdehyde and a decrease in chlorophyll content, superoxide dismutase, and catalase after 17 days of salt stress. The Relief algorithm and principal component analysis were introduced to reduce data dimension with the first 9 principal component images (PC1 to PC9) accounting for 95.2% of the original variations. An optimized EfficientNet-B2 (EfficientNet-OB2), purposely used for a fixed resource budget, was established to detect salt stress by optimizing a proportional number of convolution kernels assigned to the first convolution according to the corresponding contributions of PC1 to PC9 images. EfficientNet-OB2 achieved an accuracy of 84.80%, 91.18%, and 95.10% for 5, 10, and 17 days of salt stress, respectively, which outperformed EfficientNet-B2 and EfficientNet-OB4 with higher training speed and fewer parameters. The results demonstrate the potential of combining multicolor fluorescence–multispectral reflectance imaging with the deep learning model EfficientNet-OB2 for salt stress detection of cotton at the seedling stage, which can be further deployed in mobile platforms for high-throughput screening in the field.