Geographical origin identification of fragrant pears is crucial for ensuring fruit quality, protecting regional brand value, and maintaining market order. However, pears from different origins often exhibit highly similar appearance and physicochemical properties, making rapid and nondestructive identification challenging for traditional methods. This study proposes a hyperspectral origin identification method based on an enhanced one-dimensional convolutional neural network (ECNN-1D) incorporating an Efficient Channel Attention (ECA) mechanism, using visible-near-infrared (Vis-NIR) and short-wave infrared (SWIR) spectral data. To address the technical challenges of highly similar spectra, redundant features, and complex information distribution, ECNN-1D enhances discriminative spectral feature representation, overcoming limitations of conventional machine learning and standard deep learning models in feature extraction and classification stability. Systematic comparisons with machine learning models (LDA, RF, KNN, SVM) and deep learning models (VGG-1D, ResNet-1D, CNN-1D) showed that while all models performed well on Vis-NIR spectra, ECNN-1D achieved the highest test accuracy of 98.94% and F1 score of 98.95% on the more challenging SWIR spectra, outperforming other approaches. These results indicate that ECNN-1D enables high-precision, nondestructive origin identification of fragrant pears, with potential cost advantages, providing a reliable technical solution for fruit traceability and quality supervision.

Soil salinization constitutes a major abiotic constraint limiting global crop productivity, and breeding salt-tolerant cultivars represents a pivotal strategy to addressing this challenge. In this study, 50 processing tomato genotypes with diverse genetic backgrounds were cultivated hydroponically in Hoagland nutrient solution and subjected to either 0 (control) or 150 mM NaCl at the four-leaf stage. Nine seedling traits, encompassing plant height, stem diameter, and antioxidant enzyme activities, were measured on the 9th day after treatment initiation. Comprehensive evaluation of salt tolerance was performed using principal component analysis (PCA), fuzzy membership function analysis, and cluster analysis. The coefficients of variation (CVs) for all measured traits ranged from 21.54% to 92.69%, with relative proline content exhibiting the highest CV (92.69%) and relative stem diameter showing the lowest (21.54%). Correlation analysis revealed a highly significant positive correlation between relative plant height and relative stem diameter, and a highly significant negative correlation between relative plant height and relative proline (Pro) content. PCA reduced the nine seedling traits to four principal components, which collectively accounted for 67.529% of the total variance. Based on the combined results of fuzzy membership function and cluster analyses, the 50 genotypes were classified into three distinct categories: highly salt-tolerant (six genotypes), moderately salt-tolerant (26 genotypes), and salt-sensitive (18 genotypes). These findings provide a theoretical foundation and valuable germplasm resources for breeding salt-tolerant processing tomato varieties.

In order to screen high-quality processed tomato germplasm resources, the present research measured the content of quality indicators—lycopene, soluble solids, total acidity, total sugar, and vitamin C—in mature fruits of 113 processed tomato high-generation inbred lines. Comprehensive evaluations of germplasm quality were conducted through genetic diversity analysis, correlation analysis, principal component analysis, and cluster analysis. The results indicated that the variability of the five quality traits in the materials under test was relatively high, with a range of variation from 12.21% to 39.04%. Total sugar exhibited the greatest variation, while soluble solids content showed the least variation. The genetic diversity index ranged from 1.899 to 2.064, with total sugar, vitamin C, and lycopene showing high genetic variation. Soluble solids content was significantly positively correlated with lycopene, total sugar, and total acidity, while lycopene content was significantly positively correlated with total sugar. Vitamin C showed weaker correlations with other traits, but exhibited a significant negative correlation with total sugar. Total acidity had relatively simple correlations with other traits, being significantly correlated only with soluble solids. The three principal components extracted from the principal component analysis all had eigenvalues above 0.8%, contributing to a cumulative contribution rate of 77.435%. Through cluster analysis, the tested materials were divided into six major groups at an Euclidean distance of 15. Group I serves as candidate materials for breeding varieties with good basic quality and high vitamin C content. Group II stood out in terms of high sugar and lycopene content, suitable for developing tomato sauce or juice products with high vibrancy and sweetness. Group III had a high nutritional value and vibrant color, serving as core germplasm resources for breeding high-end processing-specific varieties. Group IV had high soluble solids content, making it a parent source for improving the viscosity and flavor of sauce tomatoes. Group V was suitable for specific formulations requiring high acidity or as breeding materials for high-acidity characteristics. Group VI had limited processing potential and should be used cautiously in breeding. The comprehensive evaluation results showed that the top five germplasm resources in terms of score were W119, 61, 82, 83, and W144. This study enriched the high-quality processed tomato germplasm resources and provided parental resources for quality breeding of processed tomatoes.

Currently, the escalating global problem of soil salinization severely limits the yield and quality of processing tomatoes. However, the differential responses and salt-tolerance strategies among processing tomato genotypes with different salt tolerances under salt stress remain largely elusive. Therefore, this study used salt-tolerant genotype 'S39' and salt-sensitive genotype 'S37' as materials. Seeds were sown in plug trays, and seedlings at the two-leaf-one-heart stage were transplanted into hydroponic containers filled with Hoagland nutrient solution. When seedlings reached the four-leaf-one-heart stage, they were exposed to NaCl treatments of 0 mM (control), 120 mM (Na120), and 180 mM (Na180). Plant samples were collected at 3, 6, and 9 days after treatment to determine growth parameters, physiological indices, and gene expression levels, aiming to reveal the dynamic differential responses to salt stress between the two processing tomato genotypes. The results demonstrated that the inhibitory effect of NaCl on the growth of processing tomatoes was aggravated with increasing NaCl concentration and treatment duration. The most significant difference in salt tolerance between the two genotypes was observed at 9 days under 180 mM NaCl treatment. At this sampling point, the relative salt-stress indices of superoxide dismutase (SOD) activity, peroxidase (POD) activity, soluble sugar content, proline content, chlorophyll a, chlorophyll b, and total chlorophyll (a + b) in 'S39' were significantly higher than those in 'S37' by 31.55%, 53.40%, 66.70%, 65.07%, 20.80%, 15.74%, and 19.44%, respectively. In addition, Na contents in roots and stems, as well as K contents in stems and leaves, were significantly higher in 'S39' than in 'S37' by 43.40%, 8.67%, 22.08%, and 21.99%, respectively. In contrast, relative electrolyte leakage and malondialdehyde (MDA) content in 'S37' were 15.54% and 12.44% higher than those in 'S39'. In addition, photosynthetic parameters, including net photosynthetic rate (Anet), stomatal conductance (gs), intercellular CO2 concentration (Ci), transpiration rate (E), and chlorophyll fluorescence parameters, were more stable in 'S39' than in 'S37'. In conclusion, 'S39' possesses stronger salt tolerance via a multi-level regulatory strategy involving an enhanced antioxidant enzyme system, elevated accumulation of osmoregulatory substances, improved mineral ion balance, and increased stability of the photosynthetic apparatus. This study provides a comprehensive multi-level analysis of the differential salt tolerance mechanisms in processing tomato genotypes with contrasting salt tolerances and lays a theoretical basis for the screening and identification of salt-tolerant germplasm in processing tomatoes.

Accurate fig detection in complex environments is a significant challenge. Small targets, occlusion, and similar backgrounds are considered the main obstacles in intelligent harvesting. To address this, this study proposes Fig-YOLO, an improved YOLOv11n-based detection algorithm with multiple targeted architectural innovations. First, a Spatial-Frequency Selective Convolution (SFSConv) module is introduced into the backbone to replace conventional convolution, enabling joint modeling of spatial structures and frequency-domain texture features for more effective discrimination of figs from visually similar backgrounds. Second, an enhanced bi-branch attention mechanism (EBAM) is incorporated at the network's terminal stage to strengthen the representation of key regions and improve robustness under severe occlusion. Third, a multi-branch dynamic sampling convolution (MFCV) module replaces the original C3k2 structure in the feature fusion stage, capturing figs of varying sizes through dynamic sampling and residual deep-feature fusion. Experimental results show that Fig-YOLO achieves precision, recall, and mAP@0.5 of 89.2%, 78.4%, and 87.3%, respectively, substantially outperforming the baseline YOLOv11n. Further evaluation confirms that the model maintains stable performance across varying fruit sizes, occlusion levels, lighting conditions, and data sources. Fig-YOLO's innovations offer solid support for intelligent orchard monitoring and harvesting.

Total Soluble Solids (TSS) in tomatoes is a core indicator for evaluating fruit quality and processing characteristics. Its composition mainly consists of soluble sugars (such as fructose and glucose) and organic acids (such as citric acid and malic acid). The contents of sugars and acids and their ratio directly affect the flavor and nutritional value. Cultivated tomatoes have a TSS of 4–6%, compared with 10–15% in wild varieties. In recent years, with the advancement of molecular biology and genomics technologies, significant progress has been made in the research on the regulatory mechanisms of tomato fruit TSS and major sugars and acids, including the identification of major quantitative trait locus (QTLs) (Lin5, SlALMT9), functional characterization via CRISPR/Cas9 and elucidation of the transporter network. Breaking the negative correlation between TSS and yield remains a major bottleneck in breeding. Analyzing the mechanism by which environmental factors regulate the TSS and optimizing cultivation measures are crucial for increasing the TSS content in tomatoes. The deep integration of cutting-edge technologies (such as Genome-wide association studies (GWAS), metabolome-wide association studies (mGWAS), Genomic selection (GS), genome editing, and crop modeling) with design breeding is expected to accelerate the development of high-TSS tomato varieties. This paper reviews the current research status from the following four aspects: QTL mapping related to tomato TSS and mining of major genes, metabolic and transport mechanisms of major sugars and acids and key genes, the influence of environmental factors on TSS, and application of genetic improvement strategies and technologies.

Drought stress significantly threatens maize yield worldwide. A promising strategy to mitigate the impact of drought involves regulating stomatal closure, thereby conserving water more effectively. Despite this, the mechanisms underlying stomatal responses to drought in maize have remained largely elusive. In this study, we have identified two maize inbred lines, CML493 and XUN971, that exhibit significantly distinct phenotypes in terms of water loss from detached shoots. Under drought conditions, CML493 exhibits superior survival rates, higher relative water content, and improved photosynthetic efficiency compared to XUN971. These observations suggest that CML493 possesses greater drought resilience, which can be attributed to its more rapid stomatal closure in response to water scarcity. To further understand this phenomenon, we employed RNA sequencing technology to uncover differentially expressed genes (DEGs) associated with stomatal closure in these lines. Our analysis uncovered a set of 571 up-regulated genes enriched processes such as oxidation-reduction reactions, protein phosphorylation, responses to water deprivation, and hormone-mediated signaling pathways. Whereas, the 1158 down-regulated genes were mainly enriched the processes of photosynthesis, response to light stimulus, response to abiotic stimulus, chloroplast rRNA processing, photosystem II assembly. We identified 12 key candidate genes, such as the ethylene signaling factor ZmEIL5, auxin signaling factors ZmIAA25 and ZmIAA44, actin-depolymerizing factor ZmADF14, calcium uniporter protein mitochondrial ZmMCU4, ABC transporter G family member ZmABCG40, and mitogen-activated protein kinase ZmMAPK19, that are likely involved in stomatal regulation during drought. These results provide new clues on understanding the molecular mechanisms of stomatal closure in response to drought stress.

High-throughput plant phenotyping with hyperspectral imaging (HSI) is pivotal for accelerating crop improvement to address global food security. Adoption is limited by a data-processing bottleneck, forcing a trade-off between costly, inflexible commercial software and programming-intensive open-source libraries. To overcome this barrier, we developed PlantSpecLab, an open-source, no-code platform that unifies the HSI workflow from image processing to modeling within a single interactive interface. The platform introduces spectrally guided segmentation strategies (Range Averaging, Difference Enhancement) and a spectral Fractional-Order Differencing (FOD) preprocessor to enhance extraction of subtle, physiologically relevant features. Across diverse in-house and public datasets, FOD-preprocessed spectra improved model performance over conventional pipelines, yielding a mean classification accuracy of 82.86 % for tomato maturity and average R 2 = 0.8638 for fruit firmness. In cross-software benchmarks, PlantSpecLab matched the accuracy of ENVI and code-based Python pipelines while reducing end-to-end workflow time by over 90 % (from approximately 80 minutes to about 8 minutes). PlantSpecLab provides a transparent, efficient analytical environment that lowers the technical barrier to HSI analysis. This enables researchers to prioritize biological interpretation while minimizing computational overhead.

In this study, processing tomato (Solanum lycopersicum L.) ‘Ligeer 87-5’ was hydroponically cultivated under 100 mM NaCl to simulate salt stress. To investigate the impacts on ion homeostasis, osmotic regulation, and redox status in tomato seedlings, different endogenous levels of ascorbic acid (AsA) were established through the foliar application of 0.5 mM AsA (NA treatment), 0.25 mM lycorine (LYC, an inhibitor of AsA synthesis; NL treatment), and a combination of LYC and AsA (NLA treatment). The results demonstrated that exogenous AsA significantly increased the activities and gene expressions of key enzymes (L-galactono-1,4-lactone dehydrogenase (GalLDH) and L-galactose dehydrogenase (GalDH)) involved in AsA synthesis in tomato seedling leaves under NaCl stress and NL treatment, thereby increasing cellular AsA content to maintain its redox status in a reduced state. Additionally, exogenous AsA regulated multiple ion transporters via the SOS pathway and increased the selective absorption of K+, Ca2+, and Mg2+ in the aerial parts, reconstructing ion homeostasis in cells, thereby alleviating ion imbalance caused by salt stress. Exogenous AsA also increased proline dehydrogenase (ProDH) activity and gene expression, while inhibiting the activity and transcription levels of Δ1-pyrroline-5-carboxylate synthetase (P5CS) and ornithine-δ-aminotransferase (OAT), thereby reducing excessive proline content in the leaves and alleviating osmotic stress. LYC exacerbated ion imbalance and osmotic stress caused by salt stress, which could be significantly reversed by AsA application. Therefore, exogenous AsA application increased endogenous AsA levels, reestablished ion homeostasis, maintained osmotic balance, effectively alleviated the inhibitory effect of salt stress on tomato seedling growth, and enhanced their salt tolerance.

Rapid and precise 3D organ segmentation is crucial for the automatic extraction of phenotypic traits, forming a fundamental prerequisite for intelligent plant breeding. The advancement of deep learning technology has replaced labor-intensive manual measurements and traditional computer vision methods, which are sensitive to parameters, in phenotypic trait extraction. However, current larger network structures not only require extensive point cloud data but also consume substantial computational resources, rendering them unsuitable for agricultural tasks with limited plant samples. Therefore, this study developed a lightweight 3D deep learning network (PEPNet) that achieves precise plant organ segmentation and stem-leaf phenotypic trait extraction. The adopted simple-but-effective network architecture and innovative modern operations, including a high-dimensional feature mapping strategy for preprocessing input points, a local feature extraction module based on inverted residual bottleneck block, and a cost-free attention block for spatial feature fusion, effectively implement multiscale hierarchies and adaptively reduce computational overheads. Experimental results from cotton stem-leaf segmentation demonstrated that PEPNet not only presented approximately 2 x faster inference speed (9.59 ms) and throughput (146.32 plants per second) but also achieved competitive segmentation performance compared to other six state-of-the-art deep learning networks, namely PointNet++, DGCNN, CurveNet, Point Cloud Transformer, PointMLP, and SPoTr, achieving 95.99 %, 94.66 %, 95.32 %, and 91.31 % in Precision, Recall, F1-score, and mIoU, respectively. In transferability experiments with tomato and soybean plants, PEPNet achieved almost all the best metrics and significantly outperformed the second-best model (CurveNet). Furthermore, ablation study verified the optimal trade-off between efficiency and accuracy in this network. Any modifications to the modules could potentially disrupt the optimal trade-off. This work could contribute to reducing computational resources and annotation costs for applying segmentation methods in high-throughput phenotyping tasks.

Potential competing interests: No potential competing interests to

Moisture content and sugar content are characteristic substances that determine the quality of dried jujubes. In this study, we collected visible/near-infrared and near-infrared hyperspectral data (Vis-NIR and NIR) from three dried jujubes samples with different storage periods, and established recognition models for different storage periods of jujubes using Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), Deep Learning Methods (LeNet, ResNet, DenseNet, MobileNet and EfficientNet). Then, we constructed a dried jujubes storage period classification model based on feature bands using Successive projections algorithm (SPA) and Principal component analysis (PCA) methods, the results showed that the classification results based on Vis-NIR were better than those based on NIR, and the classification model based on SPA method was more accurate. In addition, the internal quality attributes of moisture content and total sugar during a single storage period of jujube were also predicted, and a quality prediction model for multiple storage periods was established based on NIR. This study provides a fast and non-destructive method for detecting the storage and quality components of jujube, in order to control the quality of jujube at different storage periods.

Tomatoes are susceptible to damage from cold temperatures in all stages of growth. Therefore, it is important to identify genetic resources and genes that can enhance tomato’s ability to tolerate cold. In this study, a population of 223 tomato accessions was used to identify the sensitivity or tolerance of plants to cold stress. Transcriptome analysis of these accessions revealed that SUS3, a member of the sucrose synthase gene family, was induced by cold stress. We further investigated the role of SUS3 in cold stress by overexpression (OE) and RNA interference (RNAi). Compared with the wild type, SUS3-OE lines accumulated less MDA and electrolyte leakage and more proline and soluble sugar, maintained higher activities of SOD and CAT, reduced superoxide radicals, and suffered less membrane damage under cold. Thus, our findings indicate that SUS3 plays a crucial role in the response to cold stress. This study indicates that SUS3 may serve as a direct target for genetic engineering and improvement projects, which aim to augment the cold tolerance of tomato crops.

Leaf color mutants serve as valuable models for studying the regulation of plant photosynthesis, alternations in chloroplast structure and function, and the analysis of associated gene functions. A yellow leaf mutant, ylm, was separated from the wild tomato M82, with its yellowing intensity influenced by low temperature. To assess the low-temperature sensitivity of this mutant, the photosynthetic and chlorophyll fluorescence responses of ylm and M82 were examined under different temperature conditions. In this study, the ylm mutant and its wild type, M82, were exposed to three temperature levels, 16, 25, and 30 °C, for 48 h. The impact of these temperature treatments on leaf color change, chlorophyll content, photosynthetic performance, and chlorophyll fluorescence characteristics of mutant ylm was investigated. The results revealed the following: (1) After exposure to 16 °C, the ylm mutant exhibited significant yellowing, a marked reduction in chlorophyll content, and a notable increase in carotenoid content. At 25 °C, the differences were less pronounced, and at 30 °C, the differences between ylm and M82 were minimal. (2) The photosynthetic rate of the ylm mutant was lower than that of M82 at 16 °C, with the gap narrowing as temperature increased, eventually converging at higher temperatures. (3) The fluorescence transient curve (OJIP) of the ylm mutant differed significantly from that of M82 at 16 °C, with higher fluorescence intensity at the O point and lower intensity at the J, I, and P points. This difference was decreased at 25 °C and nearly disappeared at 30 °C. Additionally, the Fv/Fm, Fv/Fo, PIabs, PItotal, ABS/CSm, TRo/CSm, and ETo/CSm values of ylm were lower than those of M82 at 16 °C, while the ABS/RC and DIo/RC values were higher, with no significant differences observed at 30 °C. These findings suggest that the ylm mutant is highly sensitive to low temperature, with pronounced yellowing, reduced light energy absorption and capture efficiency, and impaired electron transport at lower temperature.

Camel milk powder possesses high nutritional and economic value. The adulteration of camel milk powder with other varieties seriously compromises consumer rights. In the practical application of hyperspectral analysis for camel milk powder detection, the sample categories used for testing often differ from those used to construct the model. As a learning approach adept at domain-shifted and few shot scenarios, meta-learning is employed to tackle this issue. In this study, we used camel milk powder adulterated with cow milk powder as training samples and adulterated with goat milk powder as test samples. In the detection of eleven adulteration levels, the detection accuracy for pure camel milk powder reached 98.92%. Notably, the detection accuracy for the less conspicuous 70% adulteration level achieved 77.69%. The comprehensive detection accuracy of meta-learning reached 84.4%, showcasing notable improvements compared to SVM, BP, and CNN, which saw increases of 24.67%, 28.16%, and 18.4%, respectively. The detailed analysis of feature vectors and contributions substantiates the reliability and stability of the meta-learning-based qualitative analysis. The introduction of meta-learning methods is poised to make significant contributions to rapid detection by relevant testing agencies and the protection of consumer rights.

Domestication and improvement are important processes that generate the variation in genome and phonotypes underlying crop improvement.Unfortunately,during selection for certain attributes,other valuable traits may be inadvertently discarded.One example is the decline in fruit soluble solids content(SSC)during tomato breeding.Several genetic loci for SSC have been identified,but few reports on the underlying mechanisms are available.In this study we performed a genome-wide association study(GWAS)for SSC of the red-ripe fruits in a population consisting of 481 tomato accessions with large natural variations and found a new quantitative trait locus,STP1,encoding a sugar transporter protein.The causal variation of STP1,a 21-bp InDel located in the promoter region 1124 bp upstream of the start codon,alters its expression.STP1 Insertion accessions with an 21-bp insertion have higher SSC than STP1Deletion accessions with the 21-bp deletion.Knockout of STP1 in TS-23 with high SSC using CRISPR/Cas9 greatly decreased SSC in fruits.In vivo and in vitro assays demonstrated that ZAT10-LIKE,a zinc finger protein transcription factor(ZFP TF),can specifically bind to the promoter of STP1Insertion to enhance STP1 expression,but not to the promoter of STP1Deletion,leading to lower fruit SSC in modern tomatoes.Diversity analysis revealed that STP1 was selected during tomato improvement.Taking these results together,we identified a naturally occurring causal variation underlying SSC in tomato,and a new role for ZFP TFs in regulating sugar transporters.The findings enrich our understanding of tomato evolution and domestication,and provide a genetic basis for genome design for improving fruit taste.

Early detection and diagnosis of crop anomalies is crucial for enhancing crop yield and quality. Recently, the combination of machine learning and deep learning with hyperspectral images has significantly improved the efficiency of crop detection. However, acquiring a large amount of properly annotated hyperspectral data on stressed crops requires extensive biochemical experiments and specialized knowledge. This limitation poses a challenge to the construction of large-scale datasets for crop stress analysis. Meta-learning is a learning approach that is capable of learning to learn and can achieve high detection accuracy with limited training samples. In this paper, we introduce meta-learning to hyperspectral imaging and crop detection for the first time. In addition, we gathered 88 hyperspectral images of drought-stressed tomato plants and 68 images of freeze-stressed tomato plants. The data related to drought serve as the source domain, while the data related to frost damage serve as the target domain. Due to the difficulty of obtaining target domain data from real-world testing scenarios, only a limited amount of target domain data and source domain data are used for model training. The results indicated that meta-learning, with a minimum of eight target domain samples, achieved a detection accuracy of 69.57%, precision of 59.29%, recall of 66.32% and F1-score of 62.61% for classifying the severity of frost stress, surpassing other methods with a target domain sample size of 20. Moreover, for determining whether the plants were under stress, meta-learning, with a minimum of four target domain samples, achieved a detection accuracy of 89.1%, precision of 89.72%, recall of 93.08% and F1-score of 91.37% outperforming other methods at a target domain sample size of 20. The results show that meta-learning methods require significantly less data across different domains compared to other methods. The performance of meta-learning techniques thoroughly demonstrates the feasibility of rapidly detecting crop stress without the need for collecting a large amount of target stress data. This research alleviates the data annotation pressure for researchers and provides a foundation for detection personnel to anticipate and prevent potential large-scale stress damage to crops.

Firmness, soluble solid content (SSC) and titratable acidity (TA) are characteristic substances for evaluating the quality of cherry tomatoes. In this paper, a hyper spectral imaging (HSI) system using visible/near-infrared (Vis-NIR) and near-infrared (NIR) was proposed to detect the key qualities of cherry tomatoes. The effects of individual spectral information and fused spectral information in the detection of different qualities were compared for firmness, SSC and TA of cherry tomatoes. Data layer fusion combined with multiple machine learning methods including principal component regression (PCR), partial least squares regression (PLSR), support vector regression (SVR) and back propagation neural network (BP) is used for model training. The results show that for firmness, SSC and TA, the determination coefficient R2 of the multi-quality prediction model established by Vis-NIR spectra is higher than that of NIR spectra. The R2 of the best model obtained by SSC and TA fusion band is greater than 0.9, and that of the best model obtained by the firmness fusion band is greater than 0.85. It is better to use the spectral bands after information fusion for nondestructive quality detection of cherry tomatoes. This study shows that hyperspectral imaging technology can be used for the nondestructive detection of multiple qualities of cherry tomatoes, and the method based on the fusion of two spectra has a better prediction effect for the rapid detection of multiple qualities of cherry tomatoes compared with a single spectrum. This study can provide certain technical support for the rapid nondestructive detection of multiple qualities in other melons and fruits.

Processing tomato (Lycopersicon esculentum Mill.) is rich in vitamins and lycopene, which is favored by con-sumers. In this study, near-infrared hyperspectral imaging (HSI) technology (980-1660 nm) was used to detect the firmness, soluble solids, lycopene, and titratable acid content of processing tomatoes and to classify fruits at three maturity stages. Savitzky-Golay (SG) smoothing was used to reduce the noise of hyperspectral images. The average spectrum of the tomato fruit was extracted for model development. Random forest (RF), partial least squares (PLS), and recurrent neural network (RNN) were used to develop models for predicting the four quality attributes and identifying the maturity level. Results showed that the RNN model had a classification accuracy of 40% higher than RF and 17% higher than PLS. In the prediction of quality parameters, RNN models had the highest R2 value (>0.87), followed by PLS and RF models. Important wavelengths were identified by calculating its contribution values and were used to interpret the model. The results illustrated that near-infrared hyper -spectral imaging technology combined with deep learning could effectively predict the quality and maturity of processing tomatoes. The work can provide a perspective on the application of HSI as a nondestructive testing approach for other agricultural products.

This study investigated the protective effects of exogenous ascorbic acid (AsA, 0.5 mmol·L−1) treatment on salt-induced photosystem inhibition in tomato seedlings under salt stress (NaCl, 100 mmol·L−1) conditions with and without the AsA inhibitor lycorine. Salt stress reduced the activities of photosystem II (PSII) and PSI. AsA treatment mitigated inhibition of the maximal photochemical efficiency of PSII (Fv/Fm), maximal P700 changes (Pm), the effective quantum yields of PSII and I [Y(II) and Y(I)], and non-photochemical quenching coefficient (NPQ) values under salt stress conditions both with and without lycorine. Moreover, AsA restored the balance of excitation energy between two photosystems (β/α-1) after disruption by salt stress, with or without lycorine. Treatment of the leaves of salt-stressed plants with AsA with or without lycorine increased the proportion of electron flux for photosynthetic carbon reduction [Je(PCR)] while decreasing the O2-dependent alternative electron flux [Ja(O2-dependent)]. AsA with or without lycorine further resulted in increases in the quantum yield of cyclic electron flow (CEF) around PSI [Y(CEF)] while increasing the expression of antioxidant and AsA–GSH cycle-related genes and elevating the ratio of reduced glutathione/oxidized glutathione (GSH/GSSG). Similarly, AsA treatment significantly decreased the levels of reactive oxygen species [superoxide anion (O2−) and hydrogen peroxide (H2O2)] in these plants. Together, these data indicate that AsA can alleviate salt-stress-induced inhibition of PSII and PSI in tomato seedlings by restoring the excitation energy balance between the photosystems, regulating the dissipation of excess light energy by CEF and NPQ, increasing photosynthetic electron flux, and enhancing the scavenging of reactive oxygen species, thereby enabling plants to better tolerate salt stress.