Salt stress has become a major problem in the tomato planting process, of which peroxidase (POD) activity is an important parameter reflecting the antioxidant capacity of plants. In order to explore the dynamic changes of catalase in leaves under different concentrations of NaCl stress, it is necessary to establish a rapid detection technology for changes of POD activity in micro-areas of leaves. In this study, a total of 139 microscopic images were obtained under different concentrations of salt stress (0 g/L, 1 g/L, 2 g/L, 3 g/L) in the spectral range of 400–1000 nm. Regions of interest were extracted according to the reflectance of the samples, and the model was established by combining POD activity. Various spectral pre-treatment combined with partial least-squares regression models was compared to original spectrum combined with partial least-squares regression model. The characteristic wavelength was extracted by four methods, and partial least-squares regression (PLSR) and principal component regression (PCR) were established according to the characteristic wavelength. The results show that multiple scattering correction (MSC) is optimized as the pre-treatment method. The partial least-squares regression model based on the interval variable iterative space contraction method is the best, and the coefficient of determination and root mean square error of prediction set (RMSEP) are 0.66 and 18.94 U/g·min, respectively. The results show that it is feasible to detect the peroxidase activity in tomato leaves by micro-hyperspectral imaging combined with stoichiometry.

In order to select the light quality suitable for plant growth, a quantitative detection model of chlorophyll content in muskmelon leaves was established to monitor plant growth quickly and accurately. In the paper, muskmelon “Boyang 91” was used as the experimental material, and six different light proportion treatments were set up. Through measuring plant height, stem diameter, number of leaves, nodes, and other growth indicators, in addition to leaf chlorophyll content, the response difference of muskmelon to different light qualities was explored in a plant factory. The hyperspectral imaging technology was used to establish the prediction model for the chlorophyll content of muskmelon. The original spectrum was preprocessed and optimized by five pretreatments, and then the characteristic wavelengths were extracted by six methods. Partial least squares regression (PLSR), least squares support vector machine (LSSVM), and convolutional neural network (CNN) were established for optimal feature wavelength. The results showed that the plant height and stem diameter of the T3 treatment were higher than those of other treatments, and their values were 14.48 (cm) and 5.02 (mm), respectively. The chlorophyll content of the T3 treatment was the highest, and its value was 40.16 (mg/g), which was higher than that of other treatments. Through comprehensive analysis, the T3 treatment (light ratio: 6R/1B/2W, light quantum flux: 360 μmol/(m²·s), photoperiod: 12 h) was optimal. Meanwhile, the average spectral reflectance data of 216 leaf samples were extracted, and the S-G preprocessing method was selected to preprocess the original spectral data (Rc = 0.860, RMSEC = 1.806; Rcv = 0.790, RMSECV = 2.161). By comparing and analyzing the correlation coefficients and root mean square errors of six feature wavelength extraction methods, it was concluded that the variable combination population analysis (VCPA) method had the best model effect for feature wavelength extraction (R_P = 0.824, RMSEP = 1.973). Ten characteristic wavelengths ( 396, 409, 457, 518, 532, 565, 687, 691, 701, and 705 nm) extracted by the VCPA method were used to establish the chlorophyll content prediction model, and the chlorophyll content prediction model of S-G-VCPA-CNN had the best performance (Rc = 0.9151, RMSEC = 1.445; Rp = 0.811, RMSEP = 2.055). The results of this study provide data support and a theoretical basis for screening the light ratio of other crops, and also present technical support for online monitoring of crop growth in plant factories.

Summary: Superoxide dismutase (SOD) plays an important role to respond in the defence against damage when tomato leaves are under different types of adversity stresses. This work employed microhyperspectral imaging (MHSI) and visible near‐infrared (Vis–NIR) hyperspectral imaging (HSI) technologies to predict tomato leaf SOD activity. The macroscopic model of SOD activity in tomato leaves was constructed using the convolutional neural network in conjunction with the long and short‐term temporal memory (CNN‐LSTM) technique. Using heterogeneous two‐dimensional correlation spectra (H2D‐COS), the sensitive macroscopic and microscopic absorption peaks connected to tomato leaves' SOD activity were made clear. The combination of CNN‐LSTM algorithm and H2D‐COS analysis was used to research transfer learning between microscopic and macroscopic models based on sensitive wavelengths. The results demonstrated that the CNN‐LSTM model, which was based on the FD preprocessed spectra, had the best performance for the microscopic model, with R_C and R_P reaching 0.9311 and 0.9075, and RMSEC and RMSEP reaching 0.0109 U/mg and 0.0127 U/mg respectively. There were 10 macroscopic and 10 microscopic significant sensitivity peaks found. The transfer learning was carried out using sensitive wavelengths, and the model performed well with an R_P value of 0.7549 and an RMSEP of 0.0725 U/mg. The combined CNN algorithm and H2D‐COS analysis demonstrated the viability of transfer learning across microscopic and macroscopic models for quantitative tomato leaf SOD prediction.

Excessive or improper fertilization not only salinizes soil but also reduces crop yield and quality. The objective of this study was to determine the optimum N, P, and K levels capable of improving tomato fruit quality and reducing environmental pollution for tomato plants under brackish water irrigation conditions. The ‘Jingcai 8’ tomato was used as the research object, and an orthogonal experimental design was used to set up three nutritional factors of N, P, and K. Each factor was set at three levels: N (mmol·L⁻¹): 2.00 (N1), 4.00 (N2), and 8.00 (N3); P (mmol·L⁻¹): 0.67 (P1), 1.33 (P2), and 2.00 (P3); K (mmol·L⁻¹): 8.00 (K1), 12.00 (K2), and 16.00 (K3). The effects of different levels of N, P, and K on plant growth indexes, root vigor and antistress enzymes, biomass and nutrients of plants and fruits, yield, quality, soil nutrients, and soil enzymes were investigated, and metabolomic measurements were performed on treatments ranked first (N:P:K ratio was 2:1.33:12) and ninth (N:P:K ratio was 8:1.33:8) for overall quality. In general, a N concentration of 8 mmol·L⁻¹ promoted plant vegetative growth and plant biomass accumulation by promoting the accumulation of aboveground nitrogen content, but it reduced the weight of single fruit and tomato quality due to an increase in soil EC and pH. In contrast, 0.67 mmol·L⁻¹ of P and 12 mmol·L⁻¹ of K were able to promote both plant vegetative growth and tomato quality formation. In addition, 0.67 mmol·L⁻¹ of P enhanced soil nutrient availability and enzyme activity, while 16 mmol·L⁻¹ of K reduced nutrient availability and enzyme activity and increased soil EC. The concentrations of ferulic acid, cinnamic acid, caffeic acid, coumarin, and (-)-epigallocatechin were generally higher in tomatoes from the T2 treatment (N:P:K ratio was 2:1.33:12) than in those from other treatments. Together, the optimum N:P:K ratio (2:1.33:12) of fertilization enhances tomato yield and quality under brackish water irrigation.