To assess the influence of drought stress on the growth and nitrogen nutrition status of pakchoi (Brassica campestris ssp. Chinensis L.) at different nitrogen (N) levels, the changes in N accumulation and enzyme activities involved in N assimilation were investigated. The drought was induced by adding polyethylene glycol (PEG) under hydroponic culture conditions. Pakchoi seedlings were exposed to a modified nutrient solution with different nitrogen concentration (N1, N2, and N3 represent 2, 9 and 18 mM NaNO₃, respectively) and osmotic potential (W1, W2 and W3 represent 0, 60 and 120 g·L⁻¹ PEG 6000) in a full factorial, replicated randomized block design. A short time (seven days) of drought stress caused a significant decline in plant water content, transpiration rate, shoot biomass and shoot nitrogen concentration. Increasing N availability considerably alleviate drought stress by increasing the content of total free amino acids in the roots, promoting the acceleration of root biomass accumulation, and improving the activities of nitrate reductase (NR; EC 1.7.1.1) and glutamine synthetase (GS; EC 6.3.1.2) which would reduce moisture limitations. The results suggested that pakchoi supplied with relative higher N had better growth performance under drought stress.

Monitoring plant nitrogen (N) in a timely way and accurately is critical for precision fertilization. The imaging technology based on visible light is relatively inexpensive and ubiquitous, and open-source analysis tools have proliferated. In this study, texture- and geometry-related phenotyping combined with color properties were investigated for their potential use in evaluating N in pakchoi (Brassica campestris ssp. chinensis L.). Potted pakchoi treated with four levels of N were cultivated in a greenhouse. Their top-view images were acquired using a camera at six growth stages. The corresponding plant N concentration was determined destructively. The quantitative relationships between the nitrogen nutrition index (NNI) and the image-based phenotyping features were established using the following algorithms: random forest (RF), support vector regression (SVR), and neural network (NN). The results showed the full model based on the color, texture, and geometry-related features outperforms the model based on only the color-related feature in predicting the NNI. The RF full model exhibited the most robust performance in both the seedling and harvest stages, reaching prediction accuracies of 0.823 and 0.943, respectively. The high prediction accuracy of the model allows for a low-cost, non-destructive monitoring of N in the field of precision crop management.