Nonheading Chinese cabbage is an important leafy vegetable, and quantitative identification and automated analysis of nonheading Chinese cabbage leaves are crucial for cultivating new varieties with higher quality, yield, and resistance. Traditional leaf phenotypic analysis relies mainly on phenotypic observation and the practical experience of breeders, leading to issues such as time consumption, labor intensity, and low precision, which result in low breeding efficiency. Considering these issues, a method for the extraction and analysis of phenotypes of nonheading Chinese cabbage leaves is proposed, targeting four qualitative traits and ten quantitative traits from 1500 samples, by integrating deep learning and OpenCV image processing technology. First, a leaf classification model is trained using YOLOv8 to infer the qualitative traits of the leaves, followed by the extraction and calculation of the quantitative traits of the leaves using OpenCV image processing technology. The results indicate that the model achieved an average accuracy of 95.25%, an average precision of 96.09%, an average recall rate of 96.31%, and an average F1 score of 0.9620 for the four qualitative traits. From the ten quantitative traits, the OpenCV-calculated values for the whole leaf length, leaf width, and total leaf area were compared with manually measured values, showing RMSEs of 0.19 cm, 0.1762 cm, and 0.2161 cm², respectively. Bland–Altman analysis indicated that the error values were all within the 95% confidence intervals, and the average detection time per image was 269 ms. This method achieved good results in the extraction of phenotypic traits from nonheading Chinese cabbage leaves, significantly reducing the personpower and time costs associated with genetic resource analysis. This approach provides a new technique for the analysis of nonheading Chinese cabbage genetic resources that is high-throughput, precise, and automated.

Cytokinins (CKs) are among the hormones that regulate plants’ growth and development, and the CKX and IPT genes, which are CK degradation and biosynthesis genes, respectively, play important roles in fine-tuning plants’ cytokinin levels. However, the current research on the function of IPT and CKX in cucumber’s growth, development, and response to abiotic stress is not specific enough, and their regulatory mechanisms are still unclear. In this study, we focused on the IPT and CKX genes in cucumber, analyzed the physiological and biochemical properties of their encoded proteins, and explored their expression patterns in different tissue parts and under low light, salt stress, and drought stress. Eight CsCKX and eight CsIPT genes were identified from the cucumber genome. We constructed a phylogenetic tree from the amino acid sequences and performed prediction analyses of the cis-acting elements of the CsCKX and CsIPT promoters to determine whether CsCKXs and CsIPTs are responsive to light, abiotic stress, and different hormones. We also performed expression analysis of these genes in different tissues, and we found that CsCKXs and CsIPTs were highly expressed in roots and male flowers. Thus, they are involved in the whole growth and development process of the plant. This paper provides a reference for further research on the biological functions of CsIPT and CsCKX in regulating the growth and development of cucumber and its response to abiotic stress.

Irrigation has a significant impact on NxO (N2O and NO) emissions from cultivated land, yet the N2O or NO emission among the irrigation lower limits under different irrigation modes has not been well compared. In an irrigated lettuce field, three DR (drip irrigation) lower limits were designed, including 75% (DR1), 65% (DR2) and 55% (DR3) field capacity, and one FI (furrow irrigation) lower limit (65% field capacity). The N2O and NO emission fluxes and soil nitrogen (N) forms were determined, and the linear correlation between these indicators was analyzed. Results showed that under the same irrigation regime, the N2O and NO emissions from furrow irrigation treatment increased by 36.8% and 45.2% respectively compared to that from drip irrigation treatment. The cumulative N2O and NO emissions under DR3 were 30.2% and 28.6% higher than under DR1, respectively. Moreover, DR1 was also the lowest among the four treatments in soil NO3--N concentration. The N2O and NO emission fluxes were more correlated to soil NH4+-N (r=0.88 and 0.76) or NO2--N (r=0.90 and 0.80) concentration than soil NO3--N and soluble organic N, indicating that N2O and NO were mainly produced by the soil nitrification process. When the irrigation regime was the same, N2O and NO emissions were lower with drip irrigation than with furrow irrigation. Besides, drip irrigation with small quota but high frequency reduced N2O and NO emission compared to that with large quota but low frequency. Keywords: nitrous oxide, nitric oxide, drip irrigation, furrow irrigation, soil nitrogen DOI: 10.25165/j.ijabe.20231604.7961 Citation: Hou M M, Xiao Y, Zhu Q Y, Chen J N, Huang H, Jin Q, et al. NxO emissions in response to the irrigation lower limits under different irrigation modes in a lettuce field. Int J Agric & Biol Eng, 2023; 16(4): 159–167.

Gray mold is one of the major diseases affecting tomato production. Its early symptoms are often inconspicuous, yet the disease spreads rapidly, leading to severe economic losses. Therefore, the development of efficient and non-destructive early detection technologies is of critical importance. At present, multispectral imaging-based detection methods are constrained by two major bottlenecks: limited sample size and single modality, which hinder precise recognition at the early stage of infection. To address these challenges, this study explores a detection approach integrating multispectral fluorescence and reflectance imaging, combined with machine learning algorithms, to enhance early recognition of tomato gray mold. Particular emphasis is placed on evaluating the effectiveness of multimodal information fusion in extracting early disease features, and on elucidating the quantitative relationships between disease progression and key physiological indicators such as chlorophyll content, water content, malondialdehyde levels, and antioxidant enzyme activities. Furthermore, an improved WGAN-GP (Wasserstein Generative Adversarial Network with Gradient Penalty) is employed to alleviate data scarcity under small-sample conditions. The results demonstrate that multimodal data fusion significantly improves model sensitivity to early-stage disease detection, while WGAN-GP-based data augmentation effectively enhances learning performance with limited samples. The Random Forest model achieved an early recognition precision of 97.21% on augmented datasets, and transfer learning models attained an overall precision of 97.56% in classifying different disease stages. This study provides an effective approach for the early prediction of tomato gray mold, with potential application value in optimizing disease management strategies and reducing environmental impact.