It is of great significance to develop early prediction technology for controlling downy mildew and promoting cucumber production. In this study, a cucumber downy mildew prediction method was proposed by fusing quantitative disease information and environmental data. Firstly, the number of cucumber downy mildew spores during the experiment was collected by a portable spore catcher, and the proportion of cucumber downy mildew leaf area to all cucumber leaf area was recorded, which was used as the incidence degree of cucumber plants. The environmental data in the greenhouse were monitored and recorded by the weather station in the greenhouse. Environmental data outside the greenhouse were monitored and recorded by a weather station in front of the greenhouse. Then, the influencing factors of cucumber downy mildew were analyzed based on the Pearson correlation coefficient method. The influencing factors of the cucumber downy mildew early warning model in greenhouse were identified. Finally, the CNN-LSTM (Convolutional Neural Network-Long Short-Term Memory) algorithm was used to establish the cucumber downy mildew incidence prediction model. The results showed that the Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and determination coefficient (R²) of the CNN-LSTM network model were 0.069, 0.0098, 0.0991, and 0.9127, respectively. The maximum error between the predicted value and the true value for all test sets was 16.9398%. The minimum error between the predicted value and the true value for all test sets was 0.3413%. The average error between the predicted and true values for all test sets was 6.6478%. The Bland–Altman method was used to analyze the predicted and true values of the test set, and 95.65% of the test set data numbers were within the 95% consistency interval. This work can serve as a foundation for the creation of early prediction models of greenhouse crop airborne diseases.

The most significant aspect of promoting greenhouse productivity is the timely monitoring of disease spores and applying proactive control measures. This paper introduces a method to classify spores of airborne disease in greenhouse crops by using fingerprint characteristics of diffraction–polarized images and machine learning. Initially, a diffraction–polarization imaging system was established, and the diffraction fingerprint images of disease spores were taken in polarization directions of 0°, 45°, 90° and 135°. Subsequently, the diffraction–polarization images were processed, wherein the fingerprint features of the spore diffraction–polarization images were extracted. Finally, a support vector machine (SVM) classification algorithm was used to classify the disease spores. The study’s results indicate that the diffraction–polarization imaging system can capture images of disease spores. Different spores all have their own unique diffraction–polarization fingerprint characteristics. The identification rates of tomato gray mold spores, cucumber downy mold spores and cucumber powdery mildew spores were 96.02%, 94.94% and 96.57%, respectively. The average identification rate of spores was 95.85%. This study can provide a research basis for the identification and classification of disease spores.

Both abiotic and biological stresses reduce the quality and quantity of cultivated plants. In order to observe the response of cucumber plants to potassium stress and cucumber downy mildew infestation, two different levels of downy mildew infestation, B0 (disease infestation) and B1 (disease-free infestation), and three fertilizer requirement levels of potassium fertilization, T1 (K-50%), T2 (K-100%) and T3 (K-150%), were applied in the greenhouse. Results show that the photosynthetic rate and stomatal conductance of cucumber plants leaves treated with B1T2 had an increasing trend, and the increase in stomatal conductance was more significant. The intercellular CO₂ concentration of cucumber leaves treated with B1T2 showed no significant difference. The plant height of cucumbers treated with B0T1, B0T2, B0T3, B1T1 and B1T3 decreased by 32.21%, 16.93%, 21.59%, 53.54% and 6.31%, respectively, compared with that treated with B1T2. The leaf area of cucumbers treated with B0T1, B0T2, B0T3, B1T1 and B1T3 decreased by 27.85%, 15.97%, 21.47%, 7.29% and 18.5%, respectively, compared with that treated with B1T2. The stem diameter of cucumbers treated with B0T1, B0T2, B0T3 and B1T1 decreased by 13.43%, 8.72%, 6.01% and 7.06%, respectively, compared with that treated with B1T2. The stem diameter of cucumbers treated with B1T3 increased by 6.83% compared with that treated with B1T2. The root total length, root surface area, root average diameter, root total volume and total root tips of cucumber plants were significantly different under different experimental conditions (p < 0.05). This study provides a theoretical basis for cucumber stress resistance cultivation in greenhouses and has important practical significance to ensure the sustainable development of the greenhouse cucumber industry.

The aim of this study was to accurately meet the demand of real-time detection of seedling shortage in large-scale seedling production and solve the problems of low precision of traditional models and insufficient adaptability of mainstream lightweight models. This study proposed a Light-YOLO-Pepper seedling shortage detection model based on the improvement of YOLOv8n. This model was based on YOLOv8n. The SE (Squeeze-and-Excitation) attention module was introduced to dynamically suppress the interference of the nutrient soil background and enhance the features of the seedling shortage area. Depth-separable convolution (DSConv) was used to replace the traditional convolution, which can reduce computational redundancy while retaining core features. Based on K- means clustering, customized anchor boxes were generated to adapt to the hole sizes of 72-unit (large size) and 128-unit (small size and high-density) seedling trays. The results show that the overall mAP@0.5, accuracy and recall rate of Light-YOLO-Pepper model were 93.6 ± 0.5%, 94.6 ± 0.4% and 93.2 ± 0.6%, which were 3.3%, 3.1%, and 3.4% higher than YOLOv8n model, respectively. The parameter size of the Light-YOLO-Pepper model was only 1.82 M, the calculation cost was 3.2 G FLOPs, and the reasoning speeds with regard to the GPU and CPU were 168.4 FPS and 28.9 FPS, respectively. The Light-YOLO-Pepper model was superior to the mainstream model in terms of its lightweight and real-time performance. The precision difference between the two seedlings was only 1.2%, and the precision retention rate in high-density scenes was 98.73%. This model achieves the best balance of detection accuracy, lightweight performance, and scene adaptability, and can efficiently meet the needs of embedded equipment and real-time detection in large-scale seedling production, providing technical support for replanting automation.

Analyzing the transmission dynamics of airborne disease spores is crucial for advancing early warning and control strategies for crop diseases. This study introduces a novel approach utilizing the HYSPLIT-5 model to investigate the spore transmission patterns and pathways of airborne crop diseases. By employing the Lagrangian particle trajectory method of HYSPLIT-5 in conjunction with MeteInfoMap 3.5, the spatiotemporal frequency of cucumber downy mildew spore trajectories over extended periods was examined. The results indicate that the transmission trajectory of cucumber downy mildew spores is heavily influenced by atmospheric circulation, with spores spreading along air currents to surrounding areas. These trajectories frequently intersect, resulting in a broad transmission range, and the observed transmission patterns exhibit a degree of universality. Which provided a basis for the subsequent study of a large-scale prediction model of cucumber downy mildew.

In order to understand the effects of biotic stress and abiotic stress on hormone metabolism and substance accumulation in cucumber, two different infection levels of downy mildew were set, B0 (diseased) and B1 (disease-free), and T1 (K-50%: 50% of normal potassium application), T2 (K-100%: normal potassium application), and T3 (K-150%: 150% of normal potassium application). The results show that the hormone metabolism in the cucumber plants was measured on the 15th day after transplanting. Compared with the B1T2 treatment, the cane sugar contents in the B0T1, B0T2, B0T3, B1T1, and B1T3 treatments decreased by 35.87%, 23.29%, 25.41%, 12.98%, and 6.05%; the soluble sugar contents in the B0T1, B0T2, B0T3, B1T1, and B1T3 treatments decreased by 36.16%, 27.13%, 31.97%, 9.89%, and 7.84%; the hydrogen peroxide (H₂O₂) contents in the B0T1, B0T2, B0T3, and B1T1 treatments increased by 30.59%, 21.08%, 14.74%, and 9.2%; the catalase (CAT) contents in the B0T1, B0T2, B0T3, B1T1, and B1T3 treatments decreased by 53.78%, 36.57%, 47.18%, 34.75%, and 16.39%; the superoxide dismutase (SOD) contents in the B0T1, B0T2, B0T3, and B1T1 treatments increased by 30.28%, 22.59%, 12.9%, and 13.17%; and the polyphenol oxidase (PPO) contents in the B0T1, B0T2, B0T3, and B1T1 treatments increased by 39.38%, 25.27%, 4.49%, and 23.05%, respectively. Compared with the B1T2 treatment, the malondialdehyde (MDA) contents in the B0T1, B0T2, B0T3, B1T1, and B1T3 treatments increased by 82.78%, 23.07%, 60.21%, 74.55%, and 25.12%. Compared with the B1T2 treatment, the hydrogen peroxide (H₂O₂), superoxide dismutase (SOD), and polyphenol oxidase (PPO) contents in the B1T3 treatment decreased by 16.11%, 4.36%, and 4.43%. On the 20th day after transplanting the cucumber plants, downy mildew infection and potassium stress had significant effects on the dry and fresh weights of the leaves, stems, and roots (p < 0.05). The B0T1 treatment had the greatest effect on the dry and fresh weights of the leaves, stems, and roots of the cucumber plants. The B1T3 treatment had the least effect on the dry and fresh weights of the leaves, stems, and roots of the cucumber plants. This research can provide a theoretical basis for the study and cultivation of cucumber stress resistance.