Kaige Liu

Cucumber downy mildew, caused by the obligate parasitic oomycete Pseudoperonospora cubensis [(Berkeley & M. A. Curtis) Rostovzev], is a major threat to global cucumber production. Effective disease management relies on rapid and accurate pathogen detection. However, due to the specialized parasitic nature of P. cubensis, conventional methods are often laborious, low-throughput and inadequate, necessitating the development of a new approach for high-throughput sporangia counting. To address this limitation, we developed a rapid, high-throughput flow cytometry (FCM) assay for the direct quantification of P. cubensis sporangia. The optimal staining protocol involved adding 30 µL of 1000× diluted SYBR Green I to 500 µL of sporangial suspension and incubating at room temperature for 20 min. The flow cytometry parameters were set to a high sample loading speed with a 30-s acquisition time. Instrumental settings included an FL1 (green fluorescence) threshold of 8 × 10⁴ and an SSC (side scatter) threshold of 3 × 10⁵, with low gain. Validation against hemocytometer counts revealed a strong positive correlation (r = 0.8352). The assay demonstrated high reproducibility, with relative standard deviations (RSDs) ranging from 1.96–9.84%, and a detection limit of 1–10 sporangia/µL. Operator-dependent variability ranged from 8.85% to 18.79%. These results confirm that the established flow cytometry assay is a reliable and efficient tool for P. cubensis quantification, offering considerable potential for improving cucumber downy mildew monitoring and control strategies.

This study addresses the limitations of current non-destructive techniques for assessing tomato quality, such as their high cost, strong dependence on spectroscopic instruments, and difficulty in dynamic monitoring. The study proposes an integrated tomato quality prediction model that combines a Long Short-Term Memory (LSTM)-based environmental predictor, a Gated Recurrent Unit with attention mechanism (GRU-AT) for dynamic maturity prediction, and a Deep Neural Network (DNN)-based quality evaluation module. The LSTM model demonstrated high accuracy in environmental prediction (R² > 0.9559). The GRU-AT model excelled in color ratio prediction (R² > 0.86), and the DNN model achieved R² values exceeding 0.811 for lycopene (LYC), firmness (FI), and soluble solids content (SSC). Experimental results demonstrate that this approach can accurately predict multiple quality parameters using only standard RGB images. In summary, this study provides a low-cost, low-complexity solution enabling real-time, non-destructive monitoring of greenhouse tomato quality, offering a viable pathway for crop quality management in precision agriculture.

Facility agriculture cultivation is the main production form of the vegetable industry in the world. As an important vegetable crop, hot peppers are easily threatened by many diseases in a facility microclimate environment. Traditional disease detection methods are time-consuming and allow the disease to proliferate, so timely detection and inhibition of disease development have become the focus of global agricultural practice. This article proposed a generalizable and explainable machine learning model for hot pepper damping-off in intensive seedling production under the condition of ensuring the high accuracy of the model. Through Kalman filter smoothing, SMOTE-ENN unbalanced sample processing, feature selection and other data preprocessing methods, 19 baseline models were developed for prediction in this article. After statistical testing of the results, Bayesian Optimization algorithm was used to perform hyperparameter tuning for the best five models with performance, and the Extreme Random Trees model (ET) most suitable for this research scenario was determined. The F₁-score of this model is 0.9734, and the AUC value is 0.9969 for predicting the severity of hot pepper damping-off, and the explainable analysis is carried out by SHAP (SHapley Additive exPlanations). According to the results, the hierarchical management strategies under different severities are interpreted. Combined with the front-end visualization interface deployed by the model, it is helpful for farmers to know the development trend of the disease in advance and accurately regulate the environmental factors of seedling raising, and this is of great significance for disease prevention and control and to reduce the impact of diseases on hot pepper growth and development.

This paper experimented with a methodology of machine learning modelling using virtual samples generated by fast CFD (Computational Fluid Dynamics) simulations in order to predict the greenhouse natural ventilation. However, the output natural ventilation rates using fast two-dimensional (2D) CFD models are not always consistent with the three-dimensional (3D) one for all the scenarios. The first contribution of this paper is a proposed comparative modelling methodology between two-dimensional and three-dimensional CFD studies, regarding its validity, especially when buildings are in rows. The results show that the error of the ventilation rate prediction could exceed 50%, if 2D models are not properly used. Subsequently, in those scenarios where the 2D and the 3D models had equal accuracy, nearly one thousand samples were generated using fast 2D CFD simulations to train a natural ventilation rate regression tree model. This model is efficient to deal with the combined effect of wind pressure and thermal gradients under various vent configurations, with only four necessary inputs. In addition, by analyzing the wind speed distribution contour of the outdoor wind field around the greenhouse rows, the optimal wind speed-measuring locations were determined to eliminate interference for predicting the natural ventilation rate.

Rational irrigation and nitrogen management strategies are crucial for wheat growth. However, the optimal amount of water and nitrogen for the newly developed drip irrigated spring wheat system (TR6S, one drip tube service for six rows of wheat, with a row spacing of 10 cm and an inter-block space of 25 cm, saves drip tubes and obtains higher profits) in dry and semi-arid areas remains unclear. Therefore, a field experiment was conducted with four nitrogen levels (300, 270, 240, and 0 kg ha⁻¹ referred N300, N270, N240, and N0) and four irrigation levels (4500, 4200, 3900, and 3600 m³ ha⁻¹ referred I4500, I4200, I3900, and I3600) during the 2021–2022 and 2022–2023 spring wheat seasons to analyze the effects of irrigation (I) and nitrogen (N) levels on grain yield, water-nitrogen use efficiency, profit, biomass accumulation, and nitrogen nutrient absorption status under TR6S. Compared with the traditional irrigation and nitrogen management strategy (N300–I4500, as control), lesser irrigation and nitrogen supply (I3 ha⁻¹ and NI>3979 m³ ha⁻¹ and 300 kg ha⁻¹ >N>273 kg ha⁻¹) improved grain yield, WUE, AEN, and profit. The increase in grain yield was mainly related to the rise in 1000-grain weight and kernels per spike. Although the moderate reduction in irrigation lowered soil moisture status, the dry matter pre-stored in the vegetative organs before anthesis that gets redistributed into grains during grain filling was improved. Moreover, the moderate reduction in nitrogen supply resulted in a more reasonable nitrogen nutrition index (NNI) of wheat plant, which improved flag leaf area and chlorophyll relative content (SPAD) at the anthesis stage. This also played a positive role in biomass accumulation and redistributed, yield structure optimization. Considering comprehensively yield, WUE, AEN and profit, combination of 285 kg ha⁻¹ N and 4170 m³ ha⁻¹ I was optimal irrigation and nitrogen application pattern for TR6S. This strategy can be applied to other arid and semi-arid regions.

Timely and accurate judgment of the nitrogen nutritional status of crops is the key to develop an optimal nitrogen application strategy. However, the evaluation criteria of nitrogen nutrition and nitrogen application strategies at each growth stage of wheat are not clear for the new type of drip-irrigated spring wheat system, TR6S (where one drip tube serves six rows of wheat, with a row spacing (RS) of 10 cm, inter-block space (IBS) of 25 cm and the lateral spacing (LS) of 80 cm, which achieved a lower drip-tube input and higher profit compared with the traditional planting system in Xinjiang). Therefore, we studied the recommendation mechanism of nitrogen fertilizer in different growth stages of wheat based on the critical SPAD values of leaves under TR6S. We set four nitrogen treatments (N1 (300 kg ha⁻¹), N2 (270 kg ha⁻¹), N3 (240 kg ha⁻¹) and N4 (0 kg ha⁻¹)) during two spring wheat growth seasons. The results revealed that the correlation coefficient (r²) between SPAD (soil plant analysis development) value and plant nitrogen content in the middle of first top leaf (L1-M) of wheat was higher than that in other leaf types and leaf positions under TR6S. A quadratic function relationship existed between a SPAD value of L1-M and grain yield. The critical SPAD values at the jointing, booting, anthesis, early milk, and late milk stages were 37.34, 39.40, 42.25, 45.57, and 35.91, respectively. In addition, through the establishment of the nitrogen application recommendation model for various wheat growth stages based on the critical SPAD value, the recommended optimal nitrogen application rates at jointing, booting, anthesis, early milk, and late milk stages were observed to be 69.4, 80.0, 90.8, 44.0, and 6.0 kg ha⁻¹, respectively. This recommended nitrogen application strategy exhibited a better parallel relationship with the nitrogen nutrition index (NNI) of each growth period than the conventional nitrogen application strategy. Therefore, it was more in line with the actual absorption and utilization of nitrogen in wheat of TR6S. In conclusion, the SPAD values of L1-M could be relatively more accurate to evaluate the nitrogen nutrition status of wheat. Compared to traditional nitrogen application strategy, reducing and delaying nitrogen application, recommended based on the leaf SPAD model, was more suitable for nitrogen utilization under TR6S. The results can be applied in other arid and semiarid regions.