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 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.