Grapevine white rot, caused by Coniella diplodiella, can severely damage berries during ripening. The effects of temperature and wetness duration on the infection severity of C. diplodiella were investigated by artificially inoculating grape berries through via infection pathways (uninjured and injured berries, and through pedicels). The effect of temperature on incubation was also studied, as was that of inoculum dose. Injured berries were affected sooner than uninjured berries, even though 100% of the berries inoculated with C. diplodiella conidia became rotted whether injured or not; infection through pedicels was less severe. On injured berries, the disease increased as the inoculum dose increased. Irrespective of the infection pathway, 1 h of wetness was sufficient to cause infection at any temperature tested (10–35 °C); with the optimal temperature being 23.8 °C. The length of incubation was shorter for injured berries than for uninjured ones, and was shorter at 25–35 °C than at lower temperatures; the shortest incubation period was 14 h for injured berries at 30 °C. Mathematical equations were developed that fit the data, with R² = 0.93 for infection through any infection pathway, and R² = 0.98 for incubation on injured berries, which could be used to predict infection period and, therefore, to schedule fungicide applications.

Ripe rot caused by Colletotrichum spp. is a serious threat in many vineyards, and its control relies mainly on the repeated use of fungicides. A mechanistic, dynamic model for the prediction of grape ripe rot epidemics was developed by using information and data from a systematic literature review. The model accounts for (i) the production and maturation of the primary inoculum; (ii) the infection caused by the primary inoculum; (iii) the production of a secondary inoculum; and (iv) the infection caused by the secondary inoculum. The model was validated in 19 epidemics (vineyard × year combinations) between 1980 and 2014 in China, Japan, and the USA. The observed disease incidence was correlated with the number of infection events predicted by the model and their severity (ρ = 0.878 and 0.533, respectively, n = 37, p ≤ 0.001). The model also accurately predicted the disease severity progress during the season, with a concordance correlation coefficient of 0.975 between the observed and predicted data. Overall, the model provided an accurate description of the grape ripe rot system, as well as reliable predictions of infection events and of disease progress during the season. The model increases our understanding of ripe rot epidemics in vineyards and will help guide disease control. By using the model, growers can schedule fungicides based on the risk of infection rather than on a seasonal spray calendar.

The occurrence of cucumber downy mildew in solar greenhouses directly affects the yield and quality of cucumber. Chemical control methods may cause excessive pesticide residues, endanger food quality and safety, pollute the ecological environment, etc. Therefore, it is very important to predict the disease before its occurrence. To provide farmers with better and effective guidance for the prevention and control work, minimize the loss of disease damage, this article took cucumber ‘Lyujingling No. 2′ as the experimental material and acquired greenhouse environmental factors data by wireless sensors, including Temp (Temperature), RH (Relative Humidity), ST (Soil Temperature) and SR (Solar Radiation). LSTM (Long Short-Term Memory) neural network structure was constructed based on Keras deep learning framework to develop a prediction model with time-series environmental factors. Combined with the occurrence of downy mildew from manual investigation and statistics, through debugging the parameters, this article developed an occurrence prediction model for cucumber downy mildew and compared it with KNN (K-Nearest Neighbors Classification) and ANN (Artificial Neural Network). In the prediction model, the forecasted results of the four environmental factors were consistent with the true value distributions, and R² (R-Squared) were all above 0.95. Among them, the ST variable predicted the best results, e.g., R² = 0.9982, RMSE (Root Mean Square Error) = 0.08 °C, and MAE (Mean Absolute Error) = 0.05 °C. In the disease occurrence prediction model, the training accuracy was 95.99%, the Loss value was 0.0159, the disease occurrence prediction Accuracy was 90%, Precision was 94%, Recall was 89%, F₁-score was 91%, the AUC (Area Under Curve) value was 90.15%, and Kappa coefficient was 0.80. It also had obvious advantages over other different models. In summary, the model had a high classification accuracy and performance, and it can provide a reference for the occurrence prediction of cucumber downy mildew in actual production.