Abrupt changes in environmental temperature, wind and humidity can lead to great threats to human life safety. The Gansu marathon disaster of China highlights the importance of early warning of hypothermia from extremely low apparent temperature (AT). Here a deep convolutional neural network model together with a statistical downscaling framework is developed to forecast environmental factors for 1 to 12 h in advance to evaluate the effectiveness of deep learning for AT prediction at 1 km resolution. The experiments use data for temperature, wind speed and relative humidity in ERA-5 and the results show that the developed deep learning model can predict the upcoming extreme low temperature AT event in the Gansu marathon region several hours in advance with better accuracy than climatological and persistence forecasting methods. The hypothermia time estimated by the deep learning method with a heat loss model agrees well with the observed estimation at 3-hour lead. Therefore, the developed deep learning forecasting method is effective for short-term AT prediction and hypothermia warnings at local areas.

In order to explore the application of the new integrated intelligent spore capture system developed in China in the prediction of cucumber downy mildew and cucumber powdery mildew, the main working parameters of the integrated intelligent spore capture system, such as the presence or absence of air cutting head, the height of air collection port and the time of air collection, were optimized by identifying the morphology of captured spores in the case of natural disease in the field. The relationship between the disease index of cucumber downy mildew and cucumber powdery mildew in greenhouse and the amount of spores captured was analyzed through the dynamic monitoring of disease and spores. The results show that when the air cutting head is not installed, the height of the air collection port is 70 cm, and the period of 10: 00–10: 30 was beneficial to the capture of spores. The disease index of cucumber downy mildew and cucumber powdery mildew had a strong positive correlation with the total amount of spores captured for 7 consecutive days. Continuous monitoring of cucumber downy mildew sporangia and rapid increase in the number is a predictor of the occurrence or rapid increase of cucumber downy mildew. The conidia of cucumber powdery mildew were not detected before the disease onset, and the number of conidia captured was still small at the peak of the disease. The research shows that the integrated intelligent spore capture system is suitable for the prediction of cucumber downy mildew, but there are still some problems in the prediction of cucumber powdery mildew.