Occurrence prediction of pests and diseases in cotton on the basis of weather factors by long short term memory network

摘要

Cotton is an important economic crop, which occupies a important position in the national economy. However, cotton was always damaged by various pests and diseases during its growth. Perennial pests and diseases can cause about 15–20% economic loss, even up to 50% in some years. Therefore, the control of pests and diseases is crucial to the growth of cotton, which can recover more than 900,000 tons of cotton annually [ ]. During cotton growth, many factors can affect the production, of which the most significant one is abnormal climate change. Abnormal climate change can result in the continuous evolution of pests and further make pests adaptive to the environment, which seriously influences the yield and quality and makes it more difficult to control the pests and diseases [ ]. Investigating the relationship between pandemic diseases and weather factors is significant for establishing weather-pest forecasting models and improving the long-term prediction of pests and diseases.