Rice borer peak period detection method based on intelligent forecasting lamp data

Abstract

The application discloses a rice borer peak period detection method based on intelligent forecasting lamp data, comprising the following steps: step 1, pest monitoring time series data acquisition and pretreatment; step 2, abnormal trapping data identification and repair based on the working condition characteristics of the insect trapping device; step 3, multi-peak Gaussian model construction; step 4, model adaptive optimal parameter selection and peak period detection; step 5, peak value merging and ecological generation division; step 6, peak period information extraction and prevention window output. The application utilizes the overall trend and peak value characteristics of the time series curve, can effectively reduce local interference, and improve the accuracy and stability of moth peak identification; and can simultaneously extract multiple moth peak characteristics of multiple sites and multiple years in a region, does not need to separately set a measurement standard for different scenes, and can be applied to large-scale Chilo suppressalis population dynamic monitoring.

Images