Multi-scale space-time diagram convolution blue-green algae forecasting method and device based on hydrodynamic perception
By introducing a multi-scale spatiotemporal map convolution network of hydrodynamic perception in the prediction of cyanobacteria outbreaks, combining the spatial distance and hydrodynamic factors of water quality monitoring stations, the problem of low prediction accuracy in the existing technology is solved, and more efficient cyanobacteria is achieved forecast.
Patent Information
- Application Number
- CN202411489223.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-24
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-10-24
AI Technical Summary
The existing cyanobacteria outbreak prediction methods have low prediction accuracy under complex hydrodynamic conditions and fail to fully consider the spatial structure and hydrodynamic characteristics of the water system, resulting in insufficient prediction accuracy.
Using the multi-scale spatiotemporal graph convolution network (MS-STGCN) method based on hydrodynamic perception, a multi-scale spatiotemporal convolution network is constructed by obtaining the spatial distance and hydrodynamic factors between water quality monitoring stations, combining the graph diameter and average space The distance and degree matrix is characterized by enhanced to predict cyanobacteria outbreaks.
It significantly improves the accuracy of cyanobacteria forecasts, can more accurately capture complex space-time dependencies and water quality changes, and provides a more reliable scientific basis for water environment management.
