Constructing method of combined air quality forecasting model
A forecasting model and air quality technology, applied in neural learning methods, biological neural network models, forecasting, etc., can solve problems such as insensitivity to extreme value performance, large forecast errors during periods of high-concentration pollution, and unsatisfactory forecasting results
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0078] Example: PM in a place from May 2011 to April 2012 10 Daily mean concentration forecast
[0079] Prepare training sample data: PM of a certain environmental automatic monitoring station from January 1, 2008 to April 30, 2012 10 Concentration data and weather monitoring and weather forecast data.
[0080] (1) Based on the training sample set, establish a BP neural network prediction model;
[0081] (11) Input layer neuron determination
[0082] The factors with greater comprehensive influence weight are selected as the neurons in the input layer of the respective neural network. Determine the input parameters of the PM10 daily average forecast model as: today's wind W p , Today's Rain RF p , Yesterday's rain RF p-1 , Yesterday air pressure AP p-1 , Yesterday relative humidity RH p-1 , Atmospheric stability level AS at 18:00 yesterday p-1 , Background density of yesterday, background density of the day before yesterday.
[0083] (12) The hidden layer neuron determination is based ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap