Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for extracting multi-source live spatio-temporal predictors and incorporating them into model interpretation

A predictor and model interpretation technology, which is applied in data processing applications, prediction, calculation, etc., can solve problems such as limited impact of decision-making, inconsistent forecast errors, and limited results

Active Publication Date: 2021-06-25
NATIONAL METEOROLOGICAL CENTRE
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are also individual studies that try to use the actual information of points around the forecast site as a predictor into the modeling process (Sebastian Trepte et al., 2018), but since the selected site is the actual value of a nearby station at a moment before the start of the forecast, the actual value The time and the close distance to the forecast site determine that the impact of the actual situation on the timeliness of the future forecast must be very limited; there are also live data as the source of real-time rolling corrections to the forecast, using the latest live data of the forecast site and the error of the previous forecast to achieve The time-weighted correction of the later aging, but because the interpretation and application forecast models of different forecasting aging are established separately, they are different, and the daily changes of the forecast elements and their error characteristics cause the inconsistency of the forecast error between different forecasting aging, so The effect is also very limited

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for extracting multi-source live spatio-temporal predictors and incorporating them into model interpretation
  • A method for extracting multi-source live spatio-temporal predictors and incorporating them into model interpretation
  • A method for extracting multi-source live spatio-temporal predictors and incorporating them into model interpretation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. The method of the present invention includes the following steps, such as figure 2 Shown:

[0060] Step 1. Select the source of live spatio-temporal predictor information

[0061] When the variables of the forecast elements are determined, according to the attributes of the forecast elements, synoptic principles, and forecast experience, analyze the type of observation information that has the most forecasting significance for the forecast elements, and combine the availability and reliability of the actual information sources to consider whether the observation data are The timely delivery of each observation time, the accuracy of the observation data, and whether there is a long enough historical archive data are used to select and determine the information source of the real-time spatiotemporal predictors, so that they can be extracted as predictors ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for extracting multi-source real-time space-time forecast factors and incorporating them into model interpretation applications; the calculation method, technical process and software system of multi-source real-time space-time forecast factors of the present invention are used as a part of the model interpretation application and post-processing process A separate live forecast factor preprocessing module extracts and prepares real-time space-time forecast factors with synoptic forecast indication significance; multi-source live space forecast factors with hourly or even minute-level rolling updates are added to the forecast factors, which makes up for the global numerical forecast. Due to the low frequency of model forecasts and the inability to achieve high-frequency rolling objective weather forecasts, it provides an effective technical means to support rolling forecasts relying on live updates. According to the balance between actual forecast demand and operational efficiency, an objective weather forecast system based on high-frequency updates of real-time spatial forecast factors can be developed, and hourly or even minute-level rolling updates can be carried out, and the accuracy of high-frequency rolling fine meteorological element forecasts can be further significantly improved.

Description

technical field [0001] The invention belongs to the technical field of weather forecasting, and in particular relates to a method for extracting multi-source real-time space-time forecasting factors and incorporating them into model interpretation applications. Background technique [0002] At present, meteorological services are developing in the direction of refined and seamless smart grid weather forecasting. The so-called intelligence focuses on exploiting the extreme capabilities of objective weather forecasting. Objective weather forecasting, that is, relying entirely on objective technical methods to generate forecasts of weather elements such as temperature, precipitation, wind, humidity, cloud cover, sky conditions, and weather phenomena, without manual intervention by forecasters. Reliable, precise, and rich multi-source real-time data, as well as the rapid development of numerical forecasting models, provide prerequisites and strong support for refined objective w...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/04
CPCG06Q10/04
Inventor 赵瑞霞张宏薛峰张志刚赵晓宇何文英胡争光
Owner NATIONAL METEOROLOGICAL CENTRE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products