Time-space domain model modeling method and system for ecological environment monitoring

A technology for environmental monitoring and model modeling, applied in character and pattern recognition, instrumentation, computing, etc., can solve problems such as inability to become, discrete and sparse ecological environment monitoring data, and achieve good classification results.

Pending Publication Date: 2020-03-27
谢国宇 +1
View PDF16 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the defects in the prior art, the present invention provides a time-space domain model and modeling method for ecological environment monitoring, through which the monitoring data is converted into orderly and dense data, which can be provided to dee

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
  • Time-space domain model modeling method and system for ecological environment monitoring
  • Time-space domain model modeling method and system for ecological environment monitoring

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0033] Example 1

[0034] Such as figure 1 As shown, the present invention provides a spatio-temporal model modeling method for ecological environment monitoring, including the following steps:

[0035] S1. Collect pollutant data regularly to obtain multiple data frames;

[0036] S2. In chronological order, multiple data frames are superimposed using spatial superposition to obtain a data structure in the space-time domain;

[0037] S3. Use the change of the spatio-temporal domain data as the feature quantity to perform feature extraction on the spatiotemporal data structure to obtain a data structure without null values;

[0038] S4. Use the data dimensionality reduction method to reduce the data structure of the data structure without null values ​​to obtain the spatio-temporal domain model;

[0039] S5. Input the sparse monitoring data into the spatio-temporal domain model, and convert the monitoring data into dense data through the spatio-temporal domain model as input for deep learn...

Example Embodiment

[0059] Example 2

[0060] In the data dimensionality reduction processing of the PCA algorithm, the effect of classification is not obvious, which is not particularly ideal for constructing the input of deep learning. Because deep learning data needs to be divided into training set and validation set.

[0061] In order to solve the above technical problems, the Laplacian feature mapping algorithm is used in data dimensionality reduction.

[0062] The working principle is explained below: Laplace algorithm uses the local angle of the data vector to construct the relationship between the data. If the two data frames are very similar, they should be as close as possible in the target subspace after dimensionality reduction. The specific steps of the algorithm when used are: first use the KNN algorithm to construct all the points into a graph, and connect each point with the nearest K points. In this embodiment, the requirement is to reduce the dimensionality of the data from 4 dimensi...

Example Embodiment

[0063] Example 3

[0064] The present invention also provides a spatio-temporal model modeling system for ecological environment monitoring, such as figure 2 As shown, it includes: a data input unit, a data superposition unit, a data feature extraction unit, and a data dimensionality reduction processing unit;

[0065] The data input unit is used to input multiple data frames obtained based on the collected pollutant information;

[0066] The data superimposition unit is used to superimpose multiple data frames in a spatial superposition method to obtain a data structure in the spatio-temporal domain;

[0067] The data feature extraction unit is used to perform feature extraction on the spatiotemporal data structure using the change of the spatiotemporal data as the feature quantity to obtain a data structure without null values;

[0068] The data dimensionality reduction processing unit is used to perform dimensionality reduction processing on data structures that do not contain null...

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 provides a time-space domain model modeling method for ecological environment monitoring, and the method comprises the following steps: S1, collecting pollutant data at regular time, andobtaining a plurality of data frames; S2, superposing the plurality of data frames in a spatial superposition mode according to a time sequence to obtain a time-space domain data structure; S3, performing feature extraction on the time-space domain data structure by taking the change of the time-space domain data as a feature quantity to obtain a data structure without a null value; S4, performing dimension reduction processing on the data structure without the null value by using a data dimension reduction method to obtain a time-space domain model; and S5, inputting the sparse monitoring data into the time-space domain model, and converting the sparse monitoring data into dense data as input of deep learning training. The invention further provides a time-space domain model modeling system for ecological environment monitoring. The time-space domain model modeling system comprises a data input unit, a data superposition unit, a data feature extraction unit and a data dimension reduction processing unit.

Description

technical field [0001] The invention relates to a data processing method and a data processing system for prediction purposes, in particular to a time-space domain model modeling method and system for ecological environment monitoring. Background technique [0002] By monitoring the ecological environment, a series of monitoring data can be obtained, which can be used for analysis, prediction and governance of environmental protection. At present, for the ecological environment monitoring data in the field of environmental protection, deep learning methods have been used to analyze the data, but deep learning needs big data as support, and its training model is difficult to converge when encountering sparse data. In the field of environmental protection, a considerable part of the monitoring data on the ecological environment is discrete and sparse; for example, for air pollutants, they may appear randomly, and may disappear soon after they appear. In this way, these discre...

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
IPC IPC(8): G06K9/62
CPCG06F18/2136G06F18/2135G06F18/214G06F18/24
Inventor 谢国锦谢国宇刘仲阳
Owner 谢国宇
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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