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

Brain-like cross-modal identification and parallel processing method of pollution precursor emission source for remote sensing space-time big data

A cross-modal, big data technology, applied in the field of atmospheric remote sensing and environmental pollution, can solve problems such as low recognition efficiency

Pending Publication Date: 2021-01-15
HENAN UNIVERSITY
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional methods generally use quantum behavior particle swarm optimization algorithm (Tian Na et al. Application of quantum particle swarm with disturbance operator in water pollution source identification. Journal of System Simulation. 2015), firefly swarm algorithm (Chen et al. A New Air Pollution Source Identification Method Based on RemotelySensed Aerosol and Improved Glowworm Swarm Optimization.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.2017), and inversion and numerical simulation (Yifan Yang et al. Numerical simulation of the inversion problem of location identification of sudden air pollution sources .Environmental Science Journal.2013) and other methods, the recognition efficiency is relatively low

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
  • Brain-like cross-modal identification and parallel processing method of pollution precursor emission source for remote sensing space-time big data
  • Brain-like cross-modal identification and parallel processing method of pollution precursor emission source for remote sensing space-time big data
  • Brain-like cross-modal identification and parallel processing method of pollution precursor emission source for remote sensing space-time big data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0141] As shown in the figure, the embodiment of the present invention provides another brain-inspired cross-modal identification method for emission sources of pollution precursors oriented to remote sensing spatiotemporal big data, including the following steps:

[0142] S21. Target positioning for ESPP

[0143] According to the BRD and DOAS algorithms, the atmospheric satellite monitoring data of the two time phases are inverted, and the PM in the observation area under the two time phases is calculated 2.5 Concentration distribution chart VCD PM and Concentration Profile VCD of Contamination Precursors HP . In the range of threshold δ and γ, locate the high concentration area of ​​precursor HCD HP and PM 2.5 VCD in high concentration area PM :

[0144]

[0145] Among them, S is the spatial region and T is the time interval; through this step, it can be known that for a possible ESPP, it must be located in the space-time range HCD HP Pollutant emissions have occur...

Embodiment 3

[0158] Considering the timeliness of atmospheric environment monitoring, in the embodiment of the present invention, a hybrid heterogeneous parallel strategy is adopted to increase the speed of the BCR algorithm of ESPP and realize the application of remote sensing BCR with high recognition rate and fast speed. Such as Figure 6 As shown, the specific ideas of parallel BCR research are as follows:

[0159] S31. Task decomposition for ESPP parallel recognition

[0160] Since the remote sensing image BCR task has decomposability and data tensor structure, the preprocessed remote sensing image is used to construct a multi-resolution pyramid. Among them, low-resolution images are used for pollution source location, and high-resolution images are used for pollution source identification and verification. Slice the image layer by layer to form a data block D k . According to the nature of the task, the BCR task can be decomposed into M workflows, and each workflow consists of N ...

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 brain-like cross-modal identification and parallel processing method of a pollution precursor emission source (ESPP) for remote sensing space-time big data. The method specifically comprises the following steps: respectively inverting the tropospheric column concentrations of atmospheric pollution trace gases such as NO2, O3, SO2 and NH3 based on satellite remote sensing inversion, and calculating the PM2.5 concentration near the ground; training based on brain heuristic calculation according to the satellite remote sensing inversion result, the hyperspectral image, the synthetic aperture radar image and the target semantic tag Cp of the ESPP, and establishing an ESPP-oriented cross-modal neural cognitive calculation model; and extracting cross-modal, multi-level and multi-scale ESPP features in the remote sensing space-time big data based on deep learning. the invention discloses an object-oriented remote sensing cross-modal ESPP representation and reasoning method based on a probability cognition framework. Multi-scale topic clustering, cross-modal ESPP cognition processing and incremental learning of ESPP recognition are carried out on ESPP features. According to the invention, ESPP identification based on brain-like computing can be effectively realized, and a systematic solution is provided for atmospheric pollution tracing.

Description

technical field [0001] The invention relates to the fields of atmospheric remote sensing and environmental pollution, in particular to a brain-inspired cross-modal identification method and a parallel processing method for pollution precursor emission sources of remote sensing spatiotemporal big data. Background technique [0002] A good atmospheric environment is the natural environment basis for economic development. However, with my country's industrialization and urbanization, as well as the rapid development of agriculture and aquaculture, air pollution weather such as sandstorms and smog occurs frequently on a large scale around the world, seriously affecting human health and the ecological balance of the earth. The main cause of air pollution such as smog is the emission of sulfur dioxide (SO 2 ), nitrogen oxides (NO x ) (mainly including nitric oxide NO and nitrogen dioxide NO 2 ), ammonia (NH 3 ), ozone (O 3 ) and volatile organic compounds (VOC s ) and other ...

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): G06F30/27G06N3/04G06N3/08G06K9/00G06K9/62
CPCG06F30/27G06N3/08G06V20/13G06N3/045G06F18/241Y02A90/10
Inventor 刘扬蔡坤李莘莘田猛赵金环孟伟曹珂境王瑞毅
Owner HENAN UNIVERSITY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com