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

Marine sediment testing system and method based on deep learning

A marine sediment and testing system technology, applied in the field of marine water quality testing, can solve problems such as inaccurate analysis results

Active Publication Date: 2021-01-01
HUNAN GUOTIAN ELECTRONICS TECH CO LTD
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The data detected by the existing marine sediments are often analyzed and processed directly after the data are obtained by satellites, and the data obtained by satellites often have quite a lot of errors, which can easily lead to inaccurate final analysis results

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
  • Marine sediment testing system and method based on deep learning
  • Marine sediment testing system and method based on deep learning
  • Marine sediment testing system and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] Such as figure 1 As shown, a deep learning-based marine sediment testing system provided in this embodiment includes: a marine remote sensing satellite ground station, a remote remote sensing satellite, a feedback neural network connecting the marine remote sensing satellite ground station and a remote remote sensing satellite, and a running The radiative transfer and atmospheric correction module of the feedback neural network;

[0078] There are two groups of remote sensing satellites, namely the first remote sensing satellite and the second remote sensing satellite;

[0079] It is characterized in that the system also includes: the first long-range remote sensing satellite and the second long-range remote sensing satellite acquire the electromagnetic wave characteristic data information of the ocean, the electromagnetic wave characteristic data information is collected by the sensor, and the sensor sends the data information to the radiation of the operation feedback...

Embodiment 2

[0125] The feedback neural network includes: input unit, fuzzy unit, rule calculation unit and output unit; input unit: the number of input data information is n, the corresponding number of nodes is n, and the output of this unit is the value of input data information, that is, i=1 , 2,..., n, where: xi is the value of the i-th input data information; fuzzy unit: use the membership function to realize the fuzzy input data information, the node input is the output of the input unit, through the corresponding membership function Fuzzy the node input and take the product of these values ​​as the output of the node, the membership function is: in is the membership function of the i-th input sample parameter to the j-th neuron, is the mean value, is the reciprocal of the standard deviation parameter, n is the number of input vectors; rule calculation layer: each node represents a fuzzy rule, and the multiplication of membership degree is used as the fuzzy rule, through the...

Embodiment 3

[0127] On the basis of the previous embodiment, the first remote sensing satellite and the second remote sensing satellite acquire the electromagnetic wave characteristic data information of the ocean, and after sending them to the feedback neural network, the feedback neural network fuzzifies the received data information, Errors and missing values ​​are corrected.

[0128] Specifically, the deposition rate of marine sediments varies greatly in different parts of the seafloor. The inhomogeneity of deposition rate reflects the difference of depositional environment, which shows great difference in deposition type and deposition thickness. The main factors affecting the deposition rate are material source, climate, tectonic process and so on. In sea areas with sufficient material sources and abundant marine biological products, the sedimentation rate is high, and vice versa. Since periods of rapid deposition often alternate with periods of slow deposition, no deposition or er...

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 belongs to the technical field of marine water quality testing, and particularly relates to a marine sediment testing system and method based on deep learning. The marine sediment testing system comprises an ocean remote sensing satellite ground station, remote sensing satellites and a feedback neural network connecting the ocean remote sensing satellite ground station and the remotesensing satellites, wherein the two groups of remote sensing satellites are respectively a first remote sensing satellite and a second remote sensing satellite. The marine sediment testing system ischaracterized in that: the first remote sensing satellite and the second remote sensing satellite acquire ocean electromagnetic wave characteristic data information and send the data information to the feedback neural network; and the feedback neural network performs feedback correction on the received data information, corrects data information errors, and sends the corrected information errors to a remote sensing satellite ground station. The marine sediment testing system has the advantages of high intelligent degree and high accuracy degree.

Description

technical field [0001] The invention belongs to the technical field of marine water quality testing, and in particular relates to a deep learning-based marine sediment testing system and method. Background technique [0002] From 1872 to 1876, the expedition of the British "Challenger" opened the prelude to the investigation and research of marine sediments, especially the classification of deep-sea sediments is still of great significance today. From 1899 to 1900, the survey conducted by the Dutch ship "Siboga" also achieved important results in the distribution and composition of sediments. [0003] After the Second World War, with the needs of the military and the exploration and development of mineral resources such as seabed oil, the study of marine sediments has made great progress. People began to carry out special surveys and studies on specific sea areas and major theoretical topics. In the late 1940s, monographs on marine geology by F.P. Sheppard and M.B. Klenova...

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 Applications(China)
IPC IPC(8): G06F16/215G06F16/2458G06N3/08G01N33/18
CPCG01N33/18G06N3/084G06F16/215G06F16/2458
Inventor 江峦陈路尤蓉蓉肖志伟吕冰冰
Owner HUNAN GUOTIAN ELECTRONICS TECH CO LTD
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