A Distributed Water Depth Prediction Method Based on GWR and BP Neural Network

A BP neural network and neural network technology, applied in the field of distributed water depth prediction based on GWR and BP neural network, can solve problems such as unsatisfactory water depth accuracy, unbalanced water quality, and no consideration of spatial diversity and geographical location changes.

Inactive Publication Date: 2017-01-18
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the real marine environment is very complex, there may be various situations such as unbalanced water quality, inconsistent seabed materials, turbid water, and spatial diversity. Considering the influence of spatial diversity and geographic location changes, spatial non-stationarity cannot be eliminated, making the depth accuracy of the inversion not ideal

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 Distributed Water Depth Prediction Method Based on GWR and BP Neural Network
  • A Distributed Water Depth Prediction Method Based on GWR and BP Neural Network
  • A Distributed Water Depth Prediction Method Based on GWR and BP Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0053] For the convenience of description, the relevant technical terms appearing in the specific implementation are explained first:

[0054] GWR (Geographically weighted regression): Geographically weighted regression;

[0055] BP(Back Propagation): Backpropagation;

[0056] LoG(Laplace of Gaussian function): Gaussian-Laplace operator;

[0057] DN (Digital Number) value: the brightness value of the remote sensing image pixel;

[0058] ROI (region of interest): the area of ​​interest;

[0059] CCRS (Canada Center for Remote Sensing): Canadian Center for Remote Sensing;

[0060] figure 1 It is a flowchart of the distributed water depth prediction method based on GWR and BP neural network in the present invention.

[0061] In this example, if figure 1 Shown, a kind of distributed water depth prediction method based on GWR and BP neural network of the present invention comprises the following steps:

[0062] S1. Preprocessing remote sensing images

[0063] S1.1), perform...

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 distributed water depth prediction method based on GWR and BP neural network. First, the remote sensing image is preprocessed, and then the measured water depth value collected by the laser radar and the blue and green band DN of the corresponding coordinate point in the remote sensing image are combined. value, establish sampling data, and then divide the area to be predicted into multiple sub-areas based on the GWR method, and establish a neural network water depth prediction model for each sub-area. Finally, by designing all the regional neural networks around each point to be predicted in the area to be predicted The weighting factor of the water depth prediction model establishes a distributed neural network water depth prediction model for the entire area to be predicted. In this way, the present invention will not be affected by seawater quality, seabed type, and spatial diversity, and can quickly and conveniently establish a nonlinear relationship between multispectral remote sensing images and actual water depth values, and has good practical value for shallow sea depth prediction.

Description

technical field [0001] The invention belongs to the technical field of shallow water depth remote sensing detection, and more specifically relates to a distributed water depth prediction method based on GWR and BP neural network. Background technique [0002] Bathymetry is an essential work in water conservancy, shipping, offshore engineering, water resource utilization, tidal flat development, etc. The traditional bathymetry method is to use the bathymetry equipment installed on the survey ship to measure the water depth of each point in the whole water area, and then calculate and draw the map according to the drawing requirements, so as to obtain the underwater topographic map of the measured water area. Due to the wide coverage of water depth information collection, the harsh environmental conditions in some areas, and the difficulty for sounding personnel to set foot in, there are many practical difficulties in this traditional sounding method. [0003] With the rapid ...

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): G01C13/00G06N3/02
CPCG01C13/008G06N3/084
Inventor 刘珊王磊高勇郑文锋杨波林鹏李晓璐
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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