CN113673155A - Water area sand content inversion method based on support vector machine - Google Patents
Water area sand content inversion method based on support vector machine Download PDFInfo
- Publication number
- CN113673155A CN113673155A CN202110944949.7A CN202110944949A CN113673155A CN 113673155 A CN113673155 A CN 113673155A CN 202110944949 A CN202110944949 A CN 202110944949A CN 113673155 A CN113673155 A CN 113673155A
- Authority
- CN
- China
- Prior art keywords
- sand content
- model
- scale
- sand
- different depths
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000004576 sand Substances 0.000 title claims abstract description 59
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 19
- 101100041681 Takifugu rubripes sand gene Proteins 0.000 claims abstract description 58
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 238000005259 measurement Methods 0.000 claims abstract description 8
- 238000012216 screening Methods 0.000 claims abstract description 8
- 238000007689 inspection Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 230000001360 synchronised effect Effects 0.000 abstract description 2
- 239000013049 sediment Substances 0.000 description 5
- 238000011835 investigation Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Dispersion Chemistry (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a water area sand content inversion method based on a support vector machine, which belongs to the field of geographic information technology and water environment monitoring, and comprises the specific operation steps of firstly screening sensitive wave bands with different levels of sand content by utilizing a data set formed by measured data and multispectral remote sensing data; then, taking the point scale as a training scale and a testing scale, selecting the optimal parameters by using the training data, and outputting the optimal model inverted by the sand contents at different depths by using the testing data set; and then upscaling the inverse prediction model of the sand content at different depths, of which the point scale is higher than the threshold value, to the scale of the whole water area, and calculating the spatial distribution of the sand content at different depths of the whole water area. The invention is not limited by the environment of on-site monitoring, solves the limitation of manual point scale measurement, and can realize the inversion of the sand content of the upper layer of the water area in a large-area synchronous and remote manner.
Description
Technical Field
The invention belongs to the field of geographic information technology and water environment monitoring, and particularly relates to a water area sand content inversion method based on a support vector machine.
Background
The content of suspended sediment in the water body directly influences the optical properties of the water body, such as transparency, turbidity, water color and the like, and also influences the ecological conditions of the water body and the erosion and deposition change process of a channel. Therefore, the method has qualitative and quantitative knowledge on the suspended sand content of the water area at the Yangtze river mouth, and has important significance on the safe operation of the Yangtze river channel and the construction of coastal zone engineering. The conventional investigation method is to sample and analyze point by using a ship. However, in order to obtain a large-scale sand content distribution in the estuary region, the conventional investigation method needs to sample large-area sediment, and has the disadvantages of slow investigation speed, long period and high observation cost. Moreover, the point scale acquisition mode can only acquire data of a small number of points which are very discrete in time and space distribution. The satellite remote sensing technology has the advantages of wide information coverage area, multiple time phases and multiple wave bands, can reflect the water body condition of a large area of a water area, has instant synchronization signals, has relatively short period for repeatedly acquiring data, and can effectively monitor the distribution and dynamic change of the sand content. In addition, the satellite remote sensing data can objectively and truly reflect the information of the water body, so that the space and time change rule of the suspended sediment is inverted. In recent years, the increase of the number of high-resolution remote sensing satellites at home and abroad provides more data support for inverting the concentration of suspended sediment in a water area. A plurality of scholars at home and abroad use remote sensing images to research the sand content information of different water areas, but because the sand content information of the actual water body is difficult to acquire and is difficult to be consistent with the shooting time of a satellite, the number of actually measured data samples is small, and therefore, a plurality of scholars usually adopt linear models, index models or empirical formulas of different areas to simulate the sand content of the water body. However, the linear model, the exponential model and the simple nonlinear model cannot accurately reflect the real spatial distribution relation of the suspended sediment concentration of the water body.
Disclosure of Invention
The invention aims to provide a water sand content inversion method based on a support vector machine, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a water area sand content inversion method based on a support vector machine comprises the following specific operation steps:
step 1, carrying out spatial position matching on actually measured sand content data obtained by point scale and high-resolution remote sensing multispectral data of corresponding time, extracting multispectral information of corresponding points, and forming a training and testing data set consisting of different levels of sand content and spectral information.
And 2, determining the optimal parameters of the training model by adopting a two-time lattice point search and ten-fold cross inspection method based on the training data set, and outputting the optimal inversion model based on the test data set.
And 3, taking a single grid where the actual measurement points are located as a calculation unit, calculating the sand content of different levels by using the optimal model, performing precision verification, and after the verification is passed, upscaling the grid unit to the whole water area to form a spatial distribution calculation result of the sand content of the water area.
As a further scheme of the invention: the step S1 includes the following specific steps:
1) inputting the longitude and latitude of the water area real measuring point into geographic information software, and carrying out spatial position matching on the actually measured sand content data obtained by the point scale and the high-resolution remote sensing multispectral data of corresponding time;
2) selecting data of each wave band of the image grid corresponding to the actual measurement points, and forming a test data set with actually measured sand content of different layers;
3) and (3) adopting a support vector machine model training model, sequentially removing each wave band, checking the model training precision after the wave bands are removed, and selecting the wave bands with the precision reduced by more than a certain threshold value as sensitive wave bands.
As a further scheme of the invention: the step S2 includes the following specific steps:
1) setting two parameter screening sections in different intervals by depending on a support vector machine model, and acquiring the optimal value of each parameter by adopting a ten-fold cross inspection method;
2) and outputting an optimal model capable of inverting the sand content at different depths as an inversion model by utilizing the test data set and combining the optimal parameters.
As a further scheme of the invention: the step S3 includes the following specific steps:
1) taking the grid as a unit to perform inversion prediction of sand contents at different depths;
2) taking the numerical values of the sand contents at different depths of the actual measuring points as a reference, and verifying the accuracy of the sand contents at different depths predicted by the model; setting a certain threshold value, and returning to the first step to restart the training if the precision is lower than the threshold value;
3) and (4) upscaling the inverse prediction model of the sand content at different depths, of which the point scale is higher than the threshold value, to the scale of the whole water area, and calculating the spatial distribution of the sand content at different depths of the whole water area.
Compared with the prior art, the method is not limited by the environment of on-site monitoring, solves the limitation of manual point scale measurement, and can realize inversion of the sand content of the upper layer of the water area in a large-area synchronous and remote manner.
Drawings
Fig. 1 is a schematic flow chart of a water sand content inversion method based on a support vector machine.
FIG. 2 is a schematic diagram of a sand content inversion in a water area based on a support vector machine.
Detailed Description
The technical solution of the present patent will be described in further detail with reference to the following embodiments.
Referring to fig. 1-2, a method for inverting sand content in a water area based on a support vector machine includes the following steps:
step S1, screening of sensitive wave bands: and screening out sensitive wave bands with different levels of sand content by utilizing a data set formed by the measured data and the multispectral remote sensing data.
To further explain the working process, step S1 includes the following specific steps:
1) and inputting the longitude and latitude of the water area actual measurement point into geographic information software, so that the actual measurement sand content data obtained by the point scale and the high-resolution remote sensing multispectral data of corresponding time are subjected to spatial position matching.
2) Selecting data of each wave band of the image grid corresponding to the actual measurement points, and forming a test data set with actually measured sand content of different layers;
3) and (3) adopting a support vector machine model training model, sequentially removing each wave band, checking the model training precision after the wave bands are removed, and selecting the wave bands with the precision reduced by more than a certain threshold value as sensitive wave bands.
Step S2, outputting an optimal inversion model: and (3) selecting the optimal parameters by using the training data and outputting the optimal model inverted by the sand contents at different depths by using the test data set by using the point scale as the training and testing scale.
To further explain the working process, step S2 includes the following specific steps:
1) setting two parameter screening sections in different intervals by depending on a support vector machine model, and acquiring the optimal value of each parameter by adopting a ten-fold cross inspection method;
2) and outputting an optimal model capable of inverting the sand content at different depths as an inversion model by utilizing the test data set and combining the optimal parameters.
And step S3, upscaling the training model of the point scale to the surface scale to obtain the inversion result of the spatial distribution of the sand content of the large-area water area.
To further explain the working process, step S3 includes the following specific steps:
1) taking the grid as a unit to perform inversion prediction of sand contents at different depths;
2) taking the numerical values of the sand contents at different depths of the actual measuring points as a reference, and verifying the accuracy of the sand contents at different depths predicted by the model; setting a certain threshold value, and returning to the first step to restart the training if the precision is lower than the threshold value;
3) and (4) upscaling the inverse prediction model of the sand content at different depths, of which the point scale is higher than the threshold value, to the scale of the whole water area, and calculating the spatial distribution of the sand content at different depths of the whole water area.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art through specific situations.
Although the preferred embodiments of the present patent have been described in detail, the present patent is not limited to the above embodiments, and various changes can be made without departing from the spirit of the present patent within the knowledge of those skilled in the art.
Claims (4)
1. A water sand content inversion method based on a support vector machine is characterized by comprising the following specific operation steps:
step S1, screening of sensitive wave bands: screening out sensitive wave bands with different levels of sand content by utilizing a data set formed by the measured data and the multispectral remote sensing data;
step S2, outputting an optimal inversion model: selecting the optimal parameters by using the training data and outputting the optimal model inverted by the sand contents at different depths by using the test data set by using the point scale as the training scale and the test scale;
and step S3, upscaling the training model of the point scale to the surface scale to obtain the inversion result of the spatial distribution of the sand content of the large-area water area.
2. The method for water sand content inversion based on the support vector machine as claimed in claim 1, wherein said step S1 includes the following specific steps:
1) inputting the longitude and latitude of the water area real measuring point into geographic information software, and carrying out spatial position matching on the actually measured sand content data obtained by the point scale and the high-resolution remote sensing multispectral data of corresponding time;
2) selecting data of each wave band of the image grid corresponding to the actual measurement points, and forming a test data set with actually measured sand content of different layers;
3) and (3) adopting a support vector machine model training model, sequentially removing each wave band, checking the model training precision after the wave bands are removed, and selecting the wave bands with the precision reduced by more than a certain threshold value as sensitive wave bands.
3. The method for water sand content inversion based on the support vector machine as claimed in claim 1, wherein said step S2 includes the following specific steps:
1) setting two parameter screening sections in different intervals by depending on a support vector machine model, and acquiring the optimal value of each parameter by adopting a ten-fold cross inspection method;
2) and outputting an optimal model capable of inverting the sand content at different depths as an inversion model by utilizing the test data set and combining the optimal parameters.
4. The method for water sand content inversion based on the support vector machine as claimed in claim 1, wherein said step S3 includes the following specific steps:
1) taking the grid as a unit to perform inversion prediction of sand contents at different depths;
2) taking the numerical values of the sand contents at different depths of the actual measuring points as a reference, and verifying the accuracy of the sand contents at different depths predicted by the model; setting a certain threshold value, and returning to the first step to restart the training if the precision is lower than the threshold value;
3) and (4) upscaling the inverse prediction model of the sand content at different depths, of which the point scale is higher than the threshold value, to the scale of the whole water area, and calculating the spatial distribution of the sand content at different depths of the whole water area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110944949.7A CN113673155B (en) | 2021-08-17 | 2021-08-17 | Water area sand content inversion method based on support vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110944949.7A CN113673155B (en) | 2021-08-17 | 2021-08-17 | Water area sand content inversion method based on support vector machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113673155A true CN113673155A (en) | 2021-11-19 |
| CN113673155B CN113673155B (en) | 2022-11-08 |
Family
ID=78543379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110944949.7A Active CN113673155B (en) | 2021-08-17 | 2021-08-17 | Water area sand content inversion method based on support vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113673155B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115655994A (en) * | 2022-09-15 | 2023-01-31 | 浙江天禹信息科技有限公司 | Ultrasonic measurement method and system for silt in water area |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103398927A (en) * | 2013-08-15 | 2013-11-20 | 上海市城市建设设计研究总院 | River sand content nonlinear retrieval method |
| CN105300864A (en) * | 2015-12-07 | 2016-02-03 | 广州地理研究所 | Quantitative remote sensing method of suspended sediment |
| CN109283144A (en) * | 2018-10-26 | 2019-01-29 | 浙江省水利河口研究院 | The strong long remote sensing calculation method for lasting variation of tidal height muddiness river mouth suspension bed sediment |
| US20190041377A1 (en) * | 2017-02-22 | 2019-02-07 | Hohai University | Method for measuring a mudflat elevation by remotely sensed water content |
| CN109657392A (en) * | 2018-12-28 | 2019-04-19 | 北京航空航天大学 | A kind of high-spectrum remote-sensing inversion method based on deep learning |
| CN110865040A (en) * | 2019-11-29 | 2020-03-06 | 深圳航天智慧城市系统技术研究院有限公司 | Sky-ground integrated hyperspectral water quality monitoring and analyzing method |
-
2021
- 2021-08-17 CN CN202110944949.7A patent/CN113673155B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103398927A (en) * | 2013-08-15 | 2013-11-20 | 上海市城市建设设计研究总院 | River sand content nonlinear retrieval method |
| CN105300864A (en) * | 2015-12-07 | 2016-02-03 | 广州地理研究所 | Quantitative remote sensing method of suspended sediment |
| US20190041377A1 (en) * | 2017-02-22 | 2019-02-07 | Hohai University | Method for measuring a mudflat elevation by remotely sensed water content |
| CN109283144A (en) * | 2018-10-26 | 2019-01-29 | 浙江省水利河口研究院 | The strong long remote sensing calculation method for lasting variation of tidal height muddiness river mouth suspension bed sediment |
| CN109657392A (en) * | 2018-12-28 | 2019-04-19 | 北京航空航天大学 | A kind of high-spectrum remote-sensing inversion method based on deep learning |
| CN110865040A (en) * | 2019-11-29 | 2020-03-06 | 深圳航天智慧城市系统技术研究院有限公司 | Sky-ground integrated hyperspectral water quality monitoring and analyzing method |
Non-Patent Citations (1)
| Title |
|---|
| 龚婷婷 等: "基于高分五号卫星数据的地表温度反演技术研究", 《数字技术与应用》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115655994A (en) * | 2022-09-15 | 2023-01-31 | 浙江天禹信息科技有限公司 | Ultrasonic measurement method and system for silt in water area |
| CN115655994B (en) * | 2022-09-15 | 2023-09-19 | 浙江天禹信息科技有限公司 | Ultrasonic measurement method and system for sediment in water area |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113673155B (en) | 2022-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103020478B (en) | A kind of method of Ocean color remote sensing product authenticity inspection | |
| CN104458895A (en) | Three-dimensional pipeline leakage flux imaging detection method and system | |
| CN104166801B (en) | Significant wave height and wave period parameterization method | |
| CN105300864A (en) | Quantitative remote sensing method of suspended sediment | |
| CN111597756A (en) | Water quality parameter inversion method based on multispectral data of unmanned aerial vehicle | |
| CN104453874A (en) | Glutenite reservoir oil saturation calculation method based on nuclear magnetic resonance | |
| CN113673155B (en) | Water area sand content inversion method based on support vector machine | |
| CN116486305B (en) | Image recognition-based deep sea suspended particulate matter concentration prediction method | |
| CN113673737A (en) | Estimation method for dissolved carbon dioxide in algae-type lake water body based on satellite remote sensing image | |
| CN110070220A (en) | A kind of ammonia nitrogen index flexible measurement method based on neural network algorithm | |
| CN106918389A (en) | It is a kind of based on the vibration modal analysis method of doppler optical displacement method and its application | |
| CN109444879A (en) | A kind of nearly tomography coseismic deformation extracting method of DInSAR | |
| CN115964915A (en) | Kelatong rock-ring three-dimensional material framework tracing method | |
| CN103995147B (en) | A kind of Data Post Processing System being applicable to acoustic Doppler velocimetry and application | |
| CN113297810B (en) | Method and system for arranging field observation equipment for inspecting sea surface height | |
| CN111256574A (en) | Method and system for measuring thickness of metal pipeline | |
| CN105004846B (en) | A kind of satellite remote sensing method monitoring high muddy turbidity of sea water | |
| CN103837533A (en) | Method for concrete temperature monitoring and simulation back analysis based on thermal imager | |
| CN103276713B (en) | Environmental piezocone penetration test (CPTU) probe capable of evaluating permeability characteristic of saturated soil in site | |
| CN117471071A (en) | Port infrastructure structure durability safety early warning system and port infrastructure structure durability safety early warning method | |
| CN105003258A (en) | Method for acquiring density framework parameters of methane fluid in high temperature high pressure air layer | |
| Balayssac et al. | An overview of 15 years of French collaborative projects for the characterization of concrete properties by combining NDT methods | |
| CN103575618A (en) | Measuring method for quantification of central looseness of casting blank | |
| CN109059813B (en) | Method for detecting corrosion strength of steel structure of hoisting machinery | |
| CN105089632A (en) | Method for obtaining CO2 fluid longitudinal wave time difference framework parameters of high-temperature and high-pressure reservoir |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |