CN115424134A - Pollution sea-entering flux prediction method and device based on remote sensing image - Google Patents
Pollution sea-entering flux prediction method and device based on remote sensing image Download PDFInfo
- Publication number
- CN115424134A CN115424134A CN202211032871.2A CN202211032871A CN115424134A CN 115424134 A CN115424134 A CN 115424134A CN 202211032871 A CN202211032871 A CN 202211032871A CN 115424134 A CN115424134 A CN 115424134A
- Authority
- CN
- China
- Prior art keywords
- data
- water body
- area
- water
- sea
- 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
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000004907 flux Effects 0.000 title claims description 28
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 364
- 238000005070 sampling Methods 0.000 claims abstract description 93
- 238000012549 training Methods 0.000 claims abstract description 65
- 238000003062 neural network model Methods 0.000 claims abstract description 36
- 238000007637 random forest analysis Methods 0.000 claims abstract description 36
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 52
- 238000004422 calculation algorithm Methods 0.000 claims description 32
- 229910052757 nitrogen Inorganic materials 0.000 claims description 26
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 25
- 229930002875 chlorophyll Natural products 0.000 claims description 25
- 235000019804 chlorophyll Nutrition 0.000 claims description 25
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 claims description 25
- 229910052760 oxygen Inorganic materials 0.000 claims description 25
- 239000001301 oxygen Substances 0.000 claims description 25
- 239000000126 substance Substances 0.000 claims description 25
- 210000000746 body region Anatomy 0.000 claims description 21
- 239000003344 environmental pollutant Substances 0.000 claims description 18
- 231100000719 pollutant Toxicity 0.000 claims description 18
- 230000001419 dependent effect Effects 0.000 claims description 17
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 14
- 229910052698 phosphorus Inorganic materials 0.000 claims description 14
- 239000011574 phosphorus Substances 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims 1
- 238000003384 imaging method Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 3
- 238000009360 aquaculture Methods 0.000 description 9
- 244000144974 aquaculture Species 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 238000000746 purification Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000002310 reflectometry Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 239000010865 sewage Substances 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000009395 breeding Methods 0.000 description 2
- 230000001488 breeding effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012851 eutrophication Methods 0.000 description 2
- 239000008239 natural water Substances 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000003651 drinking water Substances 0.000 description 1
- 235000020188 drinking water Nutrition 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/16—Image acquisition using multiple overlapping images; Image stitching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of geographic information, in particular to a pollution incoming traffic prediction method based on remote sensing images, which comprises the following steps: acquiring an ortho-image of the culture area, removing a non-water body area in the ortho-image, acquiring a water body image of the culture area, and acquiring water quality data corresponding to each sampling point in the water body image of the culture area according to the number of preset sampling points; acquiring wave band data corresponding to each sampling point in a water body image of a culture area, combining water quality data and wave band data corresponding to the same sampling point, and acquiring training data sets corresponding to a plurality of sampling points; inputting training data sets corresponding to the plurality of sampling points into a random forest neural network model for training to obtain a water quality prediction model; inputting the orthographic image of the culture area into a water quality prediction model, acquiring water quality prediction data of the water body area of the culture area, and acquiring a detection result of a pollution source area of the culture area according to the water quality prediction data of the water body area of the culture area.
Description
Technical Field
The invention relates to the technical field of geographic information, in particular to a method, a device, equipment and a storage medium for predicting the pollution incoming traffic based on remote sensing images.
Background
In recent years, with the rapid development of economic society, the demand of human beings for aquatic products is increasing, and the culture quantity is also increasing. The problem of water eutrophication caused by direct discharge of culture tail water to rivers, lakes and seas is increasingly prominent, and the safety of drinking water of human beings is seriously influenced. The natural water body has a certain self-purification capacity, but when the overloaded eutrophic water body is discharged, namely the polluted sea inflow volume exceeds the self-purification capacity of the water body, the eutrophic water body can be caused, thereby causing a series of water environment ecological problems.
However, since the purification technology and management cost of sewage discharge are high, and sewage treatment is not yet completely popularized, in some areas, especially in areas with high supervision difficulty, the situation that sewage is directly discharged into rivers, lakes and seas sometimes occurs. However, the current technical scheme cannot comprehensively and accurately calculate the pollution sea-entering flux in a large-scale area, and a great problem is caused for water pollution supervision.
Disclosure of Invention
Based on the above, the present invention aims to provide a method, an apparatus, a device and a storage medium for predicting the pollution sea inflow based on a remote sensing image, wherein a water quality prediction model and a water depth prediction model are constructed by acquiring water quality data, water depth data and waveband data in the remote sensing image of a culture area and adopting a deep learning method, so as to accurately and rapidly acquire the water quality prediction data and the water depth prediction data of the culture area, and acquire the pollution sea inflow prediction data of a water body area of the culture area according to the water quality prediction data and the water depth prediction data.
In a first aspect, an embodiment of the present application provides a method for predicting a polluted incoming traffic volume based on a remote sensing image, including the following steps:
acquiring a plurality of remote sensing images of a culture area, splicing the remote sensing images to obtain an orthoimage of the culture area, wherein the orthoimage comprises a water body area as a non-water body area;
removing non-water body areas in the orthographic images, acquiring water body images of the culture areas, and acquiring water quality data corresponding to each sampling point in the water body images of the culture areas according to the number of preset sampling points;
acquiring wave band data and water depth data corresponding to each sampling point in a water body image of the culture area, combining the water quality data and the wave band data corresponding to the same sampling point to acquire a plurality of first training data sets corresponding to the sampling points, and combining the water depth data and the wave band data corresponding to the same sampling point to acquire a plurality of second training data sets corresponding to the sampling points;
the wave band data are used as independent variables, the water quality data are used as dependent variables, a first random forest neural network model is constructed, a first training data set corresponding to a plurality of sampling points is input to the first random forest neural network model for training, and a water quality prediction model is obtained;
taking the waveband data as independent variables and the water depth data as dependent variables, constructing a second random forest neural network model, inputting a second training data set corresponding to a plurality of sampling points into the second random forest neural network model for training, and obtaining a water depth prediction model;
inputting the orthographic images of the culture area into the water quality prediction model and the water depth prediction model respectively, obtaining the water body area of the culture area and the water quality prediction data and the water depth prediction data of the water body area of the culture area, and obtaining the sea inflow flux prediction data of the culture area according to the water body area of the culture area and the water quality prediction data and the water depth prediction data of the water body area of the culture area.
In a second aspect, an embodiment of the present application provides a device for predicting a pollution incoming traffic based on a remote sensing image, including:
the system comprises an orthoimage acquisition module, a data processing module and a data processing module, wherein the orthoimage acquisition module is used for acquiring a plurality of remote sensing images of a culture area, splicing the remote sensing images and acquiring an orthoimage of the culture area, wherein the orthoimage comprises a water body area as a non-water body area;
the water quality data acquisition module is used for eliminating a non-water body area in the orthographic image, acquiring a water body image of the culture area, and acquiring water quality data corresponding to each sampling point in the water body image of the culture area according to the number of preset sampling points;
the training data acquisition module is used for acquiring wave band data and water depth data corresponding to each sampling point in a water body image of the culture area, combining the water quality data and the wave band data corresponding to the same sampling point to acquire a plurality of first training data sets corresponding to the sampling points, and combining the water depth data and the wave band data corresponding to the same sampling point to acquire a plurality of second training data sets corresponding to the sampling points;
the first model training module is used for constructing a first random forest neural network model by taking the waveband data as independent variables and the water quality data as dependent variables, inputting a first training data set corresponding to a plurality of sampling points into the first random forest neural network model for training, and acquiring a water quality prediction model;
the second model training module is used for constructing a second random forest neural network model by taking the waveband data as an independent variable and the water depth data as a dependent variable, inputting a second training data set corresponding to a plurality of sampling points into the second random forest neural network model for training, and acquiring a water depth prediction model;
and the polluted sea inflow forecasting module is used for inputting the orthographic images of the culture area into the water quality forecasting model and the water depth forecasting model respectively, acquiring the water body area of the culture area, the water quality forecasting data and the water depth forecasting data of the water body area of the culture area, and acquiring the polluted sea inflow forecasting data of the water body area of the culture area according to the water body area of the culture area, the water quality forecasting data and the water depth forecasting data of the water body area of the culture area.
In a third aspect, an embodiment of the present application provides a computer device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor; the computer program when executed by the processor implements the steps of the remote sensing image-based pollution incoming traffic prediction method according to the first aspect.
In a fourth aspect, an embodiment of the present application provides a storage medium, where the storage medium stores a computer program, and the computer program, when executed by a processor, implements the steps of the method for predicting pollution inflow volume based on remote sensing images according to the first aspect.
In the embodiment of the application, a method, a device, equipment and a storage medium for predicting the pollution sea inflow based on remote sensing images are provided, water quality data, water depth data and wave band data in the remote sensing images of the culture area are obtained, a deep learning method is adopted to construct a corresponding water quality prediction model and a corresponding water depth prediction model, the water quality prediction data and the water depth prediction data of the culture area are accurately and quickly obtained, the pollution sea inflow prediction data of the water body area of the culture area are obtained according to the water quality prediction data and the water depth prediction data, and timely detection and early warning are carried out on the area with the pollution sea inflow exceeding standard.
For a better understanding and practice, the invention is described in detail below with reference to the accompanying drawings.
Drawings
Fig. 1 is a schematic flow chart of a method for predicting the inflow to the sea of pollution based on remote sensing images according to a first embodiment of the present application;
fig. 2 is a schematic flowchart of a method for predicting the inflow of pollutants into the sea based on remote sensing images according to a second embodiment of the present application;
fig. 3 is a schematic flow chart of S2 in the method for predicting the inflow of pollutants into the sea based on remote sensing images according to the first embodiment of the present application;
fig. 4 is a schematic flow chart of S6 in the method for predicting the inflow of pollutants into the sea based on remote sensing images according to the first embodiment of the present application;
fig. 5 is a schematic flowchart of S62 in the method for predicting the pollutant incoming traffic based on the remote sensing image according to the first embodiment of the present application;
fig. 6 is a schematic flowchart of a method for predicting the inflow to the sea of pollution based on remote sensing images according to a third embodiment of the present application;
fig. 7 is a schematic structural diagram of a device for predicting the inflow to the sea of pollution based on remote sensing images according to a fourth embodiment of the present application;
fig. 8 is a schematic structural diagram of a computer device according to a fifth embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if/if" as used herein may be interpreted as "at … …" or "at … …" or "in response to a determination", depending on the context.
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for predicting a pollution incoming traffic based on a remote sensing image according to an embodiment of the present application, where the method includes the following steps:
s1: the method comprises the steps of obtaining a plurality of remote sensing images of a culture area, splicing the remote sensing images, and obtaining an orthoimage of the culture area.
The main execution body of the remote sensing image-based pollution incoming traffic prediction method is prediction equipment (hereinafter referred to as prediction equipment) of the remote sensing image-based pollution incoming traffic prediction method, and in an optional embodiment, the prediction equipment can be one computer device, a server or a server cluster formed by combining a plurality of computer devices.
The aquaculture area is an area relevant to the aquaculture industry and can comprise aquaculture ponds. In daily operation of the aquaculture industry, the aquaculture tail water is directly discharged into rivers, lakes and seas, and although natural water bodies all have certain self-purification capacity, once the aquaculture tail water with overload is discharged, namely the pollution sea inflow amount exceeds the self-purification capacity of the water bodies, the water body eutrophication can be caused, and a series of water environmental ecological problems are caused.
The remote sensing images are multispectral remote sensing images, in the embodiment, the prediction device can acquire a plurality of remote sensing images of the culture area input by a user, also can acquire a plurality of remote sensing images of the culture area through an unmanned aerial vehicle, and splices the plurality of remote sensing images to acquire an orthoimage of the culture area, wherein the orthoimage comprises a water body area and is a non-water body area.
S2: and removing the non-water body area in the orthographic image, acquiring the water body image of the culture area, and acquiring water quality data corresponding to each sampling point in the water body image of the culture area according to the number of preset sampling points.
In order to reduce the complexity of the operation and improve the efficiency of acquiring the band data, in this embodiment, the prediction device eliminates the non-water body region in the multispectral image, and acquires the water body image of the sample region.
And acquiring each sampling point in the water body image of the culture area according to the number of preset sampling points, specifically, distributing 10 sampling points in the culture area by prediction equipment according to a convenience principle and an uniformity principle, and acquiring water quality data corresponding to each sampling area in the water body image of the sample area, wherein the water quality data comprises chemical oxygen demand data, total nitrogen data, total phosphorus data and chlorophyll data.
Referring to fig. 2, fig. 2 is a schematic flow chart of a method for predicting the inflow of pollutant into the sea based on remote sensing images according to another embodiment of the present application, including step S7, where step S7 is before step S2, and specifically as follows:
s7: and preprocessing the ortho image to obtain a preprocessed ortho image, wherein the preprocessing comprises radiometric calibration and atmospheric correction.
In this embodiment, the prediction device performs radiometric calibration and atmospheric correction on the ortho image to obtain a preprocessed ortho image, thereby improving accuracy of measuring the waveband data of the ortho image.
Referring to fig. 3, fig. 3 is a schematic flow chart of S2 in the method for predicting the pollutant incoming traffic volume based on the remote sensing image according to an embodiment of the present application, which includes steps S21 to S22, and specifically includes the following steps:
s21: the method comprises the steps of obtaining a water body image corresponding to a sample area, and a green light band value and a near infrared band value of each pixel in the water body image, and calculating a normalized water content index value of each pixel in the water body image corresponding to the sample area according to a preset normalized water content index calculation algorithm to obtain a minimum normalized water content index value serving as a water body pixel distinguishing threshold value.
The normalized moisture index calculation algorithm is as follows:
in the formula, B green Is the value of the green band, B NIR The value of the near infrared band and NDWI is a normalized moisture index;
in this embodiment, the prediction device obtains a water body image corresponding to a sample area, and a green light band value and a near infrared band value of each pixel in the water body image, and calculates a normalized moisture index value of each pixel in the water body image corresponding to the sample area according to a preset normalized moisture index calculation algorithm to obtain a minimum normalized moisture index value as a water body pixel distinguishing threshold.
S22: the method comprises the steps of obtaining a green light wave band value and a near infrared wave band value of each pixel of an ortho-image, obtaining a normalized moisture index value of each pixel in the ortho-image according to a normalized moisture index calculation algorithm, obtaining a plurality of water body pixels in the ortho-image according to the normalized moisture index value of each pixel in the ortho-image and a water body pixel distinguishing threshold, and combining the plurality of water body pixels to obtain a water body image of the culture area.
In this embodiment, the prediction device compares the normalized moisture indexes corresponding to the pixels in the ortho-image with the water body segmentation threshold respectively, sets the pixels as water body pixels when the normalized moisture indexes corresponding to the pixels are greater than the water body segmentation threshold, sets the pixels as land pixels when the normalized moisture indexes corresponding to the pixels are less than or equal to the water body segmentation threshold, and eliminates the land pixels in the ortho-image to obtain the water body image corresponding to the water body area of the ortho-image as the water body image of the culture area.
S3: acquiring wave band data and water depth data corresponding to each sampling point in a water body image of the culture area, combining the water quality data and the wave band data corresponding to the same sampling point, acquiring a plurality of first training data sets corresponding to the sampling points, combining the water depth data and the wave band data corresponding to the same sampling point, and acquiring a plurality of second training data sets corresponding to the sampling points.
The band data includes a blue band reflectivity, a green band reflectivity, a red band reflectivity, and a near-infrared band reflectivity. In this embodiment, the prediction device acquires the wave band data and the water depth data corresponding to each sampling point in the water body image of the culture area, combines the water quality data and the wave band data corresponding to the same sampling point to acquire a plurality of first training data sets corresponding to the sampling points, and combines the water depth data and the wave band data corresponding to the same sampling point to acquire a plurality of second training data sets corresponding to the sampling points.
Specifically, the prediction device may obtain coordinate data of each sampling point in the water body image of the breeding area, obtain a sampling area corresponding to each sampling point according to a preset radius with the coordinate data of each sampling point as a circle center, obtain band data and water depth data corresponding to each pixel in the sampling area corresponding to each sampling point, average-process the band data and the water depth data, obtain average band data and average water depth data corresponding to the sampling area corresponding to each sampling point, and use the average band data and the average water depth data as band data and water depth data corresponding to each sampling point in the water body image of the breeding area.
S4: and taking the waveband data as an independent variable and the water quality data as a dependent variable, constructing a first random forest neural network model, inputting a plurality of first training data sets corresponding to the sampling points into the first random forest neural network model for training, and obtaining a water quality prediction model.
The random forest neural network model is a classifier comprising a plurality of decision trees, and the class of its output is dependent on the mode of the class output by the individual trees.
In this embodiment, the prediction device uses the waveband data as an independent variable and the water quality data as a dependent variable to construct a first random forest neural network model, and inputs a plurality of first training data sets corresponding to the sampling points into the random forest neural network model for training to obtain the water quality prediction model.
Specifically, the water quality data comprises total nitrogen data, total phosphorus data, chemical oxygen demand data and chlorophyll data, and the prediction device sets a characteristic variable data set corresponding to the water quality data corresponding to the sampling point, wherein the characteristic variable data set comprises characteristic variables, and the characteristic variables comprise total nitrogen characteristic variables, total phosphorus characteristic variables, chemical oxygen demand characteristic variables and chlorophyll characteristic variables;
the prediction equipment randomly extracts a plurality of n samples from a feature variable data set corresponding to the water quality data corresponding to the sampling points according to a first training data set corresponding to the sampling points, randomly selects m feature variables for each of the n samples, generates a decision tree model corresponding to the sample, randomly selects one feature variable from the m feature variables of each decision tree model as a node to split, stops splitting when a Gini coefficient is minimum, constructs a random forest neural network model, inputs a plurality of first training data sets corresponding to the sampling points into the random forest neural network model to train, and obtains the water quality prediction model.
S5: and taking the waveband data as independent variables and the water depth data as dependent variables, constructing a second random forest neural network model, inputting a second training data set corresponding to the plurality of sampling points into the second random forest neural network model for training, and obtaining a water depth prediction model.
In this embodiment, the prediction device uses the band data as an independent variable and the water depth data as a dependent variable to construct a second random forest neural network model, and inputs a plurality of second training data sets corresponding to the sampling points into the second random forest neural network model for training to obtain a water depth prediction model.
S6: respectively inputting the orthographic images of the culture area into the water quality prediction model and the water depth prediction model, acquiring the water body area of the culture area and the water quality prediction data and the water depth prediction data of the water body area of the culture area, and acquiring the pollution sea inflow flux prediction data of the water body area of the culture area according to the water body area of the culture area and the water quality prediction data and the water depth prediction data of the water body area of the culture area.
In this embodiment, the prediction device inputs the orthographic images of the culture area into the water quality prediction model and the water depth prediction model respectively, obtains the water body area of the culture area and the water quality prediction data and the water depth prediction data of the water body area of the culture area, and obtains the pollution sea inflow amount prediction data of the water body area of the culture area according to the water body area of the culture area and the water quality prediction data and the water depth prediction data of the water body area of the culture area.
Referring to fig. 4, fig. 4 is a schematic flow chart of S6 in the method for predicting the pollutant incoming traffic volume based on the remote sensing image according to an embodiment of the present application, which includes steps S61 to S62, specifically as follows:
s61: and acquiring area data of the water body area of the culture area, and acquiring volume prediction data of the water body area of the culture area according to the area data and the water depth prediction data.
The area data is used for indicating the area of the water body region of each pixel, and the volume prediction data is used for indicating the volume of the water body region of each pixel;
in this embodiment, the prediction device obtains area data of the water body region of the aquaculture area, and obtains volume prediction data of the water body region of the aquaculture area according to the area data and the water depth prediction data, specifically as follows:
W v ＝W d ×W s
in the formula, W v For predicting data for said volume, W d Predicting data for said water depth, W s Is the area data.
S62: and acquiring the forecast data of the water body area of the culture area for the pollution sea-going volume according to the volume forecast data, the water quality forecast data and the corresponding pollution sea-going volume calculation algorithm of the water body area of the culture area.
In this embodiment, the prediction device obtains the prediction data of the pollution sea inflow amount of the water body area of the culture area according to the volume prediction data, the water quality prediction data and the corresponding pollution sea inflow amount calculation algorithm of the water body area of the culture area, wherein the prediction data of the pollution sea inflow amount comprises total nitrogen sea inflow amount prediction data, total phosphorus sea inflow amount prediction data, chemical oxygen demand sea inflow amount prediction data and chlorophyll sea inflow amount prediction data.
Referring to fig. 5, fig. 5 is a schematic flow chart of S62 in the method for predicting the inflow of pollutant into the sea based on remote sensing images according to an embodiment of the present application, which includes steps S621 to S624, specifically as follows:
s621: and acquiring total nitrogen sea-entering flux prediction data of the culture area according to the volume prediction data and the total nitrogen sea-entering flux prediction data of the water body area of the culture area and a preset total nitrogen sea-entering flux prediction data calculation algorithm.
The total nitrogen sea-entering flux prediction data calculation algorithm comprises the following steps:
TN＝∑W v ×C TN
in the formula, TN is the total nitrogen sea-entering flux prediction data, W v Predicting data for said volume, C TN Predicting data for the total nitrogen;
in this embodiment, the prediction device calculates, according to the volume prediction data, the total nitrogen prediction data, and a preset total nitrogen sea inflow prediction data calculation algorithm of the water body region of the culture region, the total nitrogen sea inflow prediction data corresponding to each pixel of the water body region of the culture region, to obtain the total nitrogen sea inflow prediction data of the water body region of the culture region, which is used as the total nitrogen sea inflow prediction data of the culture region.
S622: and acquiring the total phosphorus-to-sea flux prediction data of the culture area according to the volume prediction data and the total phosphorus prediction data of the water body area of the culture area and a preset total phosphorus-to-sea flux prediction data calculation algorithm.
The total phosphorus-in-the-sea traffic prediction data calculation algorithm comprises the following steps:
TP＝∑W v ×C TP
wherein TP is the total phosphorus flux prediction data, C TP Predicting data for the total phosphorus;
in this embodiment, the prediction device calculates, according to the volume prediction data, the total nitrogen prediction data, and the preset total phosphorus-to-sea flux prediction data calculation algorithm of the water body region of the culture region, the total phosphorus-to-sea flux prediction data corresponding to each pixel of the water body region of the culture region, to obtain the total phosphorus-to-sea flux prediction data of the water body region of the culture region, which is used as the total phosphorus-to-sea flux prediction data of the culture region.
S623: and calculating an algorithm according to the volume prediction data, the chemical oxygen demand prediction data and the preset chemical oxygen demand sea-going volume prediction data of the water body area of the culture area to obtain the chemical oxygen demand sea-going volume prediction data of the culture area.
The calculation algorithm of the prediction data of the chemical oxygen demand sea-going volume is as follows:
COD＝∑W v ×C COD
wherein COD is the prediction data of the Chemical Oxygen Demand (COD) intake-to-the-sea flux, C COD (ii) predicting data for said chemical oxygen demand;
in this embodiment, the prediction device calculates, according to the volume prediction data, the chemical oxygen demand prediction data, and the preset chemical oxygen demand sea-going volume prediction data calculation algorithm of the water body region of the culture region, the chemical oxygen demand sea-going volume prediction data corresponding to each pixel of the water body region of the culture region, to obtain the chemical oxygen demand sea-going volume prediction data of the water body region of the culture region, which is used as the chemical oxygen demand sea-going volume prediction data of the culture region.
S621: and acquiring chlorophyll sea inflow prediction data of the culture area according to the volume prediction data, chlorophyll prediction data and a preset chlorophyll sea inflow prediction data calculation algorithm of the water body area of the culture area.
The calculation algorithm of the chlorophyll sea-entering flux prediction data is as follows:
TN＝∑W v ×C TN
wherein CHI is the predicted data of the chlorophyll sea-entering flux, C CHI Predicting data for the chlorophyll.
In this embodiment, the prediction device calculates the chlorophyll sea inflow amount prediction data corresponding to each pixel of the water body area of the culture area according to the volume prediction data, the chlorophyll prediction data and a preset chlorophyll sea inflow amount prediction data calculation algorithm of the water body area of the culture area, and obtains the chlorophyll sea inflow amount prediction data of the water body area of the culture area as the chlorophyll sea inflow amount prediction data of the culture area.
Referring to fig. 6, fig. 6 is a schematic flow chart of a method for predicting the inflow of pollutant into the sea based on remote sensing images according to a third embodiment of the present application, further including step S8, which is specifically as follows:
s8: the method comprises the steps of obtaining electronic map data corresponding to a culture area, obtaining a pollution early warning identifier of the water body area of the culture area according to pollution incoming traffic prediction data of the water body area of the culture area and a preset pollution incoming traffic threshold value, and displaying the corresponding pollution early warning identifier and marking the pollution incoming traffic prediction data on the electronic map data according to the pollution early warning identifier of the water body area of the culture area.
In this embodiment, the prediction device acquires electronic map data corresponding to the culture area, and displays an electronic map reflecting the culture area on a preset display interface.
Obtaining a pollution early warning identifier of the water body area of the culture area according to the pollution sea inflow prediction data of the water body area of the culture area and a preset pollution sea inflow threshold, specifically, the pollution sea inflow threshold comprises a total nitrogen sea inflow threshold, a total phosphorus sea inflow threshold, a chemical oxygen demand sea inflow threshold and a chlorophyll sea inflow threshold, and the prediction equipment respectively compares the pollution sea inflow prediction data with the corresponding pollution sea inflow threshold, and when the pollution sea inflow prediction data is greater than or equal to the corresponding pollution sea inflow threshold, the pollution early warning identifier is obtained.
And according to the pollution early warning identification of the water body area of the culture area, displaying the corresponding pollution early warning identification and marking the pollution incoming traffic prediction data on the electronic map data. Therefore, timely detection and early warning are carried out on the areas with the possibility of overproof culture tail water discharge in time.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a device for predicting pollutant inflow into the sea based on remote sensing images according to an embodiment of the present application, where the device may implement all or a part of the device for predicting pollutant inflow into the sea based on remote sensing images through software, hardware or a combination of the two, and the device 7 includes:
the orthoimage acquisition module 71 is configured to acquire a plurality of remote sensing images of a culture area, and splice the plurality of remote sensing images to obtain an orthoimage of the culture area, where the orthoimage includes a water body area as a non-water body area;
the water quality data acquisition module 72 is used for eliminating a non-water body area in the orthographic image, acquiring a water body image of the culture area, and acquiring water quality data corresponding to each sampling point in the water body image of the culture area according to the number of preset sampling points;
a training data acquisition module 73, configured to acquire wave band data and water depth data corresponding to each sampling point in a water body image of the aquaculture area, combine the water quality data and the wave band data corresponding to the same sampling point to acquire a plurality of first training data sets corresponding to the sampling points, combine the water depth data and the wave band data corresponding to the same sampling point to acquire a plurality of second training data sets corresponding to the sampling points;
a first model training module 74, configured to use the waveband data as an independent variable and the water quality data as a dependent variable, construct a first random forest neural network model, input a first training data set corresponding to the plurality of sampling points into the first random forest neural network model for training, and obtain a water quality prediction model;
a second model training module 75, configured to use the band data as an independent variable and the water depth data as a dependent variable, construct a second random forest neural network model, input a second training data set corresponding to the plurality of sampling points into the second random forest neural network model for training, and obtain a water depth prediction model;
and a pollution sea inflow prediction module 76, configured to input the orthographic images of the culture area into the water quality prediction model and the water depth prediction model respectively, obtain the water body area of the culture area, and the water quality prediction data and the water depth prediction data of the water body area of the culture area, and obtain the pollution sea inflow prediction data of the water body area of the culture area according to the water body area of the culture area, the water quality prediction data and the water depth prediction data of the water body area of the culture area.
In the embodiment of the application, a plurality of remote sensing images of a culture area are obtained through an orthoimage obtaining module, the remote sensing images are spliced to obtain an orthoimage of the culture area, wherein the orthoimage comprises a water body area as a non-water body area; removing non-water body areas in the orthographic images through a water quality data acquisition module, acquiring water body images of the culture area, and acquiring water quality data corresponding to each sampling point in the water body images of the culture area according to the number of preset sampling points; acquiring wave band data and water depth data corresponding to each sampling point in a water body image of the culture area through a training data acquisition module, combining the water quality data and the wave band data corresponding to the same sampling point to acquire a plurality of first training data sets corresponding to the sampling points, and combining the water depth data and the wave band data corresponding to the same sampling point to acquire a plurality of second training data sets corresponding to the sampling points; constructing a first random forest neural network model by using the waveband data as independent variables and the water quality data as dependent variables through a first model training module, inputting a first training data set corresponding to a plurality of sampling points into the first random forest neural network model for training, and obtaining a water quality prediction model; constructing a second random forest neural network model by using the waveband data as independent variables and the water depth data as dependent variables through a second model training module, inputting a second training data set corresponding to a plurality of sampling points into the second random forest neural network model for training, and obtaining a water depth prediction model; the method comprises the steps of inputting orthoimages of a culture area into a water quality prediction model and a water depth prediction model respectively through a pollution sea inflow prediction module, obtaining a water body area of the culture area, water quality prediction data and water depth prediction data of the water body area of the culture area, obtaining pollution sea inflow prediction data of the water body area of the culture area according to the water body area of the culture area, the water quality prediction data and the water depth prediction data of the water body area of the culture area, building a corresponding water quality prediction model and a corresponding water depth prediction model by obtaining water quality data, water depth data and waveband data in remote sensing images of the culture area through a deep learning method, obtaining the water quality prediction data and the water depth prediction data of the culture area accurately and quickly, and obtaining the pollution sea inflow prediction data of the water body area of the culture area according to the water quality prediction data and the water depth prediction data.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present application, where the computer device 7 includes: a processor 81, a memory 82, and a computer program 83 stored on the memory 82 and operable on the processor 81; the computer device may store a plurality of instructions, where the instructions are suitable for being loaded by the processor 81 and executing the method steps in the embodiments shown in fig. 1 to fig. 6, and a specific execution process may refer to specific descriptions of the embodiments shown in fig. 1 to fig. 6, which is not described herein again.
The Memory 82 may include a Random Access Memory (RAM) 82, and may also include a Read-Only Memory (Read-Only Memory) 82. Optionally, the memory 82 includes a non-transitory computer-readable medium. The memory 82 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 82 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch instructions, etc.), instructions for implementing the various method embodiments described above, and the like; the storage data area may store data and the like referred to in the above respective method embodiments. The memory 82 may alternatively be at least one memory device located remotely from the aforementioned processor 81.
An embodiment of the present application further provides a storage medium, where the storage medium may store multiple instructions, and the instructions are suitable for being loaded by a processor and being executed by the method steps in the embodiments shown in fig. 1 to fig. 6, and a specific execution process may refer to specific descriptions of the embodiments shown in fig. 1 to fig. 6, which is not described herein again.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc.
The present invention is not limited to the above-described embodiments, and various modifications and variations of the present invention are intended to be included within the scope of the claims and the equivalent technology of the present invention if they do not depart from the spirit and scope of the present invention.
Claims (10)
1. A pollution sea traffic prediction method based on remote sensing images is characterized by comprising the following steps:
acquiring a plurality of remote sensing images of a culture area, splicing the remote sensing images to obtain an orthoimage of the culture area, wherein the orthoimage comprises a water body area as a non-water body area;
removing non-water body areas in the orthographic images, acquiring water body images of the culture areas, and acquiring water quality data corresponding to each sampling point in the water body images of the culture areas according to the number of preset sampling points;
acquiring wave band data and water depth data corresponding to each sampling point in a water body image of the culture area, combining the water quality data and the wave band data corresponding to the same sampling point to acquire a plurality of first training data sets corresponding to the sampling points, and combining the water depth data and the wave band data corresponding to the same sampling point to acquire a plurality of second training data sets corresponding to the sampling points;
establishing a first random forest neural network model by taking the waveband data as an independent variable and the water quality data as a dependent variable, and inputting a plurality of first training data sets corresponding to the sampling points into the first random forest neural network model for training to obtain a water quality prediction model;
taking the waveband data as independent variables and the water depth data as dependent variables, constructing a second random forest neural network model, inputting a second training data set corresponding to a plurality of sampling points into the second random forest neural network model for training, and obtaining a water depth prediction model;
respectively inputting the orthographic images of the culture area into the water quality prediction model and the water depth prediction model, acquiring the water body area of the culture area and the water quality prediction data and the water depth prediction data of the water body area of the culture area, and acquiring the pollution sea inflow flux prediction data of the water body area of the culture area according to the water body area of the culture area and the water quality prediction data and the water depth prediction data of the water body area of the culture area.
2. The method for predicting the inflow of pollutant into the sea based on the remote sensing image as claimed in claim 1, wherein: the water quality data comprises total nitrogen data, total phosphorus data, chemical oxygen demand data and chlorophyll data; the water quality prediction data comprises total nitrogen prediction data, total phosphorus prediction data, chemical oxygen demand prediction data and chlorophyll prediction data.
3. The method for predicting the polluted sea inflow amount based on the remote sensing image according to claim 2, wherein the method for obtaining the predicted polluted sea inflow amount of the water body region of the culture region according to the water body region of the culture region, the water quality prediction data and the water depth prediction data of the water body region of the culture region comprises the following steps:
acquiring area data of a water body region of the culture region, and acquiring volume prediction data of the water body region of the culture region according to the area data and water depth prediction data, wherein the area data is used for indicating the area of the water body region of each pixel, and the volume prediction data is used for indicating the volume of the water body region of each pixel;
and acquiring the forecast data of the pollution sea inflow amount of the water body area of the culture area according to the volume forecast data, the water quality forecast data and the corresponding pollution sea inflow amount calculation algorithm of the water body area of the culture area, wherein the forecast data of the pollution sea inflow amount comprises total nitrogen sea inflow amount forecast data, total phosphorus sea inflow amount forecast data, chemical oxygen demand sea inflow amount forecast data and chlorophyll sea inflow amount forecast data.
4. The remote sensing image-based method for predicting the pollutant sea inflow amount according to claim 3, wherein the method for obtaining the forecast data of the pollutant sea inflow amount of the water body area of the culture area according to the volume forecast data, the water quality forecast data and the corresponding sea inflow amount calculation algorithm of the water body area of the culture area comprises the following steps:
acquiring total nitrogen sea inflow prediction data of the culture area according to the volume prediction data, the total nitrogen prediction data and a preset total nitrogen sea inflow prediction data calculation algorithm of the water body area of the culture area, wherein the total nitrogen sea inflow prediction data calculation algorithm is as follows:
TN＝∑W v ×C TN
in the formula, TN is the total nitrogen sea-entering flux prediction data, W v Predicting data for said volume, C TN Predicting data for the total nitrogen;
acquiring the total phosphorus-to-sea flux prediction data of the culture area according to the volume prediction data, the total phosphorus prediction data and a preset total phosphorus-to-sea flux prediction data calculation algorithm of the water body area of the culture area, wherein the total phosphorus-to-sea flux prediction data calculation algorithm is as follows:
TP＝∑W v ×C TP
wherein TP is the total phosphorus flux prediction data, C TP Predicting data for the total phosphorus;
acquiring the prediction data of the chemical oxygen demand-to-sea volume of the culture area according to the volume prediction data, the chemical oxygen demand prediction data and a preset calculation algorithm of the prediction data of the chemical oxygen demand-to-sea volume, wherein the calculation algorithm of the prediction data of the chemical oxygen demand-to-sea volume is as follows:
CON＝∑W v ×C COD
in the formula (I), the compound is shown in the specification,COD is the predicted data of the chemical oxygen demand sea-entering flux, C COD (ii) predicting data for said chemical oxygen demand;
obtaining the chlorophyll inflow amount prediction data of the culture area according to the volume prediction data, the chlorophyll prediction data and a preset chlorophyll inflow amount prediction data calculation algorithm of the water body area of the culture area, wherein the chlorophyll inflow amount prediction data calculation algorithm is as follows:
TN＝∑W v ×C TN
wherein CHI is the predicted data of the chlorophyll sea-entering flux, C CHI Data are predicted for the chlorophyll.
5. The method for predicting the pollutant inflow to the sea based on the remote sensing image as claimed in claim 1, wherein the method for eliminating the non-water body area in the ortho image comprises the following steps before the water body image of the culture area is acquired:
and preprocessing the ortho image to obtain a preprocessed ortho image, wherein the preprocessing comprises radiometric calibration and atmospheric correction.
6. The method for predicting the pollutant inflow to the sea based on the remote sensing image according to claim 1, wherein the non-water body area in the ortho image is removed, and the water body image of the culture area is obtained, comprising the following steps:
acquiring a water body image corresponding to a sample area, and a green light band value and a near infrared band value of each pixel in the water body image, and calculating a normalized water content index value of each pixel in the water body image corresponding to the sample area according to a preset normalized water content index calculation algorithm to obtain a minimum normalized water content index value serving as a water body pixel distinguishing threshold, wherein the normalized water content index calculation algorithm is as follows:
in the formula, B green Is the value of the green band, B NIR The value of the near infrared band and NDWI is a normalized moisture index;
the method comprises the steps of obtaining a green light wave band value and a near infrared wave band value of each pixel of the orthographic image, obtaining a normalized moisture index value of each pixel in the orthographic image according to a normalized moisture index calculation algorithm, obtaining a plurality of water body pixels in the orthographic image according to the normalized moisture index value of each pixel in the orthographic image and a water body pixel distinguishing threshold, and combining the plurality of water body pixels to obtain a water body image of the culture area.
7. The method for predicting the inflow of pollutant into the sea based on the remote sensing image as claimed in claim 1, further comprising the steps of:
the method comprises the steps of obtaining electronic map data corresponding to a culture area, obtaining a pollution early warning identifier of the water body area of the culture area according to pollution incoming traffic prediction data of the water body area of the culture area and a preset pollution incoming traffic threshold value, and displaying the corresponding pollution early warning identifier and marking the pollution incoming traffic prediction data on the electronic map data according to the pollution early warning identifier of the water body area of the culture area.
8. A pollution incoming traffic prediction device based on remote sensing images is characterized by comprising:
the system comprises an orthoimage acquisition module, a registration module and a control module, wherein the orthoimage acquisition module is used for acquiring a plurality of remote sensing images of a culture area, splicing the remote sensing images and acquiring an orthoimage of the culture area, wherein the orthoimage comprises a water body area as a non-water body area;
the water quality data acquisition module is used for eliminating a non-water body area in the orthographic image, acquiring a water body image of the culture area, and acquiring water quality data corresponding to each sampling point in the water body image of the culture area according to the number of preset sampling points;
the training data acquisition module is used for acquiring wave band data and water depth data corresponding to each sampling point in a water body image of the culture area, combining the water quality data and the wave band data corresponding to the same sampling point to acquire a plurality of first training data sets corresponding to the sampling points, and combining the water depth data and the wave band data corresponding to the same sampling point to acquire a plurality of second training data sets corresponding to the sampling points;
the first model training module is used for constructing a first random forest neural network model by taking the waveband data as independent variables and the water quality data as dependent variables, inputting a first training data set corresponding to a plurality of sampling points into the first random forest neural network model for training, and acquiring a water quality prediction model;
the second model training module is used for constructing a second random forest neural network model by taking the waveband data as an independent variable and the water depth data as a dependent variable, inputting a second training data set corresponding to a plurality of sampling points into the second random forest neural network model for training, and acquiring a water depth prediction model;
and the polluted sea inflow forecasting module is used for inputting the orthographic images of the culture area into the water quality forecasting model and the water depth forecasting model respectively, acquiring the water body area of the culture area and the water quality forecasting data and the water depth forecasting data of the water body area of the culture area, and acquiring the polluted sea inflow forecasting data of the water body area of the culture area according to the water body area of the culture area and the water quality forecasting data and the water depth forecasting data of the water body area of the culture area.
9. A computer device, comprising: a processor, a memory, and a computer program stored on the memory and executable on the processor; the computer program when executed by the processor implements the steps of the remote sensing image-based pollution incoming call volume prediction method according to any one of claims 1 to 7.
10. A storage medium, characterized by: the storage medium stores a computer program which, when executed by a processor, implements the steps of the method for predicting remote sensing image-based pollutant inflow volume according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211032871.2A CN115424134B (en) | 2022-08-26 | 2022-08-26 | Pollution sea flux prediction method and device based on remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211032871.2A CN115424134B (en) | 2022-08-26 | 2022-08-26 | Pollution sea flux prediction method and device based on remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115424134A true CN115424134A (en) | 2022-12-02 |
| CN115424134B CN115424134B (en) | 2024-04-09 |
Family
ID=84200027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211032871.2A Active CN115424134B (en) | 2022-08-26 | 2022-08-26 | Pollution sea flux prediction method and device based on remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115424134B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117292211A (en) * | 2023-11-27 | 2023-12-26 | 潍坊市海洋发展研究院 | Water quality labeling image sending method and device, electronic equipment and computer readable medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105092476A (en) * | 2015-08-20 | 2015-11-25 | 中山大学 | Method for simultaneously inverting turbidity, COD and chlorophyll concentration of inland water |
| CN106202163A (en) * | 2016-06-24 | 2016-12-07 | 中国环境科学研究院 | Tongjiang lake ecological monitoring information management and early warning system |
| CN106525762A (en) * | 2016-11-07 | 2017-03-22 | 航天恒星科技有限公司 | Water quality monitoring method and water quality monitoring device based on adaptive model |
| CN107340365A (en) * | 2017-06-19 | 2017-11-10 | 中国科学院南京地理与湖泊研究所 | A kind of three-dimensional monitoring and data digging system and method towards lake blue algae disaster |
| CN109522788A (en) * | 2018-09-30 | 2019-03-26 | 广州地理研究所 | City scope extracting method, device and electronic equipment based on random forest sorting algorithm |
| CN113298058A (en) * | 2021-07-27 | 2021-08-24 | 浙江省淡水水产研究所 | Water quality prediction inversion method and system based on hyperspectral image of unmanned aerial vehicle |
| CN114202691A (en) * | 2021-12-09 | 2022-03-18 | 广东省科学院广州地理研究所 | Rice identification method, device and equipment based on remote sensing image |
| CN114612896A (en) * | 2022-03-07 | 2022-06-10 | 广东省科学院广州地理研究所 | Rice yield prediction method, device and equipment based on remote sensing image |
| CN114707293A (en) * | 2022-01-27 | 2022-07-05 | 清华大学 | Watershed water environment simulation method and watershed water environment simulation device |
-
2022
- 2022-08-26 CN CN202211032871.2A patent/CN115424134B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105092476A (en) * | 2015-08-20 | 2015-11-25 | 中山大学 | Method for simultaneously inverting turbidity, COD and chlorophyll concentration of inland water |
| CN106202163A (en) * | 2016-06-24 | 2016-12-07 | 中国环境科学研究院 | Tongjiang lake ecological monitoring information management and early warning system |
| CN106525762A (en) * | 2016-11-07 | 2017-03-22 | 航天恒星科技有限公司 | Water quality monitoring method and water quality monitoring device based on adaptive model |
| CN107340365A (en) * | 2017-06-19 | 2017-11-10 | 中国科学院南京地理与湖泊研究所 | A kind of three-dimensional monitoring and data digging system and method towards lake blue algae disaster |
| CN109522788A (en) * | 2018-09-30 | 2019-03-26 | 广州地理研究所 | City scope extracting method, device and electronic equipment based on random forest sorting algorithm |
| CN113298058A (en) * | 2021-07-27 | 2021-08-24 | 浙江省淡水水产研究所 | Water quality prediction inversion method and system based on hyperspectral image of unmanned aerial vehicle |
| CN114202691A (en) * | 2021-12-09 | 2022-03-18 | 广东省科学院广州地理研究所 | Rice identification method, device and equipment based on remote sensing image |
| CN114707293A (en) * | 2022-01-27 | 2022-07-05 | 清华大学 | Watershed water environment simulation method and watershed water environment simulation device |
| CN114612896A (en) * | 2022-03-07 | 2022-06-10 | 广东省科学院广州地理研究所 | Rice yield prediction method, device and equipment based on remote sensing image |
Non-Patent Citations (2)
| Title |
|---|
| 陈黄蓉: ""入海口及上游河流污染水体遥感监测研究"", 《中国优秀硕士学位论文全文数据库 工程科技一辑》 * |
| 黄亚玲: ""河流氮输出与真核微生物群落结构对流域土地利用模式和水文状况的响应研究-以九龙江流域为例"", 《中国博士学位论文全文数据库》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117292211A (en) * | 2023-11-27 | 2023-12-26 | 潍坊市海洋发展研究院 | Water quality labeling image sending method and device, electronic equipment and computer readable medium |
| CN117292211B (en) * | 2023-11-27 | 2024-02-27 | 潍坊市海洋发展研究院 | Water quality labeling image sending method and device, electronic equipment and computer readable medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115424134B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115439757A (en) | Water quality pollution source tracing method, device and equipment based on remote sensing image | |
| CN110929592A (en) | Extraction method and system for outer boundary of mariculture area | |
| CN110032928B (en) | Satellite remote sensing image water body identification method suitable for color sensitivity | |
| CN115424134B (en) | Pollution sea flux prediction method and device based on remote sensing image | |
| CN113378785A (en) | Forest type identification method and device | |
| CN112419333A (en) | Remote sensing image self-adaptive feature selection segmentation method and system | |
| KR20220105530A (en) | Method for predicting water quality and apparatus thereof | |
| CN107271367B (en) | A kind of identifying water boy method and device | |
| CN111239131A (en) | AI intelligent water environmental protection real-time monitoring platform | |
| CN117953299A (en) | Land utilization classification method based on multi-scale remote sensing images | |
| CN115410086A (en) | Water quality inversion method, device and equipment based on remote sensing image | |
| Wu et al. | An improved YOLO model for detecting trees suffering from pine wilt disease at different stages of infection | |
| CN116704324A (en) | Target detection method, system, equipment and storage medium based on underwater image | |
| CN115827878A (en) | Statement emotion analysis method, device and equipment | |
| Rivera et al. | Monitoring macrophytes cover and taxa in Utah Lake by using 2009-2011 Landsat digital imagery | |
| CN115346115A (en) | Image target detection method, device, equipment and storage medium | |
| CN114495058A (en) | Traffic sign detection method and device | |
| Hashemi et al. | The Detection of the Plume of the Arvand River Using Satellite Images | |
| CN112633158A (en) | Power transmission line corridor vehicle identification method, device, equipment and storage medium | |
| CN113822255B (en) | Water body identification method and related device | |
| CN111814809A (en) | Remote sensing image vegetation information extraction method and device | |
| Şenol et al. | Trends of changing land use dynamics in the Terkos Lake basin between 1980 and 2023 and their impact on natural ecosystems | |
| CN116152656B (en) | SAR image city solid waste automatic identification method and system based on distillation learning | |
| CN118196643A (en) | Ecological advantage prediction method and device for valve-free sea mulberry area and computer equipment | |
| CN116363362B (en) | Image semantic segmentation method, object recognition method and computing device |
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 |