CN116773465B - Perfluoro compound pollution on-line monitoring method and system - Google Patents
Perfluoro compound pollution on-line monitoring method and system Download PDFInfo
- Publication number
- CN116773465B CN116773465B CN202311080843.2A CN202311080843A CN116773465B CN 116773465 B CN116773465 B CN 116773465B CN 202311080843 A CN202311080843 A CN 202311080843A CN 116773465 B CN116773465 B CN 116773465B
- Authority
- CN
- China
- Prior art keywords
- soil
- pollution
- polluted
- data
- perfluorinated
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000012544 monitoring process Methods 0.000 title claims abstract description 65
- -1 Perfluoro compound Chemical class 0.000 title claims abstract description 15
- 239000002689 soil Substances 0.000 claims abstract description 317
- 238000003900 soil pollution Methods 0.000 claims abstract description 172
- 150000001875 compounds Chemical class 0.000 claims abstract description 157
- 238000009792 diffusion process Methods 0.000 claims abstract description 47
- 238000007637 random forest analysis Methods 0.000 claims abstract description 22
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 19
- 238000005516 engineering process Methods 0.000 claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 238000005067 remediation Methods 0.000 claims description 48
- 230000008439 repair process Effects 0.000 claims description 28
- 238000003066 decision tree Methods 0.000 claims description 22
- 230000003595 spectral effect Effects 0.000 claims description 20
- 238000011176 pooling Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 16
- 239000000126 substance Substances 0.000 claims description 15
- 238000011065 in-situ storage Methods 0.000 claims description 13
- 238000001228 spectrum Methods 0.000 claims description 11
- 239000000575 pesticide Substances 0.000 claims description 10
- 239000010865 sewage Substances 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 9
- 238000011066 ex-situ storage Methods 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 239000013043 chemical agent Substances 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims description 4
- 238000005507 spraying Methods 0.000 claims description 4
- 238000004587 chromatography analysis Methods 0.000 claims description 3
- 238000013145 classification model Methods 0.000 claims description 3
- 239000003960 organic solvent Substances 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 244000005700 microbiome Species 0.000 description 26
- 230000007613 environmental effect Effects 0.000 description 16
- 238000010206 sensitivity analysis Methods 0.000 description 7
- 238000012502 risk assessment Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000011109 contamination Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000036541 health Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000006386 neutralization reaction Methods 0.000 description 2
- 238000006479 redox reaction Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 125000001153 fluoro group Chemical group F* 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 125000004435 hydrogen atom Chemical group [H]* 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 150000004812 organic fluorine compounds Chemical class 0.000 description 1
- 239000002957 persistent organic pollutant Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006722 reduction reaction Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 230000001988 toxicity Effects 0.000 description 1
- 231100000419 toxicity Toxicity 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/62—Detectors specially adapted therefor
- G01N30/72—Mass spectrometers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
-
- 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
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- 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
- G06V10/7747—Organisation of the process, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/90—Programming languages; Computing architectures; Database systems; Data warehousing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10036—Multispectral image; Hyperspectral image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
Abstract
The application discloses a perfluoro compound pollution on-line monitoring method and system, comprising the following steps: the method comprises the steps of obtaining the position of polluted soil by using a hyperspectral remote sensing technology and a random forest algorithm, obtaining perfluorinated compound monitoring information by extracting a polluted soil sample, obtaining soil pollution prediction data by a convolutional neural network model based on the perfluorinated compound monitoring information and soil pollution source information, obtaining the pollution probability of soil with different depths based on the soil pollution prediction data, obtaining the soil pollution diffusion rate based on the soil pollution prediction data with different depths, analyzing the soil pollution diffusion rate, and making a restoration scheme for the polluted soil.
Description
Technical Field
The application relates to the field of pollution monitoring, in particular to a method and a system for monitoring pollution of a perfluorinated compound on line.
Background
The perfluoro compound is a chemical compound composed of perfluoro chain carbon, belongs to fluorinated organic compounds, and has the advantages that original hydrogen atoms in molecules of the compound are completely replaced by fluorine atoms, so that hydrocarbon bonds in the molecules are replaced by fluorocarbon bonds, the perfluoro compound has high stability, is difficult to degrade in the environment, can be enriched and accumulated in organisms, can cause lasting influence on living environment of the organisms, and is a durable organic pollutant. Soil is the root of crop planting, and the soil is polluted by organic matters and can lead to the activity reduction of the soil, the nutrition effect of the soil on crops is reduced, and even the crops have toxicity and harm to the environment and the health of human bodies. Therefore, on-line monitoring of the perfluorinated compounds in the soil is needed, the concentration of the perfluorinated compounds in the soil is obtained in real time, the restoration treatment is carried out on the soil, and the pollution source is regulated and controlled.
Disclosure of Invention
The application overcomes the defects of the prior art and provides a perfluoro compound pollution on-line monitoring method and system.
In order to achieve the above purpose, the application adopts the following technical scheme:
the application provides an on-line monitoring method for pollution of a perfluorinated compound, which comprises the following steps:
based on hyperspectral remote sensing technology and random forest algorithm, predicting and positioning the soil polluted by the perfluorinated compounds to obtain polluted soil;
dividing polluted soil into a plurality of polluted subareas, and obtaining the concentration of the perfluorinated compounds in each polluted subarea to generate perfluorinated compound monitoring information;
acquiring soil pollution source information, importing the soil pollution source information and perfluorinated compound monitoring information into a prediction model for prediction, acquiring soil pollution prediction data, acquiring a data deviation value between the soil pollution prediction data and standard soil prediction data, and acquiring the pollution probability of soil with different depths based on the data deviation value;
and acquiring soil pollution diffusion rates based on the soil pollution prediction data of different depths, analyzing the soil pollution diffusion rates, and making a restoration scheme for the polluted soil.
Further, in a preferred embodiment of the present application, the method for predicting and positioning soil contaminated by perfluorinated compounds based on hyperspectral remote sensing technology and random forest algorithm, specifically, the method comprises:
the method comprises the steps that an unmanned aerial vehicle flies above target soil, and a hyperspectral remote sensing monitor is carried on the unmanned aerial vehicle and acquires hyperspectral remote sensing data containing a plurality of continuous spectrums in the soil;
analyzing hyperspectral remote sensing data containing a plurality of continuous spectrums by using a principal component analysis method to obtain correlation values between the hyperspectral remote sensing data of the plurality of continuous spectrums and soil pollution;
based on big data retrieval, acquiring spectral features related to the pollution of the perfluorinated compounds, defining the spectral features as the spectral features of the perfluorinated compounds, and importing the spectral features of the perfluorinated compounds and associated values into a decision tree model for classification;
determining dividing points of the decision tree model based on the spectral characteristics of the perfluorinated compounds, and branching branches on the decision tree model according to conditions that the perfluorinated compounds content of soil exceeds the standard and the perfluorinated compounds content is standard based on the dividing points of the decision tree model, and stopping branching when the branching times reach a preset value to obtain a decision tree classification model;
obtaining a plurality of decision tree bifurcation models to obtain a random forest, carrying out numerical statistics treatment on the random forest, dividing target soil into soil with the content of perfluorinated compounds exceeding the standard soil and soil with the content of perfluorinated compounds exceeding the standard soil, and defining the soil with the content of perfluorinated compounds exceeding the standard soil as polluted soil.
Further, in a preferred embodiment of the present application, the method for dividing contaminated soil into a plurality of contaminated subareas, obtaining the concentration of the perfluorinated compound in each contaminated subarea, and generating the perfluorinated compound monitoring information specifically includes:
dividing the polluted soil into areas to obtain a plurality of polluted subareas;
extracting a polluted soil sample in the plurality of polluted subareas, and extracting and concentrating chemical components of the polluted soil sample by using an organic solvent to obtain a sample extracting solution;
performing compound separation on a sample extracting solution by using functional chromatography to obtain perfluorinated compounds, putting the perfluorinated compounds into a mass spectrometer, detecting the mass-to-charge ratio and the relative abundance of the perfluorinated compounds, and obtaining the concentration of the perfluorinated compounds in each polluted subarea based on the mass-to-charge ratio and the relative abundance of the perfluorinated compounds;
and based on the concentration of the perfluorinated compounds in each polluted subarea, preparing a perfluorinated compound concentration curve, and analyzing the perfluorinated compound concentration curve to obtain perfluorinated compound monitoring information.
Further, in a preferred embodiment of the present application, the obtaining soil pollution source information, importing the soil pollution source information and the perfluorocompound monitoring information into a prediction model for prediction, obtaining soil pollution prediction data, obtaining a data deviation value between the soil pollution prediction data and standard soil prediction data, and obtaining the probability of pollution of the soil at different depths based on the data deviation value, specifically includes:
based on a big data platform, acquiring soil pollution source information, wherein the soil pollution source information comprises sewage flow parameters and pesticide spraying quantity of a polluted soil position;
based on a convolutional neural network, combining the soil pollution source information and the perfluorinated compound monitoring information and importing the combined soil pollution source information and the perfluorinated compound monitoring information into a convolutional neural network model, and dividing input data into a training set and a testing set in the convolutional neural network model;
the convolution layer in the convolution neural network model carries out convolution operation on the training set to generate a convolution value, the convolution value is led into the pooling layer of the convolution neural network model to carry out maximum pooling treatment to obtain a pooling feature map, the pooling feature map carries out reverse training through a cross entropy function and is verified through a test set to generate a soil pollution prediction model;
acquiring soil pollution prediction data based on the soil pollution prediction model;
constructing a standard soil prediction model, acquiring standard soil prediction data, and performing data comparison on the standard soil prediction data and the soil pollution prediction data to obtain a data deviation value;
and importing the data deviation values into a Bayesian network for analysis to obtain the probability of the pollution of the soil with different depths.
Further, in a preferred embodiment of the present application, the method further comprises the steps of:
importing the data deviation value into a Bayesian network, determining a random variable of the Bayesian network based on the data deviation value, and acquiring Bayesian network nodes and node directed edges according to the random variable;
based on a Bayesian estimation method, obtaining a node condition probability table, constructing a Bayesian network model based on the Bayesian network nodes and the directed edges of the nodes, and importing the node condition probability table into the Bayesian network model for inversion to obtain the polluted probabilities of the soil with different depths;
and obtaining soil pollution prediction data of different depths based on the pollution probability and the soil pollution prediction data of the soil of different depths.
Further, in a preferred embodiment of the present application, the method obtains a soil pollution diffusion rate based on the soil pollution prediction data of different depths, analyzes the soil pollution diffusion rate, and makes a repair scheme for the polluted soil, specifically:
constructing a soil pollution diffusion model based on the soil pollution prediction data with different depths, and acquiring a soil pollution diffusion rate according to the soil pollution diffusion model;
analyzing the soil pollution diffusion rate, and if the soil pollution diffusion rate is smaller than a preset value, acquiring a polluted soil restoration target based on big data retrieval, wherein the polluted soil restoration target is that the concentration of the perfluorinated compounds in the soil reaches a standard value;
searching and obtaining an optimal chemical restoration method in a big data network based on the soil pollution source information and the pollution soil restoration target, adding chemical agents with preset volumes and concentrations into a soil restoration machine based on the optimal chemical restoration method, and placing the soil restoration machine on the pollution soil, wherein the soil restoration machine applies the chemical agents to the pollution soil in the pollution soil to realize in-situ restoration of the pollution soil;
the soil remediation machine comprises a perfluorinated compound concentration sensor, the perfluorinated compound concentration sensor automatically monitors the perfluorinated compound concentration in the polluted soil during the working period of the soil remediation machine, and if the perfluorinated compound concentration in the polluted soil reaches a preset value, the soil remediation machine stops working and withdraws the soil remediation machine from the polluted soil;
if the soil pollution diffusion rate is greater than a preset value, defining a reference surface in the polluted soil according to the soil pollution prediction data of different depths, excavating and conveying the soil above the reference surface into a soil remediation machine for ectopic remediation, stopping ectopic remediation when the concentration of the perfluorinated compounds in the polluted soil reaches the preset value, and filling the excavated polluted soil to the original position;
and (3) after in-situ remediation and ex-situ remediation are carried out on the polluted soil, the remediated soil is obtained, and during the in-situ remediation and ex-situ remediation of the polluted soil, the soil pollution source is regulated and optimized.
The second aspect of the present application also provides a perfluorocompound pollution on-line monitoring system, which comprises a memory and a processor, wherein the memory stores a perfluorocompound pollution on-line monitoring method, and when the perfluorocompound pollution on-line monitoring method is executed by the processor, the following steps are implemented:
based on hyperspectral remote sensing technology and random forest algorithm, predicting and positioning the soil polluted by the perfluorinated compounds to obtain polluted soil;
dividing polluted soil into a plurality of polluted subareas, and obtaining the concentration of the perfluorinated compounds in each polluted subarea to generate perfluorinated compound monitoring information;
acquiring soil pollution source information, importing the soil pollution source information and perfluorinated compound monitoring information into a prediction model for prediction, acquiring soil pollution prediction data, acquiring a data deviation value between the soil pollution prediction data and standard soil prediction data, and acquiring the pollution probability of soil with different depths based on the data deviation value;
and acquiring soil pollution diffusion rates based on the soil pollution prediction data of different depths, analyzing the soil pollution diffusion rates, and making a restoration scheme for the polluted soil.
The application solves the technical defects in the background technology, and has the following beneficial effects: the method comprises the steps of obtaining the position of polluted soil by using a hyperspectral remote sensing technology and a random forest algorithm, obtaining perfluorinated compound monitoring information by extracting a polluted soil sample, obtaining soil pollution prediction data by a convolutional neural network model based on the perfluorinated compound monitoring information and soil pollution source information, obtaining the pollution probability of soil with different depths based on the soil pollution prediction data, obtaining the soil pollution diffusion rate based on the soil pollution prediction data with different depths, analyzing the soil pollution diffusion rate, and making a restoration scheme for the polluted soil. The method can acquire the implementation concentration of the perfluorinated compounds in the polluted soil by carrying out real-time on-line monitoring on the polluted soil, and formulates a restoration method for the polluted soil. The method improves the utilization rate of soil resources, reduces the pollution to the environment, reduces the harm to human health and improves the economic benefit.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a flow chart of a method for on-line monitoring of perfluorocompound contamination;
FIG. 2 shows a flowchart for acquiring soil pollution prediction data and soil pollution prediction data of different depths;
fig. 3 shows a view of an on-line monitoring system for perfluorocompound contamination.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
FIG. 1 shows an on-line monitoring method for perfluorocompound contamination, comprising the steps of:
s102: based on hyperspectral remote sensing technology and random forest algorithm, predicting and positioning the soil polluted by the perfluorinated compounds to obtain polluted soil;
s104: dividing polluted soil into a plurality of polluted subareas, and obtaining the concentration of the perfluorinated compounds in each polluted subarea to generate perfluorinated compound monitoring information;
s106: acquiring soil pollution source information, importing the soil pollution source information and perfluorinated compound monitoring information into a prediction model for prediction, acquiring soil pollution prediction data, acquiring a data deviation value between the soil pollution prediction data and standard soil prediction data, and acquiring the pollution probability of soil with different depths based on the data deviation value;
s108: and acquiring soil pollution diffusion rates based on the soil pollution prediction data of different depths, analyzing the soil pollution diffusion rates, and making a restoration scheme for the polluted soil.
It should be noted that, the perfluorinated compounds pollute the soil, and as a result, the activity of the soil is destroyed, the environment is seriously affected, and the health and safety of human bodies are endangered when crops are planted in the soil with the perfluorinated compounds exceeding the standard. On-line monitoring of the soil that is contaminated with perfluoro compounds is required.
Further, in a preferred embodiment of the present application, the method for predicting and positioning soil contaminated by perfluorinated compounds based on hyperspectral remote sensing technology and random forest algorithm, specifically, the method comprises:
the method comprises the steps that an unmanned aerial vehicle flies above target soil, and a hyperspectral remote sensing monitor is carried on the unmanned aerial vehicle and acquires hyperspectral remote sensing data containing a plurality of continuous spectrums in the soil;
analyzing hyperspectral remote sensing data containing a plurality of continuous spectrums by using a principal component analysis method to obtain correlation values between the hyperspectral remote sensing data of the plurality of continuous spectrums and soil pollution;
based on big data retrieval, acquiring spectral features related to the pollution of the perfluorinated compounds, defining the spectral features as the spectral features of the perfluorinated compounds, and importing the spectral features of the perfluorinated compounds and associated values into a decision tree model for classification;
determining dividing points of the decision tree model based on the spectral characteristics of the perfluorinated compounds, and branching branches on the decision tree model according to conditions that the perfluorinated compounds content of soil exceeds the standard and the perfluorinated compounds content is standard based on the dividing points of the decision tree model, and stopping branching when the branching times reach a preset value to obtain a decision tree classification model;
obtaining a plurality of decision tree bifurcation models to obtain a random forest, carrying out numerical statistics treatment on the random forest, dividing target soil into soil with the content of perfluorinated compounds exceeding the standard soil and soil with the content of perfluorinated compounds exceeding the standard soil, and defining the soil with the content of perfluorinated compounds exceeding the standard soil as polluted soil.
It should be noted that hyperspectral remote sensing is a remote sensing technology, and can obtain spectral characteristics and chemical composition information of soil by obtaining reflection or radiation data of soil on a plurality of continuous and narrowband spectral bands. The main component analysis method can analyze the correlation between the hyperspectral remote sensing data of a plurality of continuous spectrums and soil pollution, the hyperspectral remote sensing data of the plurality of continuous spectrums contain the spectral characteristics of perfluorinated compounds, and the spectral characteristics of the perfluorinated compounds and the correlation values need to be classified to obtain soil areas polluted by the perfluorinated compounds. The classification method is a random forest algorithm, the random forest comprises a plurality of decision trees, branches of the decision trees are divided into the branches polluted by the perfluorinated compounds and other pollution based on the spectral characteristics of the perfluorinated compounds, when the number of branches reaches a preset value, the branches are stopped, at the moment, the decision tree model is represented as soil polluted by the perfluorinated compounds, and the decision tree models form the random forest model, so that the accuracy can be improved. And finally, carrying out statistical treatment on the data of the random forest, and defining the soil with the perfluoro compound content exceeding the standard as polluted soil. The method can obtain the position of the polluted soil through a hyperspectral remote sensing technology and a random forest algorithm.
Further, in a preferred embodiment of the present application, the method for dividing contaminated soil into a plurality of contaminated subareas, obtaining the concentration of the perfluorinated compound in each contaminated subarea, and generating the perfluorinated compound monitoring information specifically includes:
dividing the polluted soil into areas to obtain a plurality of polluted subareas;
extracting a polluted soil sample in the plurality of polluted subareas, and extracting and concentrating chemical components of the polluted soil sample by using an organic solvent to obtain a sample extracting solution;
performing compound separation on a sample extracting solution by using functional chromatography to obtain perfluorinated compounds, putting the perfluorinated compounds into a mass spectrometer, detecting the mass-to-charge ratio and the relative abundance of the perfluorinated compounds, and obtaining the concentration of the perfluorinated compounds in each polluted subarea based on the mass-to-charge ratio and the relative abundance of the perfluorinated compounds;
and based on the concentration of the perfluorinated compounds in each polluted subarea, preparing a perfluorinated compound concentration curve, and analyzing the perfluorinated compound concentration curve to obtain perfluorinated compound monitoring information.
It should be noted that the contaminated soil may be unevenly distributed, so that it is necessary to divide the contaminated soil into separate areas to obtain a plurality of contaminated sub-areas. The detection of the soil by using the hyperspectral remote sensing technology is preliminary detection, the concentration of the perfluorinated compounds in the soil cannot be clearly obtained, samples are extracted from a plurality of pollution subareas to detect the perfluorinated compounds, and perfluorinated compound monitoring information is generated according to the perfluorinated compounds. According to the application, the perfluorinated compound monitoring information can be obtained by detecting the perfluorinated compound concentration of the soil.
Further, in a preferred embodiment of the present application, the method obtains a soil pollution diffusion rate based on the soil pollution prediction data of different depths, analyzes the soil pollution diffusion rate, and makes a repair scheme for the polluted soil, specifically:
constructing a soil pollution diffusion model based on the soil pollution prediction data with different depths, and acquiring a soil pollution diffusion rate according to the soil pollution diffusion model;
analyzing the soil pollution diffusion rate, and if the soil pollution diffusion rate is smaller than a preset value, acquiring a polluted soil restoration target based on big data retrieval, wherein the polluted soil restoration target is that the concentration of the perfluorinated compounds in the soil reaches a standard value;
searching and obtaining an optimal chemical restoration method in a big data network based on the soil pollution source information and the pollution soil restoration target, adding chemical agents with preset volumes and concentrations into a soil restoration machine based on the optimal chemical restoration method, and placing the soil restoration machine on the pollution soil, wherein the soil restoration machine applies the chemical agents to the pollution soil in the pollution soil to realize in-situ restoration of the pollution soil;
the soil remediation machine comprises a perfluorinated compound concentration sensor, the perfluorinated compound concentration sensor automatically monitors the perfluorinated compound concentration in the polluted soil during the working period of the soil remediation machine, and if the perfluorinated compound concentration in the polluted soil reaches a preset value, the soil remediation machine stops working and withdraws the soil remediation machine from the polluted soil;
if the soil pollution diffusion rate is greater than a preset value, defining a reference surface in the polluted soil according to the soil pollution prediction data of different depths, excavating and conveying the soil above the reference surface into a soil remediation machine for ectopic remediation, stopping ectopic remediation when the concentration of the perfluorinated compounds in the polluted soil reaches the preset value, and filling the excavated polluted soil to the original position;
and (3) after in-situ remediation and ex-situ remediation are carried out on the polluted soil, the remediated soil is obtained, and during the in-situ remediation and ex-situ remediation of the polluted soil, the soil pollution source is regulated and optimized.
The method is characterized in that the concentration of the perfluorinated compounds in the soil exceeds the standard, the soil is influenced by sewage and pesticides, the perfluorinated compounds are diffused along with the diffusion of the sewage and the pesticides, the upper soil and the lower soil are polluted, the pollution of the sewage and the pesticides to the soil is influenced from top to bottom, and the perfluorinated compounds in the upper soil have higher concentration. The soil pollution diffusion rate reflects the diffusion rate of perfluoro compounds in the soil. When the soil pollution diffusion rate is smaller than a preset value, the perfluoro compound proves that the infiltration rate of the perfluoro compound to the soil is slower, and the lower soil is not easily affected by the upper soil, so that the soil is restored in situ. The in-situ remediation is to directly remediate the polluted soil on site of the polluted soil, and the used remediation mode is chemical remediation. The chemical restoration is to add chemical substances into the soil, so that oxidation-reduction reaction or neutralization reaction is carried out on sewage, pesticide, microorganism and the like in the soil, and the concentration of the perfluorinated compound is reduced. The soil remediation machine can save manpower and material resources, can realize the accurate throwing of chemical substances, and accords with economic benefits. In the repairing process, the soil repairing machine can also excavate and loosen the soil, and the excavation and loosening treatment can increase the gap in the soil, so that the gas generated by oxidation-reduction reaction or neutralization reaction can be discharged, and the repairing efficiency is improved. The perfluorinated compound concentration sensor can monitor the perfluorinated compound concentration in the polluted soil in real time, and when the perfluorinated compound concentration reaches a preset value, the soil remediation machine stops working. When the soil pollution diffusion rate is larger than a preset value, the pollution degree of the polluted soil is larger, the influence on the soil below the polluted soil is larger, and if in-situ restoration is carried out, the restoration speed can not keep up with the pollution diffusion rate, so that the polluted soil needs to be restored in an out-of-position mode. The ex-situ remediation is to excavate and carry the polluted soil to another place for soil remediation, and when the soil remediation is completed, the excavated polluted soil is refilled to the original position. During the remediation of contaminated soil, the discharge of sewage needs to be controlled and the sewage needs to be filtered, and meanwhile, the discharge of pesticides needs to be reduced or pesticides or fertilizers of different varieties need to be replaced. The application can implement in-situ remediation or ex-situ remediation on the contaminated soil by analyzing the soil pollution diffusion rate, and obtain the remediated soil.
FIG. 2 shows a flowchart for acquiring soil pollution prediction data and soil pollution prediction data of different depths, comprising the steps of:
s202: acquiring soil pollution prediction data based on a convolutional neural network model;
s204: comparing the soil pollution prediction data with standard soil prediction data to obtain a data deviation value;
s206: and acquiring soil pollution prediction data of different depths based on the Bayesian network.
Further, in a preferred embodiment of the present application, the soil pollution prediction data is obtained based on a convolutional neural network model, specifically:
based on a big data platform, acquiring soil pollution source information, wherein the soil pollution source information comprises sewage flow parameters and pesticide spraying quantity of a polluted soil position;
based on a convolutional neural network, combining the soil pollution source information and the perfluorinated compound monitoring information and importing the combined soil pollution source information and the perfluorinated compound monitoring information into a convolutional neural network model, and dividing input data into a training set and a testing set in the convolutional neural network model;
the convolution layer in the convolution neural network model carries out convolution operation on the training set to generate a convolution value, the convolution value is led into the pooling layer of the convolution neural network model to carry out maximum pooling treatment to obtain a pooling feature map, the pooling feature map carries out reverse training through a cross entropy function and is verified through a test set to generate a soil pollution prediction model;
and acquiring soil pollution prediction data based on the soil pollution prediction model.
In order to obtain the future pollution condition of the polluted soil, the polluted soil needs to be subjected to prediction treatment, and the convolutional neural network can obtain the prediction data of the soil pollution. Combining soil pollution source information and perfluorinated compound monitoring information, and introducing the combined soil pollution source information and perfluorinated compound monitoring information into a convolutional neural network model for model training, wherein the model training comprises convolutional treatment, pooling treatment and reverse training treatment on a training set, and finally, verifying through a testing set to generate a soil pollution prediction model and obtain soil pollution prediction data. According to the application, soil pollution prediction data can be obtained through a convolutional neural network model.
Further, in a preferred embodiment of the present application, the acquiring soil pollution prediction data with different depths based on the bayesian network specifically includes:
importing the data deviation value into a Bayesian network, determining a random variable of the Bayesian network based on the data deviation value, and acquiring Bayesian network nodes and node directed edges according to the random variable;
based on a Bayesian estimation method, obtaining a node condition probability table, constructing a Bayesian network model based on the Bayesian network nodes and the directed edges of the nodes, and importing the node condition probability table into the Bayesian network model for inversion to obtain the polluted probabilities of the soil with different depths;
and obtaining soil pollution prediction data of different depths based on the pollution probability and the soil pollution prediction data of the soil of different depths.
The bayesian network can calculate the probability distribution of other variables from the known observation values and model structures, and in the present application, the cause of contamination at a point in the soil can be estimated. There are directed edges of nodes between variables, which embody the dependency between variables. The Bayesian network node represents a random variable which is related to the variable of the concentration of the perfluorinated compound in the soil, the node condition probability table defines the condition probability of the Bayesian network node, and the probability of the soil with different depths can be obtained based on the condition probability table. Based on the probability of contamination of the soil at different depths and the soil pollution prediction data, soil pollution prediction data at different depths can be obtained, wherein the soil pollution prediction data at different depths represent the change condition of the concentration of perfluorinated compounds in the soil at different depths. According to the application, soil pollution prediction data with different depths can be obtained through a Bayesian network.
In addition, the on-line monitoring method for the pollution of the perfluorinated compounds further comprises the following steps:
before the polluted soil is restored, acquiring environmental parameters of the polluted soil based on big data retrieval;
obtaining microorganism types capable of repairing the polluted soil, and screening the microorganism types based on the environmental parameters of the polluted soil;
screening to obtain microbial species suitable for survival under environmental parameters of the polluted soil, defining the microbial species as repair microorganisms, extracting a polluted soil sample from the polluted soil, performing sample repair on the polluted soil sample by using the repair microorganisms, recording the change efficiency of the concentration of the perfluorinated compounds in the polluted soil during sample repair, and generating a change efficiency statistical table;
according to the change efficiency statistical table, selecting the corresponding microorganism type with the highest change efficiency as the repairing microorganism for the polluted soil, defining the microorganism type as the optimal repairing microorganism, and enabling the optimal repairing microorganism to carry out bioremediation treatment on the polluted soil through a soil repairing machine.
In addition to the chemical remediation method, a biological remediation method may be used as a method for remediating contaminated soil. The bioremediation method is to add a proper amount of microorganisms into the polluted soil, and the microorganisms degrade perfluorinated compounds in the polluted soil so as to achieve the aim of restoring the polluted soil. Different kinds of microorganisms have specific living environments, and when the temperature, humidity and other values in the living environments are higher or lower, the microorganisms may lose activity, and the microorganisms at the moment have no restoration effect on the polluted soil, so that the microorganisms meeting the conditions need to be screened through the environmental parameters of the polluted soil. The purpose of sample repair of the repair microorganisms is to judge the repair microorganism with the highest repair efficiency of the contaminated soil among various repair microorganisms, define the repair microorganism as the optimal repair microorganism, and use the optimal repair microorganism to carry out biological repair treatment on the contaminated soil. The application can obtain the optimal repairing microorganism through the screening of the environmental parameters of the polluted soil, and carry out bioremediation on the polluted soil.
In addition, the method further comprises the following steps:
acquiring the environmental conditions around the polluted soil, carrying out environmental sensitivity analysis on the environmental conditions around the polluted soil to obtain an environmental sensitivity analysis result, and carrying out risk assessment on the environmental conditions around the polluted soil to obtain a risk assessment result;
combining the environmental sensitivity analysis result and the risk assessment result, formulating a polluted soil restoration method, and carrying out feasibility analysis on the polluted soil restoration method;
based on big data retrieval, acquiring life habits of the area where the polluted soil is located, and formulating a restoration sequence of the polluted soil according to the life habits of the area where the polluted soil is located and a restoration method of the polluted soil;
and carrying out repair work on the polluted soil based on the repair sequence of the polluted soil, monitoring the concentration of the perfluorinated compounds in the polluted soil and the surrounding environment conditions in real time during the repair of the polluted soil, and properly adjusting the repair sequence and the repair method.
It should be noted that, there may be water, vegetation, crops, residential buildings, etc. around the contaminated soil, and the contaminated soil may be affected during the remediation of the contaminated soil. For example, chemical agents and microorganisms pollute water bodies and vegetation, destroy crops or affect daily life of residents, so environmental sensitivity analysis and risk assessment are required for environmental conditions around the polluted soil, and the environmental sensitivity analysis can analyze the sensitivity of the surrounding environment and determine a sensitive area possibly affected by the environmental sensitivity analysis; risk assessment can determine the priority of contaminated soil remediation. And (3) based on the environmental sensitivity analysis result and the risk assessment result, formulating a repair method of the polluted soil, and carrying out feasibility analysis, wherein the feasibility analysis can analyze whether the repair method can be effectively applied to the current soil pollution condition and the surrounding environment. The purpose of acquiring the habit of the area where the polluted soil is located is to prevent the operation of disturbing the residents during the restoration, for example, the life habits of areas with different longitudes and latitudes are different, so that the rest time and the working time are different, the soil restoration machine is started in the rest time period, and noise is generated to influence the daily rest of residents. Based on the steps, the repair sequence of the polluted soil is formulated, the repair condition is monitored in real time during the repair period, and the repair sequence and the repair method are properly adjusted. The application can combine the surrounding environment conditions of the polluted soil to formulate a soil restoration method and a restoration sequence.
As shown in fig. 3, the second aspect of the present application further provides a perfluorocompound pollution online monitoring system, which includes a memory 31 and a processor 32, wherein the memory 41 stores a perfluorocompound pollution online monitoring method, and when the perfluorocompound pollution online monitoring method is executed by the processor 32, the following steps are implemented:
based on hyperspectral remote sensing technology and random forest algorithm, predicting and positioning the soil polluted by the perfluorinated compounds to obtain polluted soil;
dividing polluted soil into a plurality of polluted subareas, and obtaining the concentration of the perfluorinated compounds in each polluted subarea to generate perfluorinated compound monitoring information;
acquiring soil pollution source information, importing the soil pollution source information and perfluorinated compound monitoring information into a prediction model for prediction, acquiring soil pollution prediction data, acquiring a data deviation value between the soil pollution prediction data and standard soil prediction data, and acquiring the pollution probability of soil with different depths based on the data deviation value;
and acquiring soil pollution diffusion rates based on the soil pollution prediction data of different depths, analyzing the soil pollution diffusion rates, and making a restoration scheme for the polluted soil.
The foregoing is merely illustrative embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present application, and the application should be covered. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (5)
1. The on-line monitoring method for the pollution of the perfluorinated compounds is characterized by comprising the following steps of:
based on hyperspectral remote sensing technology and random forest algorithm, predicting and positioning the soil polluted by the perfluorinated compounds to obtain polluted soil;
dividing polluted soil into a plurality of polluted subareas, and obtaining the concentration of the perfluorinated compounds in each polluted subarea to generate perfluorinated compound monitoring information;
acquiring soil pollution source information, importing the soil pollution source information and perfluorinated compound monitoring information into a prediction model for prediction, acquiring soil pollution prediction data, acquiring a data deviation value between the soil pollution prediction data and standard soil prediction data, and acquiring the pollution probability of soil with different depths based on the data deviation value;
based on the soil pollution prediction data of different depths, acquiring a soil pollution diffusion rate, analyzing the soil pollution diffusion rate, and making a restoration scheme for the polluted soil;
the method comprises the steps of obtaining soil pollution source information, guiding the soil pollution source information and perfluoro compound monitoring information into a prediction model for prediction, obtaining soil pollution prediction data, obtaining a data deviation value between the soil pollution prediction data and standard soil prediction data, and obtaining the pollution probability of soil with different depths based on the data deviation value, wherein the concrete steps are as follows:
based on a big data platform, acquiring soil pollution source information, wherein the soil pollution source information comprises sewage flow parameters and pesticide spraying quantity of a polluted soil position;
based on a convolutional neural network, combining the soil pollution source information and the perfluorinated compound monitoring information and importing the combined soil pollution source information and the perfluorinated compound monitoring information into a convolutional neural network model, and dividing input data into a training set and a testing set in the convolutional neural network model;
the convolution layer in the convolution neural network model carries out convolution operation on the training set to generate a convolution value, the convolution value is led into the pooling layer of the convolution neural network model to carry out maximum pooling treatment to obtain a pooling feature map, the pooling feature map carries out reverse training through a cross entropy function and is verified through a test set to generate a soil pollution prediction model;
acquiring soil pollution prediction data based on the soil pollution prediction model;
constructing a standard soil prediction model, acquiring standard soil prediction data, and performing data comparison on the standard soil prediction data and the soil pollution prediction data to obtain a data deviation value;
the data deviation values are imported into a Bayesian network for analysis, so that the pollution probabilities of the soil with different depths are obtained;
wherein, still include the following step:
importing the data deviation value into a Bayesian network, determining a random variable of the Bayesian network based on the data deviation value, and acquiring Bayesian network nodes and node directed edges according to the random variable;
based on a Bayesian estimation method, obtaining a node condition probability table, constructing a Bayesian network model based on the Bayesian network nodes and the directed edges of the nodes, and importing the node condition probability table into the Bayesian network model for inversion to obtain the polluted probabilities of the soil with different depths;
and obtaining soil pollution prediction data of different depths based on the pollution probability and the soil pollution prediction data of the soil of different depths.
2. The online monitoring method of perfluorocompound pollution according to claim 1, wherein the method is characterized in that soil polluted by perfluorocompound is predicted and positioned based on hyperspectral remote sensing technology and random forest algorithm to obtain polluted soil, and specifically comprises the following steps:
the method comprises the steps that an unmanned aerial vehicle flies above target soil, and a hyperspectral remote sensing monitor is carried on the unmanned aerial vehicle and acquires hyperspectral remote sensing data containing a plurality of continuous spectrums in the soil;
analyzing hyperspectral remote sensing data containing a plurality of continuous spectrums by using a principal component analysis method to obtain correlation values between the hyperspectral remote sensing data of the plurality of continuous spectrums and soil pollution;
based on big data retrieval, acquiring spectral features related to the pollution of the perfluorinated compounds, defining the spectral features as the spectral features of the perfluorinated compounds, and importing the spectral features of the perfluorinated compounds and associated values into a decision tree model for classification;
determining dividing points of the decision tree model based on the spectral characteristics of the perfluorinated compounds, and branching branches on the decision tree model according to conditions that the perfluorinated compounds content of soil exceeds the standard and the perfluorinated compounds content is standard based on the dividing points of the decision tree model, and stopping branching when the branching times reach a preset value to obtain a decision tree classification model;
obtaining a plurality of decision tree bifurcation models to obtain a random forest, carrying out numerical statistics treatment on the random forest, dividing target soil into soil with the content of perfluorinated compounds exceeding the standard soil and soil with the content of perfluorinated compounds exceeding the standard soil, and defining the soil with the content of perfluorinated compounds exceeding the standard soil as polluted soil.
3. The online monitoring method for perfluorocompound pollution according to claim 1, wherein the method is characterized in that the polluted soil is divided into a plurality of polluted subareas, the concentration of the perfluorocompound in each polluted subarea is obtained, and the perfluorocompound monitoring information is generated, specifically:
dividing the polluted soil into areas to obtain a plurality of polluted subareas;
extracting a polluted soil sample in the plurality of polluted subareas, and extracting and concentrating chemical components of the polluted soil sample by using an organic solvent to obtain a sample extracting solution;
performing compound separation on a sample extracting solution by using functional chromatography to obtain perfluorinated compounds, putting the perfluorinated compounds into a mass spectrometer, detecting the mass-to-charge ratio and the relative abundance of the perfluorinated compounds, and obtaining the concentration of the perfluorinated compounds in each polluted subarea based on the mass-to-charge ratio and the relative abundance of the perfluorinated compounds;
and based on the concentration of the perfluorinated compounds in each polluted subarea, preparing a perfluorinated compound concentration curve, and analyzing the perfluorinated compound concentration curve to obtain perfluorinated compound monitoring information.
4. The online monitoring method of perfluoro compound pollution according to claim 1, wherein the method is characterized in that based on the predicted data of soil pollution at different depths, the soil pollution diffusion rate is obtained, the soil pollution diffusion rate is analyzed, and a repair scheme is formulated for the polluted soil, specifically:
constructing a soil pollution diffusion model based on the soil pollution prediction data with different depths, and acquiring a soil pollution diffusion rate according to the soil pollution diffusion model;
analyzing the soil pollution diffusion rate, and if the soil pollution diffusion rate is smaller than a preset value, acquiring a polluted soil restoration target based on big data retrieval, wherein the polluted soil restoration target is that the concentration of the perfluorinated compounds in the soil reaches a standard value;
searching and obtaining an optimal chemical restoration method in a big data network based on the soil pollution source information and the pollution soil restoration target, adding chemical agents with preset volumes and concentrations into a soil restoration machine based on the optimal chemical restoration method, and placing the soil restoration machine on the pollution soil, wherein the soil restoration machine applies the chemical agents to the pollution soil in the pollution soil to realize in-situ restoration of the pollution soil;
the soil remediation machine comprises a perfluorinated compound concentration sensor, the perfluorinated compound concentration sensor automatically monitors the perfluorinated compound concentration in the polluted soil during the working period of the soil remediation machine, and if the perfluorinated compound concentration in the polluted soil reaches a preset value, the soil remediation machine stops working and withdraws the soil remediation machine from the polluted soil;
if the soil pollution diffusion rate is greater than a preset value, defining a reference surface in the polluted soil according to the soil pollution prediction data of different depths, excavating and conveying the soil above the reference surface into a soil remediation machine for ectopic remediation, stopping ectopic remediation when the concentration of the perfluorinated compounds in the polluted soil reaches the preset value, and filling the excavated polluted soil to the original position;
and (3) after in-situ remediation and ex-situ remediation are carried out on the polluted soil, the remediated soil is obtained, and during the in-situ remediation and ex-situ remediation of the polluted soil, the soil pollution source is regulated and optimized.
5. The online monitoring system for the pollution of the perfluorinated compound is characterized by comprising a memory and a processor, wherein the memory stores an online monitoring method for the pollution of the perfluorinated compound, and when the online monitoring method for the pollution of the perfluorinated compound is executed by the processor, the following steps are realized:
based on hyperspectral remote sensing technology and random forest algorithm, predicting and positioning the soil polluted by the perfluorinated compounds to obtain polluted soil;
dividing polluted soil into a plurality of polluted subareas, and obtaining the concentration of the perfluorinated compounds in each polluted subarea to generate perfluorinated compound monitoring information;
acquiring soil pollution source information, importing the soil pollution source information and perfluorinated compound monitoring information into a prediction model for prediction, acquiring soil pollution prediction data, acquiring a data deviation value between the soil pollution prediction data and standard soil prediction data, and acquiring the pollution probability of soil with different depths based on the data deviation value;
based on the soil pollution prediction data of different depths, acquiring a soil pollution diffusion rate, analyzing the soil pollution diffusion rate, and making a restoration scheme for the polluted soil;
the method comprises the steps of obtaining soil pollution source information, guiding the soil pollution source information and perfluoro compound monitoring information into a prediction model for prediction, obtaining soil pollution prediction data, obtaining a data deviation value between the soil pollution prediction data and standard soil prediction data, and obtaining the pollution probability of soil with different depths based on the data deviation value, wherein the concrete steps are as follows:
based on a big data platform, acquiring soil pollution source information, wherein the soil pollution source information comprises sewage flow parameters and pesticide spraying quantity of a polluted soil position;
based on a convolutional neural network, combining the soil pollution source information and the perfluorinated compound monitoring information and importing the combined soil pollution source information and the perfluorinated compound monitoring information into a convolutional neural network model, and dividing input data into a training set and a testing set in the convolutional neural network model;
the convolution layer in the convolution neural network model carries out convolution operation on the training set to generate a convolution value, the convolution value is led into the pooling layer of the convolution neural network model to carry out maximum pooling treatment to obtain a pooling feature map, the pooling feature map carries out reverse training through a cross entropy function and is verified through a test set to generate a soil pollution prediction model;
acquiring soil pollution prediction data based on the soil pollution prediction model;
constructing a standard soil prediction model, acquiring standard soil prediction data, and performing data comparison on the standard soil prediction data and the soil pollution prediction data to obtain a data deviation value;
the data deviation values are imported into a Bayesian network for analysis, so that the pollution probabilities of the soil with different depths are obtained;
wherein, still include the following step:
importing the data deviation value into a Bayesian network, determining a random variable of the Bayesian network based on the data deviation value, and acquiring Bayesian network nodes and node directed edges according to the random variable;
based on a Bayesian estimation method, obtaining a node condition probability table, constructing a Bayesian network model based on the Bayesian network nodes and the directed edges of the nodes, and importing the node condition probability table into the Bayesian network model for inversion to obtain the polluted probabilities of the soil with different depths;
and obtaining soil pollution prediction data of different depths based on the pollution probability and the soil pollution prediction data of the soil of different depths.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311080843.2A CN116773465B (en) | 2023-08-25 | 2023-08-25 | Perfluoro compound pollution on-line monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311080843.2A CN116773465B (en) | 2023-08-25 | 2023-08-25 | Perfluoro compound pollution on-line monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116773465A CN116773465A (en) | 2023-09-19 |
| CN116773465B true CN116773465B (en) | 2023-10-27 |
Family
ID=88013802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311080843.2A Active CN116773465B (en) | 2023-08-25 | 2023-08-25 | Perfluoro compound pollution on-line monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116773465B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117475338B (en) * | 2023-12-28 | 2024-03-29 | 山东舜捷资源综合利用有限公司 | Land reclamation repair process monitoring system based on land management |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4599820A (en) * | 1984-10-26 | 1986-07-15 | Hill Loren G | Method and apparatus for selecting fishing lure color |
| KR101952610B1 (en) * | 2018-07-20 | 2019-03-04 | 주식회사 효림 | IOT based contamination area fate modeling system by real time monitoring of in-situ contaminated soil purification well |
| KR101952605B1 (en) * | 2018-07-20 | 2019-03-04 | 주식회사 효림 | IOT based real time monitoring system of in-situ contaminated soil purification well |
| KR20220012683A (en) * | 2020-07-23 | 2022-02-04 | 부산대학교 산학협력단 | Soil Pollution Source Prediction Method using Artificial Neural Network Model |
| WO2022069827A1 (en) * | 2020-09-30 | 2022-04-07 | Tellux | Method for analyzing soil pollution |
| CN114742272A (en) * | 2022-03-10 | 2022-07-12 | 浙江大学 | Soil cadmium risk prediction method based on space-time interaction relation |
| CN114993965A (en) * | 2022-05-13 | 2022-09-02 | 中煤嘉沣(湖南)环保科技有限责任公司 | Automatic pollution source identification method and system |
| WO2023070939A1 (en) * | 2021-10-26 | 2023-05-04 | 浙江大学 | Soil multi-pollutant recognition probe based on multispectral and time domain reflectometry, and method |
| CN116168771A (en) * | 2023-04-26 | 2023-05-26 | 北京建工环境修复股份有限公司 | Method and system for monitoring pollution of perfluorinated compounds in river based on Internet of things |
| DE202023102685U1 (en) * | 2022-05-20 | 2023-06-13 | Municipal Environmental Protection Engineering Co., Ltd Of Crec Shanghai Group | One-dimensional multi-depth simulation device for predicting contaminant migration |
| CN116362571A (en) * | 2023-06-02 | 2023-06-30 | 北京建工环境修复股份有限公司 | Multi-source pollution space-time characteristic analysis method and system based on deep learning |
| CN116629619A (en) * | 2023-07-25 | 2023-08-22 | 北京建工环境修复股份有限公司 | Method and system for predicting occurrence condition of new soil pollutants |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140012504A1 (en) * | 2012-06-14 | 2014-01-09 | Ramot At Tel-Aviv University Ltd. | Quantitative assessment of soil contaminants, particularly hydrocarbons, using reflectance spectroscopy |
| US9579700B2 (en) * | 2014-05-30 | 2017-02-28 | Iteris, Inc. | Measurement and modeling of salinity contamination of soil and soil-water systems from oil and gas production activities |
| KR102624476B1 (en) * | 2021-12-24 | 2024-01-12 | 충남대학교산학협력단 | Method of detecting soil contaminated with petroleum compounds using hyperspectral analysis |
-
2023
- 2023-08-25 CN CN202311080843.2A patent/CN116773465B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4599820A (en) * | 1984-10-26 | 1986-07-15 | Hill Loren G | Method and apparatus for selecting fishing lure color |
| KR101952610B1 (en) * | 2018-07-20 | 2019-03-04 | 주식회사 효림 | IOT based contamination area fate modeling system by real time monitoring of in-situ contaminated soil purification well |
| KR101952605B1 (en) * | 2018-07-20 | 2019-03-04 | 주식회사 효림 | IOT based real time monitoring system of in-situ contaminated soil purification well |
| KR20220012683A (en) * | 2020-07-23 | 2022-02-04 | 부산대학교 산학협력단 | Soil Pollution Source Prediction Method using Artificial Neural Network Model |
| WO2022069827A1 (en) * | 2020-09-30 | 2022-04-07 | Tellux | Method for analyzing soil pollution |
| WO2023070939A1 (en) * | 2021-10-26 | 2023-05-04 | 浙江大学 | Soil multi-pollutant recognition probe based on multispectral and time domain reflectometry, and method |
| CN114742272A (en) * | 2022-03-10 | 2022-07-12 | 浙江大学 | Soil cadmium risk prediction method based on space-time interaction relation |
| CN114993965A (en) * | 2022-05-13 | 2022-09-02 | 中煤嘉沣(湖南)环保科技有限责任公司 | Automatic pollution source identification method and system |
| DE202023102685U1 (en) * | 2022-05-20 | 2023-06-13 | Municipal Environmental Protection Engineering Co., Ltd Of Crec Shanghai Group | One-dimensional multi-depth simulation device for predicting contaminant migration |
| CN116168771A (en) * | 2023-04-26 | 2023-05-26 | 北京建工环境修复股份有限公司 | Method and system for monitoring pollution of perfluorinated compounds in river based on Internet of things |
| CN116362571A (en) * | 2023-06-02 | 2023-06-30 | 北京建工环境修复股份有限公司 | Multi-source pollution space-time characteristic analysis method and system based on deep learning |
| CN116629619A (en) * | 2023-07-25 | 2023-08-22 | 北京建工环境修复股份有限公司 | Method and system for predicting occurrence condition of new soil pollutants |
Non-Patent Citations (2)
| Title |
|---|
| 基于数值模拟的土壤重金属铬污染预测分析;彭盼盼;伍靖伟;刘聪;彭翔;李银;刘瑜;;中国农村水利水电(第08期);第196-200页 * |
| 浑河冲洪积扇土壤硝酸盐污染特征及相关因素分析;左锐;盖鹏;滕彦国;王金生;孙岳;;南水北调与水利科技(第04期);第46-50页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116773465A (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| O'Connor et al. | Phytoremediation: Climate change resilience and sustainability assessment at a coastal brownfield redevelopment | |
| Appel et al. | The Community Multiscale Air Quality (CMAQ) model versions 5.3 and 5.3. 1: system updates and evaluation | |
| Fenn et al. | Empirical and simulated critical loads for nitrogen deposition in California mixed conifer forests | |
| CN116773465B (en) | Perfluoro compound pollution on-line monitoring method and system | |
| Di Bella et al. | Evaluation of methane emissions from Palermo municipal landfill: Comparison between field measurements and models | |
| CN104103005B (en) | The source tracing method of sudden water environment event pollution sources under a kind of limited conditions | |
| Uriarte et al. | Linking spatial patterns of leaf litterfall and soil nutrients in a tropical forest: a neighborhood approach | |
| Di Luzio et al. | Formulation of a hybrid calibration approach for a physically based distributed model with NEXRAD data input | |
| CN115494047B (en) | Detection method and system for agricultural pollutants in water environment | |
| CN116384776B (en) | Site pollution evaluation method, system and storage medium based on fuzzy evaluation | |
| CN116362572B (en) | Regional and hierarchical evaluation method for groundwater pollution in production park | |
| Green et al. | Methane and carbon dioxide fluxes from open and blocked ditches in a blanket bog | |
| Liu et al. | A Bayesian approach to understanding the key factors influencing temporal variability in stream water quality–a case study in the Great Barrier Reef catchments | |
| Duenas et al. | Stochastic model to forecast ground-level ozone concentration at urban and rural areas | |
| Shashikumar et al. | The effect of ozone on pine forests in South-Eastern France from 2017 to 2019 | |
| Pérez-Indoval et al. | PWC-based evaluation of groundwater pesticide pollution in the Júcar River Basin | |
| Pärn | Radial growth response of Scots pine to climate under dust pollution in Northeast Estonia | |
| Franzaring | Temperature and concentration effects in biomonitoring of organic air pollutants | |
| Borrego et al. | Air quality management in Portugal: example of needs and available tools | |
| Shrestha et al. | Assessment of catchment response and calibration of a hydrological model using high-frequency discharge–nitrate concentration data | |
| Stretch et al. | Odour trails from landfill sites | |
| Russo et al. | A stormwater management framework for predicting first flush intensity and quantifying its influential factors | |
| Huber et al. | Sensitivity of modeled soil NOx emissions to soil moisture | |
| Chang et al. | Comparison of models of simazine transport and fate in the subsurface environment in a citrus farm | |
| Vesenmaier et al. | Fugitive methane and odour emission characterization at a composting plant using remote sensing measurements |
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 |