NL2034211A - Method and system for quantitatively identifying multi-pollution sources of mixed water body - Google Patents

Method and system for quantitatively identifying multi-pollution sources of mixed water body Download PDF

Info

Publication number
NL2034211A
NL2034211A NL2034211A NL2034211A NL2034211A NL 2034211 A NL2034211 A NL 2034211A NL 2034211 A NL2034211 A NL 2034211A NL 2034211 A NL2034211 A NL 2034211A NL 2034211 A NL2034211 A NL 2034211A
Authority
NL
Netherlands
Prior art keywords
pollution
mixed water
water body
spectrum data
sources
Prior art date
Application number
NL2034211A
Other languages
Dutch (nl)
Other versions
NL2034211B1 (en
Inventor
Zhao Zhuangming
Lin Qiaoyun
Yang Jing
Xu Min
Original Assignee
South China Institute Of Environmental Sciences Mee Res Institute Of Eco Environmental Emergency Mee
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by South China Institute Of Environmental Sciences Mee Res Institute Of Eco Environmental Emergency Mee filed Critical South China Institute Of Environmental Sciences Mee Res Institute Of Eco Environmental Emergency Mee
Publication of NL2034211A publication Critical patent/NL2034211A/en
Application granted granted Critical
Publication of NL2034211B1 publication Critical patent/NL2034211B1/en

Links

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
    • G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
    • G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
    • G01N21/64—Fluorescence; Phosphorescence
    • G01N21/6428—Measuring fluorescence of fluorescent products of reactions or of fluorochrome labelled reactive substances, e.g. measuring quenching effects, using measuring "optrodes"
    • G01N21/643—Measuring fluorescence of fluorescent products of reactions or of fluorochrome labelled reactive substances, e.g. measuring quenching effects, using measuring "optrodes" non-biological material
    • 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
    • G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
    • G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
    • G01N21/64—Fluorescence; Phosphorescence
    • G01N21/6402—Atomic fluorescence; Laser induced fluorescence
    • 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
    • G01N21/01—Arrangements or apparatus for facilitating the optical investigation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/18—Water
    • 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
    • G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
    • G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
    • G01N21/64—Fluorescence; Phosphorescence
    • G01N2021/6417—Spectrofluorimetric devices
    • 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
    • G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
    • G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
    • G01N21/64—Fluorescence; Phosphorescence
    • G01N21/6428—Measuring fluorescence of fluorescent products of reactions or of fluorochrome labelled reactive substances, e.g. measuring quenching effects, using measuring "optrodes"
    • G01N2021/6439—Measuring fluorescence of fluorescent products of reactions or of fluorochrome labelled reactive substances, e.g. measuring quenching effects, using measuring "optrodes" with indicators, stains, dyes, tags, labels, marks
    • G01N2021/6441—Measuring fluorescence of fluorescent products of reactions or of fluorochrome labelled reactive substances, e.g. measuring quenching effects, using measuring "optrodes" with indicators, stains, dyes, tags, labels, marks with two or more labels
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2201/00—Features of devices classified in G01N21/00
    • G01N2201/12—Circuits of general importance; Signal processing
    • G01N2201/129—Using chemometrical methods
    • G01N2201/1296—Using chemometrical methods 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
    • Y02A20/20—Controlling water pollution; Waste water treatment

Landscapes

  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Immunology (AREA)
  • General Health & Medical Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Physics & Mathematics (AREA)
  • Pathology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Optics & Photonics (AREA)
  • Molecular Biology (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Engineering & Computer Science (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)

Abstract

Disclosed are a method and system for quantitatively identifying multi—pollution sources in a mixed water body. The method includes: acquiring a single—pollution source sample and performing three—dimensional fluorescence spectrum measurement to 5 obtain single—pollution source three—dimensional fluorescence spectrum data; mixing the single—pollution source three— dimensional fluorescence spectrum data to obtain a pollution source three—dimensional fluorescence spectrum data set; training a pre—constructed quantitative identification model of multi— lO pollution sources in a mixed water body using the pollution source three—dimensional fluorescence spectrum data set to obtain a quantitative identification model of multi—pollution sources in a mixed, water~ body; and, quantitatively identifying, based, on the quantitative identification model of multi—pollution sources in a 15 mixed water body, a sample to be tested to obtain a sample—to—be— tested quantitative identification result. The system includes: a measurement module, a mixing module, a training module, and a quantitative identification module. 20 (+ Fig. l)

Description

METHOD AND SYSTEM FOR QUANTITATIVELY IDENTIFYING MULTI-POLLUTION
SOURCES OF MIXED WATER BODY
TECHNICAL FIELD
The present invention relates to the technical field of envi- ronmental supervision, and in particular to a method and system for quantitatively identifying multi-pollution sources in a mixed water body.
BACKGROUND ART
The traceability of water pollution in estuary regions has been a hot and difficult point in the field of environmental su- pervision. Due to the continuous mixing of seawater, incoming wa- ter from the upstream of the seagoing rivers, various industrial enterprises, domestic sewage, livestock and poultry breeding, sea- water breeding, agricultural and forestry drainage, atmospheric rainfall, and so on under the effect of tide and runoff, it is ex- tremely difficult to distinguish pollution sources in a mixed wa- ter body in the estuary regions, which is not conducive to the ac- curate control of marine pollution.
Chinese Patent No. CN111426668A discloses a method for clas- sifying and identifying the traceability of polluted water using three-dimensional fluorescence spectrum feature information. In the method, sample pollution is classified by a neural network, and suspected traceability information is obtained through simi- larity matching. Chinese Patent No. CN113311081A discloses a meth- od and device for identifying a pollution source based on three- dimensional liquid chromatography fingerprints. In the method, three-dimensional liquid chromatography fingerprints are automati- cally compared and identified using a self-organizing neural net- work so as to identify the pollution source. Chinese Patent No.
CN113033623A discloses a method and system for identifying a pol- lution source based on ultraviolet-visible absorption spectrum. In the method, a pollution source sample is collected and pre- treated, ultraviolet-visible absorption spectrum test is performed on the pre-treated pollution source sample to obtain spectral data of the pollution source sample, the spectral data is pre-treated, standard normal transformation is performed on the pre-treated spectral data, a pollution source identification model is estab- lished according to the standard normal transformed spectral data and a classification algorithm and trained, and the pollution source is identified through the trained pollution source identi- fication model. Chinese Patent No. CN113011478 A discloses a meth- od and system for identifying pollution sources based on data fu- sion. In the method, conventional water quality data, ultraviolet- visible absorption spectrum data and three-dimensional fluores- cence spectrum data are obtained by performing pollution index test on a pollution source sample after pretreatment, feature ex- traction is performed after the pretreatment of test data, the ex- tracted feature data is concatenated to construct fusion data, a pollution source identification model is established and trained according to the fusion data and a classification algorithm, and the pollution sources are identified through the trained pollution source identification model. These methods can well identify the pollution sources, but cannot identify multiple pollution sources of a mixed water body, and cannot obtain the proportion of multi- ple pollution sources.
Although an isotope-based tracing method can provide the pro- portion of various types of pollution sources, this method can on- ly provide an approximate proportion of pollution sources in a surveyed river, but cannot provide the proportion of pollution sources in a specific station. Moreover, this method involves iso- tope detection, and the measurement is very complex.
SUMMARY
In order to solve the above-mentioned technical problem, an object of the present invention is to provide a method and system for quantitatively identifying multi-pollution sources in a mixed water body, which can quickly identify multiple pollution sources in a mixed water body, and provide the proportion of various types of pollution sources.
The first technical solution adopted by the present invention is as follows. A method for quantitatively identifying multi- pollution sources in a mixed water body includes the following steps: acquiring a single-pollution source sample and performing three-dimensional fluorescence spectrum measurement to obtain sin- gle-pollution source three-dimensional fluorescence spectrum data; mixing the single-pollution source three-dimensional fluores- cence spectrum data to obtain a pollution source three-dimensional fluorescence spectrum data set; training a pre-constructed quantitative identification model of multi-pollution sources in a mixed water body using the pollu- tion source three-dimensional fluorescence spectrum data set to obtain a quantitative identification model of multi-pollution sources in a mixed water body; quantitatively identifying, based on the quantitative identi- fication model of multi-pollution sources in a mixed water body, a sample to be tested to obtain a sample-to-be-tested quantitative identification result.
Further, the method also includes: pre-treating the single- pollution source sample, wherein the pre-treating comprises fil- tering the single-pollution source sample through a filter mem- brane of 0.22 pm and storing the single-pollution source sample in a brown glass bottle from light.
Further, the step of mixing the single-pollution source three-dimensional fluorescence spectrum data to obtain a pollution source three-dimensional fluorescence spectrum data set specifi- cally includes: pre-treating the single-pollution source three-dimensional fluorescence spectrum data to obtain pre-treated single-pollution source three-dimensional fluorescence spectrum data; classifying the pre-treated single-pollution source three- dimensional fluorescence spectrum data according to different types to obtain different types of single-pollution source three- dimensional fluorescence spectrum data; mixing two or more types of the different types of single- pollution source three-dimensional fluorescence spectrum data ac- cording to different proportions to obtain multi-pollution source three-dimensional fluorescence spectrum data; integrating the single-pollution source three-dimensional fluorescence spectrum data and the multi-pollution source three- dimensional fluorescence spectrum data to obtain a pollution source three-dimensional fluorescence spectrum data set.
Further, the pre-treating the single-pollution source three- dimensional fluorescence spectrum data includes: deducting an ul- tra-pure water blank, converting fluorescence intensity into Raman units (R.U.), and removing Rayleigh scattering and Raman scatter- ing.
Further, the step of training a pre-constructed quantitative identification model of multi-pollution sources in a mixed water body using the pollution source three-dimensional fluorescence spectrum data set to obtain a quantitative identification model of multi-pollution sources in a mixed water body specifically in- cludes: dividing the pollution source three-dimensional fluorescence spectrum data set into a training set and a verification set; training the pre-constructed quantitative identification mod- el of multi-pollution sources in a mixed water body using the training set, outputting a pollution source class identification result by taking a cross entropy as a loss function, and output- ting a pollution source proportion result by taking a mean square error as a loss function, so as to obtain a trained quantitative identification model of multi-pollution sources in a mixed water bodys; verifying the accuracy of the trained quantitative identifi- cation model of multi-pollution sources in a mixed water body us- ing the verification set to obtain an accuracy verification re- sult; selecting the trained quantitative identification model of multi-pollution sources in a mixed water body with the maximum ac- curacy according to the accuracy verification result to obtain a quantitative identification model of multi-pollution sources in a mixed water body.
Further, the method also includes: evaluating the model per- formance of the quantitative identification model of multi-
pollution sources in a mixed water body, specifically including: acquiring a test set and testing the quantitative identifica- tion model of multi-pollution sources in a mixed water body to ob- tain model performance evaluation parameters; 5 evaluating the quantitative identification model of multi- pollution sources in a mixed water body according to the model performance evaluation parameters to obtain a model performance evaluation result.
The second technical solution adopted by the present inven- tion is as follows. A system for quantitatively identifying multi- pollution sources in a mixed water body includes: a measurement module, configured to acquire a single- pollution source sample and perform three-dimensional fluorescence spectrum measurement to obtain single-pollution source three- dimensional fluorescence spectrum data; a mixing module, configured to mix the single-pollution source three-dimensional fluorescence spectrum data to obtain a pollution source three-dimensional fluorescence spectrum data set; a training module, configured to train a pre-constructed quantitative identification model of multi-pollution sources in a mixed water body using the pollution source three-dimensional flu- orescence spectrum data set to obtain a quantitative identifica- tion model of multi-pollution sources in a mixed water body; a quantitative identification module, configured to quantita- tively identify, based on the quantitative identification model of multi-pollution sources in a mixed water body, a sample to be tested to obtain a sample-to-be-tested quantitative identification result.
The method and system of the present invention have the fol- lowing advantageous effects. In the present invention, firstly, by pre-treating a single-pollution source sample, it is possible to reduce the influence of external factors on the construction of a quantitative identification model of multi-pollution sources in a mixed water body, so as to ensure the accuracy of a single- pollution source sample test; secondly, in order to make single- pollution source three-dimensional fluorescence spectrum data more accurate and intuitive, the single-pollution source three-
dimensional fluorescence spectrum data is pre-treated; finally, a pollution source three-dimensional fluorescence spectrum data set is divided into a training set, a verification set and a test set, the model is trained using the training set, the accuracy of the model is verified using the verification set, the model with small model error and maximum accuracy is selected as an optimal model, and the model is tested using the test set to evaluate the perfor- mance of the model, thereby ensuring the accuracy of the construc- tion of the quantitative identification model of multi-pollution sources in a mixed water body. By means of three-dimensional fluo- rescence spectroscopy, sampling, pre-treating, simple and effi- cient measurement, and accurate and sensitive identification of pollution sources, in combination with a multi-label and multi- task convolution neural network model, pollution sources in the mixed water body and the proportion thereof can be quickly and ac- curately identified. The system is low in cost, high in timeli- ness, strong in operability, and conducive to a wide range of pro- motion, and is of great significance for pollution traceability of the mixed water body.
BRIEF DESCRIPTION OF THE DRAWINGS
FIG. 1 is a flowchart of steps of a method for quantitatively identifying multi-pollution sources in a mixed water body accord- ing to the present invention.
FIG. 2 is a structural block diagram of a system for quanti- tatively identifying multi-pollution sources in a mixed water body according to the present invention.
DETAILED DESCRIPTION OF THE EMBODIMENTS
The present invention will be described below in further de- tail with reference to the accompanying drawings and specific em- bodiments. The step numbers in the following embodiments are pro- vided only for ease of illustration, no limitation is placed on the order between the steps, and the order of execution of the steps in the embodiments may be adapted as understood by those skilled in the art.
With reference to FIG. 1, the present invention provides a method for quantitatively identifying multi-pollution sources in a mixed water body. The method includes the following steps:
Sl: Acquire a single-pollution source sample and perform three-dimensional fluorescence spectrum measurement to obtain sin- gle-pollution source three-dimensional fluorescence spectrum data.
S1.1: Acquire and pre-treat a single-pollution source sample to obtain pre-treated single-pollution source sample.
Specifically, in order to ensure the integrity and accuracy of a quantitative identification model of multi-pollution sources in a mixed water body, the acquired single-pollution source sample includes typical representative samples of all possible pollution source types in a collection area, and the natural water of a coastal seagoing river is selected as a research object in the target area. The possible pollution sources in this water area are respectively: seawater backflow, sewage discharged from urban sew- age treatment facilities, sewage discharged from agricultural and rural surface sources, and rainwater. The sewage discharged from agricultural and rural surface sources is subdivided into rural direct sewage, livestock and poultry breeding sewage, agricultural and forestry drainage, etc. 20 typical representative samples of each type were collected in different places in the watershed, to- taling 80 samples.
Secondly, there are many ways to pre-treat the single- pollution source sample. A natural clarification method may be used, and an upper 2/3 clarified solution is used for analysis and determination. A water sample digestion method may also be used.
As a preferred solution of this embodiment, the method for pre- treating the single-pollution source sample includes: filtering the single-pollution source sample through a filter membrane of 0.22 pm and storing the single-pollution source sample in a brown glass bottle from light. In order to ensure the test accuracy of the single-pollution source sample, different pre-treatment modes may be used for different pollution source samples.
S1.2: Perform three-dimensional fluorescence spectrum meas- urement on the pre-treated single-pollution source sample to ob- tain single-pollution source three-dimensional fluorescence spec- trum data.
Specifically, during the three-dimensional fluorescence spec- trum measurement, a scanning range of an excitation wavelength and emission wavelength of a three-dimensional fluorescence spectrum is 200-600 nm, and a scanning interval range is 1-10 nm.
S2: Mix the single-pollution source three-dimensional fluo- rescence spectrum data to obtain a pollution source three- dimensional fluorescence spectrum data set.
S2.1: Pre-treat the single-pollution source three-dimensional fluorescence spectrum data to obtain pre-treated single-pollution source three-dimensional fluorescence spectrum data.
Specifically, in order to make the single-pollution source three-dimensional fluorescence spectrum data more accurate and in- tuitive, it is also necessary to pre-treat the obtained single- pollution source three-dimensional fluorescence spectrum data. As a preferred solution of this embodiment, the pre-treating the sin- gle-pollution source three-dimensional fluorescence spectrum data includes: deducting an ultra-pure water blank, converting the flu- orescence intensity of an original fluorescence fingerprint into
Raman units (R.U.) using the integral of the Raman scattering in- tensity of ultra-pure water with an excitation wavelength of 350 nm and an emission wavelength of 381-426 nm, and removing Rayleigh scattering and Raman scattering. $52.2: Classify the pre-treated single-pollution source three- dimensional fluorescence spectrum data according to different types to obtain different types of single-pollution source three- dimensional fluorescence spectrum data.
Specifically, the pre-treated single-pollution source three- dimensional fluorescence spectrum data is classified into four classes: seawater backflow, sewage discharged from urban sewage treatment facilities, sewage discharged from agricultural and ru- ral surface sources, and rainwater, which are numbered S, W, N, and R in sequence.
S2.3: Mix two or more types of the different types of single- pollution source three-dimensional fluorescence spectrum data ac- cording to different proportions to obtain multi-pollution source three-dimensional fluorescence spectrum data.
Specifically, as a preferred solution of this embodiment, the different types of single-pollution source three-dimensional fluo- rescence spectrum data are mixed in a pair-by-pair combination in the ratio of 2:8, 3:7 and 4:6, so as to obtain fluorescence data of a total of 14400 mixed samples. This process must ensure that a mixed water body sample contains a combination of all types of pollution sources. 52.4: Integrate the single-pollution source three-dimensional fluorescence spectrum data and the multi-pollution source three- dimensional fluorescence spectrum data to obtain a pollution source three-dimensional fluorescence spectrum data set.
S3: Train a pre-constructed quantitative identification model of multi-pollution sources in a mixed water body using the pollu- tion source three-dimensional fluorescence spectrum data set to obtain a quantitative identification model of multi-pollution sources in a mixed water body.
Specifically, as a preferred solution of this embodiment, the quantitative identification model of multi-pollution sources in a mixed water body is a multi-label and multi-task convolution neu- ral network model. The same convolution neural network is used to accomplish two tasks simultaneously: identifying pollution source classes and calculating the proportion of various pollution sources. In the classification of the pollution source classes, a cross entropy is taken as a loss function, and in the calculation of the proportion of pollution sources, a mean square error is taken as a loss function. The sum of the two loss functions is taken as a total loss function of the quantitative identification model of multi-pollution sources in a mixed water body. Multi- label means that each pollution source corresponds to one label.
There may be one or more pollution source classes for a mixed wa- ter body sample to be detected.
The number of labels in this task is 4, and four classes: 5,
W, N, and R are represented by 0, 1, 2, and 3, respectively.
S3.1: Divide the pollution source three-dimensional fluores- cence spectrum data set into a training set and a verification set.
Specifically, a total of 14400 groups of pollution source three-dimensional fluorescence spectrum data are obtained, 90% of sample data is randomly selected as a training set, and the re- maining 10% of sample data is taken as a verification set. $3.2: Train the pre-constructed quantitative identification model of multi-pollution sources in a mixed water body using the training set to obtain a trained quantitative identification model of multi-pollution sources in a mixed water body.
S3.3: Verify the accuracy of the trained quantitative identi- fication model of multi-pollution sources in a mixed water body using the verification set to obtain an accuracy verification re- sult.
Specifically, the accuracy verification result includes the identification accuracy of the pollution resource classes and an error of a calculation result for the proportion of the pollution resources.
The identification accuracy of the pollution resource classes describes the proportion of the number of correctly classified samples to the total number of classified samples, and the calcu- lation formula is as follows:
Ate + ATN
Rim Atom where Ax is the number of correctly classified samples, Arm is the number of incorrectly classified samples, and Aai is the total number of classified samples.
The mean square error is used as the error of the calculation result for the proportion of the pollution resources, and the ex- pression is as follows:
LX)
Rysg= 11» ’ where m is the total number of samples, x, is the true value of the nth sample, and y, is the predicted value of the nth sample.
S3.4: Select the trained quantitative identification model of multi-pollution sources in a mixed water body with the maximum ac- curacy according to the accuracy verification result to obtain a quantitative identification model of multi-pollution sources in a mixed water body.
S4: Quantitatively identify, based on the quantitative iden-
tification model of multi-pollution sources in a mixed water body, a sample to be tested to obtain a sample-to-be-tested quantitative identification result.
Further as a preferred embodiment of the method, the method also includes: evaluating the model performance of the quantita- tive identification model of multi-pollution sources in a mixed water body; dividing the pollution source three-dimensional fluo- rescence spectrum data in step S3 into a training set, a verifica- tion set and a test set in the ratio of 18:1:1; testing the quan- titative identification model of multi-pollution sources in a mixed water body obtained through the training set and the verifi- cation set to obtain model performance evaluation parameters: the identification accuracy of the pollution resource classes and an error of a calculation result for the proportion of the pollution resources. The identification accuracy of the pollution resource classes is about 88%. It can be seen therefrom that the quantita- tive identification model of multi-pollution sources in a mixed water body may distinguish water samples of a single pollution source and mixed water body samples of multiple pollution sources.
The error of the calculation result for the proportion of the pol- lution resources is about 0.0052. It can be seen therefrom that the quantitative identification model of multi-pollution sources in a mixed water body is accurate and reliable, which has im- portant reference value for the pollution source tracing of coastal seagoing rivers.
As shown in FIG. 2, a system for quantitatively identifying multi-pollution sources in a mixed water body includes: a measurement module, configured to acquire a single- pollution source sample and perform three-dimensional fluorescence spectrum measurement to obtain single-pollution source three- dimensional fluorescence spectrum data; a mixing module, configured to mix the single-pollution source three-dimensional fluorescence spectrum data to obtain a pollution source three-dimensional fluorescence spectrum data set; a training module, configured to train a pre-constructed quantitative identification model of multi-pollution sources in a mixed water body using the pollution source three-dimensional flu-
orescence spectrum data set to obtain a quantitative identifica- tion model of multi-pollution sources in a mixed water body; a quantitative identification module, configured to quantita- tively identify, based on the quantitative identification model of multi-pollution sources in a mixed water body, a sample to be tested to obtain a sample-to-be-tested quantitative identification result.
All of the above-mentioned method embodiments are applicable to the system embodiment, the functions specifically realized by the system embodiment are the same as those of the above-mentioned method embodiments, and the advantageous effects achieved by the system embodiment are the same as those achieved by the above- mentioned method embodiments.
The preferred embodiments of the present invention are spe- cifically described above. However, the present invention is not limited to the embodiments. Those skilled in the art may make var- ious equivalent modifications or substitutions without departing from the spirit of the present invention, which are all included within the scope defined by the claims of the present application.

Claims (7)

CONCLUSIESCONCLUSIONS 1. Werkwijze voor het kwantitatief identificeren van bronnen van meerdere verontreinigingen in een gemengd waterlichaam, omvattende de volgende stappen: het verkrijgen van een monster van een enkele vervuilingsbron en het uitvoeren van driedimensionale fluorescentiespectrummetingen om driedimensionale fluorescentiespectrumgegevens van een enkele vervuilingsbron te verkrijgen; het mengen van de driedimensionale fluorescentiespectrumgegevens van een enkele vervuilingsbron om een driedimensionale fluorescen- tiespectrumgegevensset van een enkele vervuilingsbron te verkrij- gen; het trainen van een vooraf geconstrueerd kwantitatief identifica- tiemodel van multi-vervuilingsbronnen in een gemengd waterlichaam met behulp van de driedimensionale fluorescentiespectrumgegevens- set van de vervuilingsbron om een kwantitatief identificatiemodel van multi-verontreinigingsbronnen in een gemengd waterlichaam te verkrijgen; het kwantitatief identificeren, op basis van het kwantitatieve identificatiemodel voor multi-verontreinigingsbronnen met gemengde waterlichamen, van een te testen monster om een kwantitatief iden- tificatieresultaat van een te testen monster te verkrijgen.A method for quantitatively identifying sources of multiple contaminants in a mixed water body, comprising the steps of: obtaining a sample from a single contaminant source and performing three-dimensional fluorescent spectrum measurements to obtain three-dimensional fluorescent spectrum data from a single contaminant source; mixing the three-dimensional fluorescence spectrum data from a single pollution source to obtain a three-dimensional fluorescence spectrum data set from a single pollution source; training a pre-constructed quantitative identification model of multi-pollution sources in a mixed water body using the three-dimensional fluorescence spectrum data set of the pollution source to obtain a quantitative identification model of multi-pollution sources in a mixed water body; quantitatively identifying, based on the quantitative identification model for multi-pollution sources with mixed water bodies, a sample to be tested to obtain a quantitative identification result of a sample to be tested. 2. Werkwijze voor het kwantitatief identificeren van bronnen van meerdere verontreinigingen in een gemengd waterlichaam volgens conclusie 1, verder omvattende: het voorbehandelen van het monster van een enkele verontreinigingsbron, waarbij de voorbehandeling omvat het filteren van het monster van een enkele verontreini- gingsbron door een filter membraan van 0,22 um en het opslaan van het monster met een enkele bron van vervuiling in een bruine gla- zen fles voor bescherming tegen licht.A method for quantitatively identifying sources of multiple contaminants in a mixed water body according to claim 1, further comprising: pre-treating the sample from a single contaminant source, wherein the pre-treatment includes filtering the sample from a single contaminant source through a filter membrane of 0.22 um and storing the sample with a single source of contamination in a brown glass bottle for protection from light. 3. Werkwijze voor het kwantitatief identificeren van bronnen van meerdere verontreinigingen in een gemengd waterlichaam volgens conclusie 1, waarbij de stap van het mengen van de driedimensiona-A method for quantitatively identifying sources of multiple contaminants in a mixed water body according to claim 1, wherein the step of mixing the three-dimensional le fluorescentiespectrumgegevens van de enkele vervuilingsbron om een specifieke driedimensionale fluorescentiespectrumgegevensset van een verontreinigingsbron te verkrijgen omvat: het voorbehandelen van de driedimensionale fluorescentiespectrum- gegevens van een enkele vervuilingsbron om voorbehandelde driedi- mensionale fluorescentiespectrumgegevens van een enkele vervui- lingsbron te verkrijgen; het classificeren van de voorbehandelde driedimensionale fluores- centiespectrumgegevens van een enkele vervuilingsbron volgens ver- schillende typen om verschillende typen driedimensionale fluores- centiespectrumgegevens van een enkele vervuilingsbron te verkrij- gen; het mengen van twee of meer typen van de verschillende typen drie- dimensionale fluorescentiespectrumgegevens van eenenkele vervui- lingsbron volgens verschillende verhoudingen om driedimensionale fluorescentiespectrumgegevens van meerdere bronnen van vervuiling te verkrijgen; het integreren van de driedimensionale fluorescentiespectrumgege- vens van de enkele vervuilingsbron en de driedimensionale fluores- centiespectrumgegevens van de meervoudige vervuilingsbron om een driedimensionale fluorescentiespectrumgegevensverzameling van een vervuilingsbron te verkrijgen.the fluorescence spectrum data of the single pollution source to obtain a specific three-dimensional fluorescence spectrum data set of a pollution source comprises: pre-processing the three-dimensional fluorescence spectrum data of a single pollution source to obtain pre-treated three-dimensional fluorescence spectrum data of a single pollution source; classifying the pretreated three-dimensional fluorescent spectrum data of a single pollution source according to different types to obtain different types of three-dimensional fluorescent spectrum data of a single pollution source; mixing two or more types of the different types of three-dimensional fluorescence spectrum data from a single pollution source according to different ratios to obtain three-dimensional fluorescence spectrum data from multiple pollution sources; integrating the three-dimensional fluorescence spectrum data of the single pollution source and the three-dimensional fluorescence spectrum data of the multiple pollution source to obtain a three-dimensional fluorescence spectrum data set of a pollution source. 4. Werkwijze voor het kwantitatief identificeren van bronnen van meerdere verontreinigingen in een gemengd waterlichaam volgens conclusie 3, waarbij de voorbehandeling van de driedimensionale fluorescentiespectrumgegevens van de enkele vervuilingsbron omvat: het afleiden van een ultrazuiver waterblanco, het omzetten van de fluorescentie-intensiteit in Raman-eenheden (RU), en het verwijde- ren van Rayleigh-verstrooiing en Raman-verstrooiing.A method for quantitatively identifying sources of multiple contaminants in a mixed water body according to claim 3, wherein the pre-treatment of the three-dimensional fluorescence spectrum data of the single contaminant source includes: deriving an ultrapure water blank, converting the fluorescence intensity to Raman units (RU), and removing Rayleigh scattering and Raman scattering. 5. Werkwijze voor het kwantitatief identificeren van bronnen van meerdere verontreinigingen in een gemengd waterlichaam volgens conclusie 1, waarbij de stap van het trainen van een vooraf gecon- strueerd kwantitatief identificatiemodel van bronnen van meerdere verontreinigingen in een gemengd waterlichaam onder gebruikmaking van de driedimensionale fluorescentiespectrumgegevensset van de vervuilingsbron om een kwantitatief identificatiemodel van multi- vervuilingsbronnen in een gemengd waterlichaam te verkrijgen, in het bijzonder omvat: het verdelen van de driedimensionale fluorescentiespectrumgege- vensset van de bron van verontreiniging in een trainingsset en een verificatieset; het trainen van het vooraf geconstrueerde kwantitatieve identifi- catiemodel van multi-vervuilingsbronnen in een gemengd waterli- chaam met behulp van de trainingsset, het uitvoeren van een iden- tificatieresultaat van een vervuilingsbronklasse door een kruis- entropie als een verliesfunctie te nemen, en het uitvoeren van een resultaat van een aandeel van een vervuilingsbron door een gemid- delde kwadratische fout als verliesfunctie, om een getraind kwan- titatief identificatiemodel van multi-vervuilingsbronnen in een gemengd waterlichaam te verkrijgen; het verifiëren van de nauwkeurigheid van het getrainde kwantita- tieve identificatiemodel van multi-vervuilingsbronnen in een ge- mengd waterlichaam met behulp van de verificatieset om een nauw- keurigheidsverificatieresultaat te verkrijgen; het selecteren van het getrainde kwantitatieve identificatiemodel van multi-vervuilingsbronnen in een gemengd waterlichaam met de maximale nauwkeurigheid volgens het resultaat van de nauwkeurig- heidsverificatie om een kwantitatief identificatiemodel van multi- vervuilingsbronnen in een gemengd waterlichaam te verkrijgen.The method for quantitatively identifying sources of multiple contaminants in a mixed water body according to claim 1, wherein the step of training a pre-constructed quantitative identification model of sources of multiple contaminants in a mixed water body using the three-dimensional fluorescent spectrum data set of the pollution source to obtain a quantitative identification model of multi-pollution sources in a mixed water body, in particular comprising: dividing the three-dimensional fluorescence spectrum data set of the pollution source into a training set and a verification set; training the pre-constructed quantitative identification model of multi-pollution sources in a mixed water body using the training set, outputting an identification result of a pollution source class by taking a cross-entropy as a loss function, and outputting of a result of a share of a pollution source by a mean square error as a loss function, to obtain a trained quantitative identification model of multi-pollution sources in a mixed water body; verifying the accuracy of the trained quantitative identification model of multi-pollution sources in a mixed water body using the verification set to obtain an accuracy verification result; selecting the trained quantitative identification model of multi-pollution sources in a mixed water body with the maximum accuracy according to the accuracy verification result to obtain a quantitative identification model of multi-pollution sources in a mixed water body. 6. Werkwijze voor het kwantitatief identificeren van bronnen van meerdere verontreinigingen in een gemengd waterlichaam volgens conclusie 1, verder omvattende: het evalueren van de modelpresta- ties van het kwantitatieve identificatiemodel van meerdere veront- reinigingsbronnen in een gemengd waterlichaam, in het bijzonder omvattende: het verwerven van een testset en het testen van het kwantitatieve identificatiemodel van multi-vervuilingsbronnen in een gemengd wa- terlichaam om parameters voor de evaluatie van de modelprestaties te verkrijgen; het evalueren van het kwantitatieve identificatiemodel van multi- vervuilingsbronnen in een gemengd waterlichaam volgens de parame-A method for quantitatively identifying sources of multiple contaminants in a mixed water body according to claim 1, further comprising: evaluating the model performance of the quantitative identification model of multiple contaminants in a mixed water body, in particular comprising: acquiring a test set and testing the quantitative identification model of multi-pollution sources in a mixed water body to obtain parameters for the evaluation of model performance; evaluating the quantitative identification model of multi-pollution sources in a mixed water body according to the parameter ters van de modelprestatie-evaluatie om een resultaat van de mo- delprestatie-evaluatie te verkrijgen.ters of the model performance evaluation to obtain a result of the model performance evaluation. 7. Systeem voor het kwantitatief identificeren van bronnen van meerdere verontreinigingen in een gemengd waterlichaam, omvatten- de: een meetmodule, geconfigureerd om een monster van een enkele ver- vuilingsbron te verkrijgen en driedimensionale fluorescentiespec- trummetingen uit te voeren om driedimensionale fluorescentiespec- trumgegevens van een enkele bron van vervuiling te verkrijgen; een mengmodule, geconfigureerd om de driedimensionale fluorescen- tiespectrumgegevens van een enkele bron van vervuiling te mengen om een driedimensionale fluorescentiespectrumgegevensverzameling van een vervuilingsbron te verkrijgen; een trainingsmodule, geconfigureerd om een vooraf geconstrueerd kwantitatief identificatiemodel van bronnen van meerdere veront- reinigingen in een gemengd waterlichaam te trainen met behulp van de driedimensionale fluorescentiespectrumgegevensset van de ver- vuilingsbron om een kwantitatief identificatiemodel van bronnen van meerdere verontreinigingen in gemengd waterlichaam te verkrij- gen; een module voor kwantitatieve identificatie, geconfigureerd om, op basis van het kwantitatieve identificatiemodel van bronnen van meerdere verontreinigingen in een gemengd waterlichaam, een te testen monster kwantitatief te identificeren om een kwantitatief identificatieresultaat van een nog te testen monster te verkrij-7. A system for quantitatively identifying sources of multiple contaminants in a mixed water body, comprising: a measurement module configured to obtain a sample from a single contaminant source and perform three-dimensional fluorescence spectrum measurements to obtain three-dimensional fluorescence spectrum data from to obtain a single source of pollution; a mixing module configured to mix the three-dimensional fluorescence spectrum data of a single pollution source to obtain a three-dimensional fluorescence spectrum data set of a pollution source; a training module configured to train a pre-constructed quantitative identification model of multi-pollutant sources in a mixed water body using the three-dimensional fluorescence spectrum data set of the pollution source to obtain a quantitative identification model of multi-pollutant sources in mixed water body ; a quantitative identification module configured to quantitatively identify, based on the quantitative identification model of sources of multiple contaminants in a mixed water body, a sample under test to obtain a quantitative identification result of a sample yet to be tested gen.gene.
NL2034211A 2022-08-12 2023-02-23 Method and system for quantitatively identifying multi-pollution sources of mixed water body NL2034211B1 (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210968262.1A CN115219472B (en) 2022-08-12 2022-08-12 Method and system for quantitatively identifying multiple pollution sources of mixed water body

Publications (2)

Publication Number Publication Date
NL2034211A true NL2034211A (en) 2024-02-16
NL2034211B1 NL2034211B1 (en) 2024-03-01

Family

ID=83615500

Family Applications (1)

Application Number Title Priority Date Filing Date
NL2034211A NL2034211B1 (en) 2022-08-12 2023-02-23 Method and system for quantitatively identifying multi-pollution sources of mixed water body

Country Status (2)

Country Link
CN (1) CN115219472B (en)
NL (1) NL2034211B1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115494047B (en) * 2022-11-17 2023-05-12 广东博创佳禾科技有限公司 Detection method and system for agricultural pollutants in water environment

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111426668A (en) 2020-04-28 2020-07-17 华夏安健物联科技(青岛)有限公司 Method for tracing, classifying and identifying polluted water body by using three-dimensional fluorescence spectrum characteristic information
CN113011478A (en) 2021-03-05 2021-06-22 清华大学 Pollution source identification method and system based on data fusion
CN113029994A (en) * 2021-03-31 2021-06-25 扬州大学 Microcystin concentration inversion method based on multi-source characteristic spectrum of extracellular organic matter
CN113033623A (en) 2021-03-05 2021-06-25 清华大学 Pollution source identification method and system based on ultraviolet-visible absorption spectrum
US20210199588A1 (en) * 2018-06-01 2021-07-01 Orb Xyz, Inc. Detection of biological substances
CN113311081A (en) 2021-05-17 2021-08-27 清华大学 Pollution source identification method and device based on three-dimensional liquid chromatography fingerprint
US20210389243A1 (en) * 2018-10-11 2021-12-16 The State Of Israel, Ministry Of Agriculture & Rural Development, Agricultural Research Organization System and method for quantification of bacteria in water using fluorescence spectra measurements and machine-learning

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5424959A (en) * 1993-07-19 1995-06-13 Texaco Inc. Interpretation of fluorescence fingerprints of crude oils and other hydrocarbon mixtures using neural networks
EP1751523B1 (en) * 2004-05-13 2017-10-04 NarTest AS A portable device and method for on-site detection and quantification of drugs
CN102661939B (en) * 2012-05-15 2013-12-04 北京化工大学 Method for rapidly tracing to water pollution source
CN106018359A (en) * 2016-05-12 2016-10-12 常州市排水管理处 Sewage plant water-quality monitoring early-warning method and system
CN107576641B (en) * 2017-09-11 2020-03-31 中国科学技术大学 Method and device for decomposing three-dimensional fluorescence spectrum data
CN109470667A (en) * 2018-11-14 2019-03-15 华东理工大学 A kind of combination water quality parameter and three-dimensional fluorescence spectrum carry out the method that pollutant is traced to the source
CN112084382A (en) * 2020-09-04 2020-12-15 安徽思环科技有限公司 Pretreatment method for three-dimensional fluorescence data of water quality of industrial park pollution source
CN113051844B (en) * 2021-03-12 2022-06-28 中国科学院烟台海岸带研究所 Method for identifying and accurately tracing environmental pollution events of ocean and open water areas
CN114563381A (en) * 2022-01-14 2022-05-31 山东师范大学 Water body pollution tracing method
CN114878528A (en) * 2022-04-21 2022-08-09 宁波大学 Method for quickly tracing surface water surface floating oil based on three-dimensional fluorescence spectroscopy

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210199588A1 (en) * 2018-06-01 2021-07-01 Orb Xyz, Inc. Detection of biological substances
US20210389243A1 (en) * 2018-10-11 2021-12-16 The State Of Israel, Ministry Of Agriculture & Rural Development, Agricultural Research Organization System and method for quantification of bacteria in water using fluorescence spectra measurements and machine-learning
CN111426668A (en) 2020-04-28 2020-07-17 华夏安健物联科技(青岛)有限公司 Method for tracing, classifying and identifying polluted water body by using three-dimensional fluorescence spectrum characteristic information
CN113011478A (en) 2021-03-05 2021-06-22 清华大学 Pollution source identification method and system based on data fusion
CN113033623A (en) 2021-03-05 2021-06-25 清华大学 Pollution source identification method and system based on ultraviolet-visible absorption spectrum
CN113029994A (en) * 2021-03-31 2021-06-25 扬州大学 Microcystin concentration inversion method based on multi-source characteristic spectrum of extracellular organic matter
CN113311081A (en) 2021-05-17 2021-08-27 清华大学 Pollution source identification method and device based on three-dimensional liquid chromatography fingerprint

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
NAKAR AMIR ET AL: "Quantification of bacteria in water using PLS analysis of emission spectra of fluorescence and excitation-emission matrices", WATER RESEARCH, ELSEVIER, AMSTERDAM, NL, vol. 169, 17 October 2019 (2019-10-17), XP085975075, ISSN: 0043-1354, [retrieved on 20191017], DOI: 10.1016/J.WATRES.2019.115197 *

Also Published As

Publication number Publication date
CN115219472A (en) 2022-10-21
NL2034211B1 (en) 2024-03-01
CN115219472B (en) 2023-05-12

Similar Documents

Publication Publication Date Title
Schymanski et al. Analysis of microplastics in drinking water and other clean water samples with micro-Raman and micro-infrared spectroscopy: minimum requirements and best practice guidelines
CN107101943B (en) Device and method for detecting microalgae activity by optical flow control lens-free holographic imaging
CN101458213B (en) Oil species identification method by sea oil spill concentration auxiliary parameter fluorescence spectrum
CN109470667A (en) A kind of combination water quality parameter and three-dimensional fluorescence spectrum carry out the method that pollutant is traced to the source
CN103528617B (en) A kind of cockpit instrument identifies and detection method and device automatically
NL2034211B1 (en) Method and system for quantitatively identifying multi-pollution sources of mixed water body
CN106596436B (en) Multi-parameter water quality real-time online monitoring device based on spectrum method
Dubelaar et al. High frequency monitoring reveals phytoplankton dynamics
CN113916847A (en) Water quality detection method based on spectrum technology and linear support vector algorithm
CN105486655A (en) Rapid detection method for organic matters in soil based on infrared spectroscopic intelligent identification model
CN111879710A (en) Steel structure coating corrosion resistance evaluation method, system, server and storage medium
CN114660105A (en) Soil heavy metal Cd content inversion method, system, medium and computer equipment
Zhu et al. Online recognition of drainage type based on UV-vis spectra and derivative neural network algorithm
CN111879709A (en) Method and device for detecting spectral reflectivity of lake water body
CN115905881A (en) Method and device for classifying yellow pearls, electronic equipment and storage medium
CN110907388A (en) Oil spill type identification method based on infrared spectroscopic analysis
CN106442414A (en) Device for conducting fast detection on water body petroleum pollutants based on Brillouin-Raman spectra and method thereof
CN206583795U (en) A kind of multi-parameter water quality real time on-line monitoring device based on spectroscopic methodology
CN107576641B (en) Method and device for decomposing three-dimensional fluorescence spectrum data
CN116911183A (en) Karst wetland water chlorophyll a inversion method, system, equipment and medium
CN111398189A (en) Multi-modal optical imaging water quality remote sensing detection device and pollution feature extraction method
CN109668842A (en) A kind of shellfish heavy metal pollution rapid detection method
CN110426366A (en) Meat adulteration ratio detection method based on visualization olfactory sensor and near-infrared
CN108986096A (en) A kind of mixed oil liquid discrimination method based on three-dimensional fluorescence spectrum Yu Tchebichef square
CN115656063A (en) Target pollutant content analysis method and device based on hyperspectral data