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 PDFInfo
- 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
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000002189 fluorescence spectrum Methods 0.000 claims abstract description 83
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000005259 measurement Methods 0.000 claims abstract description 15
- 238000012795 verification Methods 0.000 claims description 18
- 238000012360 testing method Methods 0.000 claims description 14
- 238000001069 Raman spectroscopy Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000001228 spectrum Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 3
- 239000011521 glass Substances 0.000 claims description 3
- 239000012528 membrane Substances 0.000 claims description 3
- 238000002203 pretreatment Methods 0.000 claims description 3
- 229910021642 ultra pure water Inorganic materials 0.000 claims description 3
- 239000012498 ultrapure water Substances 0.000 claims description 3
- 239000000356 contaminant Substances 0.000 claims 16
- 239000003344 environmental pollutant Substances 0.000 claims 2
- 238000011109 contamination Methods 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 claims 1
- 108090000623 proteins and genes Proteins 0.000 claims 1
- 239000010865 sewage Substances 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 6
- 239000013535 sea water Substances 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 4
- 238000000862 absorption spectrum Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000009395 breeding Methods 0.000 description 3
- 230000001488 breeding effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 238000001506 fluorescence spectroscopy Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000004811 liquid chromatography Methods 0.000 description 2
- 244000144972 livestock Species 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 244000144977 poultry Species 0.000 description 2
- 241001669573 Galeorhinus galeus Species 0.000 description 1
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 210000004379 membrane Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000008239 natural water Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000002133 sample digestion Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 238000003911 water pollution Methods 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
- G01N21/62—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
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.
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.
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.
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.
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)
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)
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)
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)
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 |
-
2022
- 2022-08-12 CN CN202210968262.1A patent/CN115219472B/en active Active
-
2023
- 2023-02-23 NL NL2034211A patent/NL2034211B1/en active
Patent Citations (7)
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)
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 |