CN118134120A - Quantitative evaluation method and system for regional groundwater environment quality space-time change - Google Patents
Quantitative evaluation method and system for regional groundwater environment quality space-time change Download PDFInfo
- Publication number
- CN118134120A CN118134120A CN202410557746.6A CN202410557746A CN118134120A CN 118134120 A CN118134120 A CN 118134120A CN 202410557746 A CN202410557746 A CN 202410557746A CN 118134120 A CN118134120 A CN 118134120A
- Authority
- CN
- China
- Prior art keywords
- water quality
- quality
- indexes
- index
- groundwater
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000003673 groundwater Substances 0.000 title claims abstract description 114
- 230000008859 change Effects 0.000 title claims abstract description 68
- 238000011158 quantitative evaluation Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 47
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 139
- 238000011156 evaluation Methods 0.000 claims abstract description 55
- 238000011835 investigation Methods 0.000 claims abstract description 35
- 238000013210 evaluation model Methods 0.000 claims abstract description 13
- 238000012216 screening Methods 0.000 claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims description 35
- 238000004458 analytical method Methods 0.000 claims description 18
- 230000007246 mechanism Effects 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 17
- 230000004927 fusion Effects 0.000 claims description 16
- 238000012544 monitoring process Methods 0.000 claims description 14
- 230000002457 bidirectional effect Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 241000282414 Homo sapiens Species 0.000 claims description 5
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 5
- 239000013598 vector Substances 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 4
- 230000001953 sensory effect Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000000379 polymerizing effect Effects 0.000 claims description 2
- 230000002123 temporal effect Effects 0.000 claims 3
- 238000013441 quality evaluation Methods 0.000 abstract description 5
- 238000003860 storage Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 239000006185 dispersion Substances 0.000 description 4
- UHOVQNZJYSORNB-UHFFFAOYSA-N Benzene Chemical compound C1=CC=CC=C1 UHOVQNZJYSORNB-UHFFFAOYSA-N 0.000 description 3
- YXFVVABEGXRONW-UHFFFAOYSA-N Toluene Chemical compound CC1=CC=CC=C1 YXFVVABEGXRONW-UHFFFAOYSA-N 0.000 description 3
- HEDRZPFGACZZDS-UHFFFAOYSA-N Chloroform Chemical compound ClC(Cl)Cl HEDRZPFGACZZDS-UHFFFAOYSA-N 0.000 description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003895 groundwater pollution Methods 0.000 description 2
- 239000011133 lead Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- VZGDMQKNWNREIO-UHFFFAOYSA-N tetrachloromethane Chemical compound ClC(Cl)(Cl)Cl VZGDMQKNWNREIO-UHFFFAOYSA-N 0.000 description 2
- VEXZGXHMUGYJMC-UHFFFAOYSA-M Chloride anion Chemical compound [Cl-] VEXZGXHMUGYJMC-UHFFFAOYSA-M 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- XFXPMWWXUTWYJX-UHFFFAOYSA-N Cyanide Chemical compound N#[C-] XFXPMWWXUTWYJX-UHFFFAOYSA-N 0.000 description 1
- KRHYYFGTRYWZRS-UHFFFAOYSA-M Fluoride anion Chemical compound [F-] KRHYYFGTRYWZRS-UHFFFAOYSA-M 0.000 description 1
- DGAQECJNVWCQMB-PUAWFVPOSA-M Ilexoside XXIX Chemical compound C[C@@H]1CC[C@@]2(CC[C@@]3(C(=CC[C@H]4[C@]3(CC[C@@H]5[C@@]4(CC[C@@H](C5(C)C)OS(=O)(=O)[O-])C)C)[C@@H]2[C@]1(C)O)C)C(=O)O[C@H]6[C@@H]([C@H]([C@@H]([C@H](O6)CO)O)O)O.[Na+] DGAQECJNVWCQMB-PUAWFVPOSA-M 0.000 description 1
- 229910002651 NO3 Inorganic materials 0.000 description 1
- NHNBFGGVMKEFGY-UHFFFAOYSA-N Nitrate Chemical compound [O-][N+]([O-])=O NHNBFGGVMKEFGY-UHFFFAOYSA-N 0.000 description 1
- IOVCWXUNBOPUCH-UHFFFAOYSA-M Nitrite anion Chemical compound [O-]N=O IOVCWXUNBOPUCH-UHFFFAOYSA-M 0.000 description 1
- BUGBHKTXTAQXES-UHFFFAOYSA-N Selenium Chemical compound [Se] BUGBHKTXTAQXES-UHFFFAOYSA-N 0.000 description 1
- QAOWNCQODCNURD-UHFFFAOYSA-L Sulfate Chemical compound [O-]S([O-])(=O)=O QAOWNCQODCNURD-UHFFFAOYSA-L 0.000 description 1
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 1
- 229910052785 arsenic Inorganic materials 0.000 description 1
- RQNWIZPPADIBDY-UHFFFAOYSA-N arsenic atom Chemical compound [As] RQNWIZPPADIBDY-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001580 bacterial effect Effects 0.000 description 1
- 229910052793 cadmium Inorganic materials 0.000 description 1
- BDOSMKKIYDKNTQ-UHFFFAOYSA-N cadmium atom Chemical compound [Cd] BDOSMKKIYDKNTQ-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- JOPOVCBBYLSVDA-UHFFFAOYSA-N chromium(6+) Chemical compound [Cr+6] JOPOVCBBYLSVDA-UHFFFAOYSA-N 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- XMBWDFGMSWQBCA-UHFFFAOYSA-N hydrogen iodide Chemical compound I XMBWDFGMSWQBCA-UHFFFAOYSA-N 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- WPBNNNQJVZRUHP-UHFFFAOYSA-L manganese(2+);methyl n-[[2-(methoxycarbonylcarbamothioylamino)phenyl]carbamothioyl]carbamate;n-[2-(sulfidocarbothioylamino)ethyl]carbamodithioate Chemical compound [Mn+2].[S-]C(=S)NCCNC([S-])=S.COC(=O)NC(=S)NC1=CC=CC=C1NC(=S)NC(=O)OC WPBNNNQJVZRUHP-UHFFFAOYSA-L 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- QSHDDOUJBYECFT-UHFFFAOYSA-N mercury Chemical compound [Hg] QSHDDOUJBYECFT-UHFFFAOYSA-N 0.000 description 1
- 229910052753 mercury Inorganic materials 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 229910052759 nickel Inorganic materials 0.000 description 1
- 230000036284 oxygen consumption Effects 0.000 description 1
- 150000002989 phenols Chemical class 0.000 description 1
- 230000002285 radioactive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 229910052711 selenium Inorganic materials 0.000 description 1
- 239000011669 selenium Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 229910052708 sodium Inorganic materials 0.000 description 1
- 239000011734 sodium Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 229910052725 zinc Inorganic materials 0.000 description 1
- 239000011701 zinc Substances 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a quantitative evaluation method and a quantitative evaluation system for regional groundwater environment quality space-time variation, which relate to the technical field of groundwater quality evaluation and comprise the following steps: acquiring historical investigation data of groundwater environment quality of a target area, and screening out standard exceeding indexes corresponding to the preprocessed historical investigation data based on groundwater quality conventional factors; dividing the target area, analyzing the main component to obtain a main component corresponding to the standard exceeding index, and performing hierarchical clustering on the extracted main component to obtain a primary water quality index; acquiring time change characteristics and space change characteristics of groundwater quality in different subareas; extracting potential water quality indexes, constructing a comprehensive evaluation model through the primary water quality indexes and the potential water quality indexes, and carrying out comprehensive quantitative evaluation. According to the method, the time and space information between the groundwater in the area is obtained based on the high-correlation index, and the special evaluation index is screened for the evaluation area, so that comprehensive quantitative evaluation of the groundwater environment quality is more comprehensive and effective.
Description
Technical Field
The invention relates to the technical field of groundwater quality evaluation, in particular to a quantitative evaluation method and a quantitative evaluation system for regional groundwater environment quality space-time change.
Background
Groundwater resources are an important source of industrial, agricultural and domestic water. In recent years, with the continuous development of economy, population increase and rapid development of industry and agriculture, the exploitation of groundwater by human beings has also been rapidly increased. Especially in northern areas of China, underground water is severely adopted to cause problems of underground funnels, ground subsidence, regional ecological degradation and the like, and regional economy and social sustainable development are seriously affected. In addition, according to GB14848, after single factor evaluation is carried out on single index of groundwater quality evaluation, comprehensive evaluation results are obtained in a mode that the quality is not superior, namely, one index is V-class water, the groundwater quality at the point is V-class water, and real change conditions of groundwater quality in time and space are covered under the evaluation method. When the change condition of the groundwater quality of a region needs to be clarified, if the analysis is carried out on factors by factors, the workload is large, and the time-space change trend is difficult to be clarified. In order to ensure the coordinated development of water resources and economy, the numerical simulation and quality evaluation of the underground water system by a modern scientific method are of great significance. Scientific and reasonable basis is made for strengthening the management of groundwater resources and making the policy of protecting groundwater resources by government departments.
Due to complex groundwater pollution influencing factors, the heterogeneity of groundwater chemical component spatial distribution, the problem of small samples of groundwater sample collection and the high calculation cost of large-scale areas all form great challenges for the traditional pollution risk evaluation method. Machine learning is used as the core of artificial intelligence, has become a leading-edge hot spot for the research of the hydrogeology field, and has been explored and tried in the directions of distribution, change, occurrence mechanism and the like of underground water chemical components through intelligent and efficient data processing and mining. Therefore, how to utilize the deep learning modeling technology to fully utilize the existing water quality monitoring data and improve the quality evaluation precision and model applicability of the groundwater environment is a problem to be solved at present.
Disclosure of Invention
In order to solve the technical problems, the invention provides a quantitative evaluation method and a quantitative evaluation system for the quality space-time change of regional groundwater environment.
The invention provides a quantitative evaluation method for regional groundwater environment quality space-time change, which comprises the following steps:
Acquiring historical investigation data of groundwater environment quality of a target area, carrying out data preprocessing on the historical investigation data, and screening out standard exceeding indexes corresponding to the preprocessed historical investigation data based on groundwater quality conventional factors;
Dividing the target area according to the standard exceeding index, obtaining main components corresponding to the standard exceeding index by utilizing main component analysis in each divided subarea block, and carrying out hierarchical clustering on the extracted main components to obtain primary selection water quality indexes of different subareas;
Acquiring time variation characteristics of groundwater quality of different subareas through primary selection of water quality indexes, analyzing correlation among the different subareas by utilizing the time variation characteristics in combination with geographic positions, and acquiring space variation characteristics of groundwater quality of the different subareas based on the correlation;
And feeding back the primary water quality index according to the time change characteristic and the space change characteristic, analyzing and obtaining a potential water quality index, constructing a comprehensive evaluation model through the primary water quality index and the potential water quality index, and generating a comprehensive quantitative evaluation result of the underground water quality of the target area.
In the scheme, the method screens out the standard exceeding index corresponding to the preprocessed historical survey data based on the ground water quality conventional factors, and specifically comprises the following steps:
Carrying out data integration and data cleaning on multi-source historical investigation data of the groundwater environment quality of a target area, obtaining corresponding water quality investigation results, marking the integrated and cleaned historical investigation data, and carrying out sliding window and normalization processing on the historical investigation data under different water quality labels;
Obtaining a groundwater quality conventional factor through literature retrieval, and classifying the indexes corresponding to the groundwater quality conventional factor according to the influence factors with exceeding indexes, wherein the indexes are sensory form factors, water chemistry type conventional factors, human life and agricultural activity influence factors, industrial activity influence factors and multi-factor influence factors respectively;
Acquiring an underground water quality monitoring instance, acquiring critical values of normal water quality monitoring data corresponding to different indexes in the underground water quality monitoring instance, generating threshold information according to the critical values, acquiring threshold sets of the indexes under different evaluation factor category labels, and constructing a threshold matrix;
comparing the preprocessed historical survey data according to the threshold matrix, and assigning 0 to indexes larger than the threshold in the matrix and 1 to indexes at other positions to realize screening of exceeding indexes in different types of evaluation factors.
In this scheme, the target area is divided according to the standard exceeding index, and the main component corresponding to the standard exceeding index is obtained by using the main component analysis in each divided sub-area block, specifically:
Acquiring two-dimensional map data of a target area, performing interpolation processing on the preprocessed historical survey data by using geographic position information in the historical survey data, performing grid processing on the two-dimensional map data, and determining out-of-standard indexes in different grids;
Setting similarity coefficients according to the number of the exceeding indexes under different types of evaluation factors in the target area, acquiring evaluation factor type labels related to adjacent grids, calculating the similarity between the exceeding indexes, calling the corresponding similarity coefficients to weight, and acquiring the final similarity between the adjacent grids;
when the final similarity accords with a preset similarity threshold, regarding two adjacent grids as the same subarea, and generating a segmentation result of the subarea after traversing all grids of the target area;
and (3) performing principal component analysis in the superscalar index subsets corresponding to the subareas, and extracting principal components in the superscalar indexes.
In the scheme, hierarchical clustering is carried out on the extracted main components to obtain primary selection water quality indexes of different subareas, and the method specifically comprises the following steps:
Processing the main components in each subarea through hierarchical clustering, judging the distance by taking the sum of squares of the deviations as a measurement function, constructing n classes according to the distance between every two main components, merging the classes with the minimum distance, and constructing a new class by taking the shortest distance as the distance between the classes;
After iterative clustering is performed, when a stopping condition is reached, a clustering result is output, a simplified main component is obtained, and variance contribution rate representing importance degrees corresponding to the main components in different clusters are obtained;
And acquiring the simplified evaluation factor class labels of the main components, presetting an index quantity threshold according to the importance degree, and selecting a corresponding quantity of standard exceeding indexes from the evaluation factor class labels of the main components as primary water quality indexes of the subareas.
In this scheme, time change characteristic and space change characteristic specifically do:
according to the primary selected water quality indexes of different subareas, carrying out fusion to obtain an index fusion sequence, optimizing a Seq2Seq model by utilizing an LSTM unit, and importing the index fusion sequence into the optimized Seq2Seq model for coding;
setting an encoder and a decoder in a Seq2Seq model as LSTM units, updating the encoder by a plurality of time steps to obtain a hidden state corresponding to an index fusion sequence, and importing the hidden state into the decoder for decoding and updating;
Introducing an attention mechanism into a decoder structure, reading output vectors in a hidden layer, distributing different attention weights, capturing effective characteristic information, and performing aggregation to generate time variation characteristics of groundwater quality of each subarea;
Utilizing time change characteristics and space distances among different subareas to represent correlations among the subareas, setting connection information among the different subareas according to the correlations, constructing an undirected graph by combining the distribution of the subareas, and acquiring an adjacent matrix based on the undirected graph;
Performing representation learning on the adjacent matrix through a bidirectional graph attention network, introducing a multi-head attention mechanism into a bidirectional graph attention layer, calculating attention coefficients of the characteristics of the neighborhood subregions by using the attention mechanism, and connecting the attention coefficients in series to respectively obtain new subregion node characteristic representations;
and combining the forward propagation feature matrix and the backward propagation feature matrix to obtain the spatial variation features of the groundwater quality of each subarea.
In this scheme, according to time change characteristic and space change characteristic are fed back to the primary election water quality index, and analysis obtains potential water quality index, specifically does:
predicting the groundwater environment quality of the target area by utilizing the time change characteristics and the space change characteristics in each subarea, training and verifying by using historical survey data, and obtaining the deviation of water quality prediction data after the preset time and current water quality data;
And selecting out the relative primary water quality indexes according to the deviation, sorting according to the deviation degree, and selecting out-of-standard indexes with the number corresponding to the sorting by using a k nearest neighbor method as potential water quality indexes based on the primary water quality indexes in the sorting.
In the scheme, a comprehensive evaluation model is constructed through the primary water quality index and the potential water quality index to generate a comprehensive quantitative evaluation result of the groundwater quality of a target area, which is specifically as follows:
Establishing a comprehensive evaluation model of the groundwater environment based on a hierarchical analysis method and fuzzy comprehensive evaluation in combination with the primary water quality index and the potential water quality index, and acquiring weights of different evaluation factor category labels through the hierarchical analysis method;
Evaluating the underground water quality data of the target area by utilizing threshold information of the initially selected water quality index and the potential water quality index to obtain an index evaluation result, digitizing the index evaluation result, combining the weight with the index evaluation result, and superposing to obtain a comprehensive evaluation result of the underground water quality of the subarea;
and comparing the comprehensive evaluation results at different times, and polymerizing the comparison results of all the subareas to obtain the quantitative evaluation result of the groundwater quality of the target area.
The invention also provides a quantitative evaluation system for the space-time change of the quality of the regional groundwater environment, which comprises: the quantitative evaluation method for the regional groundwater environment quality space-time change is implemented by the processor when being executed by the processor as follows:
Acquiring historical investigation data of groundwater environment quality of a target area, carrying out data preprocessing on the historical investigation data, and screening out standard exceeding indexes corresponding to the preprocessed historical investigation data based on groundwater quality conventional factors;
Dividing the target area according to the standard exceeding index, obtaining main components corresponding to the standard exceeding index by utilizing main component analysis in each divided subarea block, and carrying out hierarchical clustering on the extracted main components to obtain primary selection water quality indexes of different subareas;
Acquiring time variation characteristics of groundwater quality of different subareas through primary selection of water quality indexes, analyzing correlation among the different subareas by utilizing the time variation characteristics in combination with geographic positions, and acquiring space variation characteristics of groundwater quality of the different subareas based on the correlation;
And feeding back the primary water quality index according to the time change characteristic and the space change characteristic, analyzing and obtaining a potential water quality index, constructing a comprehensive evaluation model through the primary water quality index and the potential water quality index, and generating a comprehensive quantitative evaluation result of the underground water quality of the target area.
The invention discloses a quantitative evaluation method and a quantitative evaluation system for the quality space-time change of regional groundwater environment, wherein the quantitative evaluation method comprises the following steps: acquiring historical investigation data of groundwater environment quality of a target area, and screening out standard exceeding indexes corresponding to the preprocessed historical investigation data based on groundwater quality conventional factors; dividing the target area, analyzing the main component to obtain a main component corresponding to the standard exceeding index, and performing hierarchical clustering on the extracted main component to obtain a primary water quality index; acquiring time change characteristics and space change characteristics of groundwater quality in different subareas; extracting potential water quality indexes, constructing a comprehensive evaluation model through the primary water quality indexes and the potential water quality indexes, and carrying out comprehensive quantitative evaluation. The method acquires the time and space between the groundwater in the area based on the high-correlation index, screens the special evaluation index for the evaluation area, enables comprehensive quantitative evaluation of the groundwater environment quality to be more comprehensive and effective, and provides regional key information for long-term monitoring of groundwater pollution.
Drawings
FIG. 1 shows a flow chart of a quantitative evaluation method for the quality space-time change of the groundwater environment in a region;
FIG. 2 shows a flow chart of the invention for obtaining primary water quality indicators for different sub-areas;
FIG. 3 is a flow chart showing the time and space variation characteristics of the invention for obtaining primary water quality indicators;
FIG. 4 shows a block diagram of a quantitative evaluation system for the quality and time-space change of the groundwater environment in a region.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
FIG. 1 shows a flow chart of a quantitative evaluation method for the quality and time-space change of the groundwater environment in a region.
As shown in fig. 1, the first aspect of the present invention provides a quantitative evaluation method for the quality space-time variation of a regional groundwater environment, which includes:
S102, acquiring historical investigation data of the groundwater environment quality of a target area, carrying out data preprocessing on the historical investigation data, and screening out an exceeding index corresponding to the preprocessed historical investigation data based on a groundwater quality conventional factor;
S104, dividing the target area according to the standard exceeding index, obtaining main components corresponding to the standard exceeding index by utilizing main component analysis in each divided subarea block, and carrying out hierarchical clustering on the extracted main components to obtain primary selection water quality indexes of different subareas;
S106, obtaining time variation characteristics of groundwater quality of different subareas through primary selection of water quality indexes, analyzing correlations among the different subareas by utilizing the time variation characteristics in combination with geographic positions, and obtaining spatial variation characteristics of groundwater quality of the different subareas based on the correlations;
S108, feeding back the primary water quality index according to the time change characteristic and the space change characteristic, analyzing to obtain a potential water quality index, and constructing a comprehensive evaluation model through the primary water quality index and the potential water quality index to generate a comprehensive quantitative evaluation result of the groundwater quality of the target area.
The method is characterized in that data integration and data cleaning are carried out on multi-source historical survey data such as sampling data, sensor monitoring data and monitoring well monitoring data of the groundwater environment quality of a target area, corresponding water quality survey results are obtained to label the integrated and cleaned historical survey data, sliding windows and normalization processing are carried out on the historical survey data under different water quality labels, and the sliding windows are used for processing the sliding windows to increase correlation and time correlation among the dimensionalities of the historical survey data; obtaining the groundwater quality conventional factors through literature retrieval, preferably obtaining 37 indexes in total of the groundwater quality conventional factors (removing 2 radioactive factors) according to GB14848, and classifying the indexes corresponding to the groundwater quality conventional factors according to the influence factors exceeding the indexes, wherein the indexes are sensory form factors, water chemistry type conventional factors, human life and agricultural activities influence factors, industrial activity influence factors and multi-factor (geological background or artificial pollution) influence factors respectively; the sensory form factor includes color, smell and taste, turbidity, and macroscopic; the water chemistry type conventional factors include pH, total hardness, total dissolved solids, sulfate, chloride, sodium, iodide; the human life and agricultural activity influencing factors comprise oxygen consumption, ammonia nitrogen, total coliform, total bacterial colony count, nitrite and nitrate; the industrial activity influencing factors comprise arsenic, hexavalent chromium, cadmium, lead, nickel, copper, mercury, lead, cyanide, volatile phenols, chloroform, carbon tetrachloride, benzene and toluene; the multi-factor (geological background or artificial pollution) influencing factors comprise iron, manganese, fluoride, zinc, aluminum and selenium.
Acquiring an underground water quality monitoring instance, acquiring critical values of normal water quality monitoring data corresponding to different indexes in the underground water quality monitoring instance, generating threshold information according to the critical values, acquiring threshold sets of the indexes under different evaluation factor category labels, and constructing a threshold matrix; comparing the preprocessed historical survey data according to the threshold matrix, and assigning 0 to indexes larger than the threshold in the matrix and 1 to indexes at other positions to realize screening of exceeding indexes in different types of evaluation factors.
The target area is divided according to the standard exceeding index, and the main component analysis is utilized to obtain the main component corresponding to the standard exceeding index in each divided subarea block, specifically: acquiring two-dimensional map data of a target area, performing interpolation processing on the preprocessed historical survey data by using geographic position information in the historical survey data, performing position visualization processing on the historical survey data, performing grid processing on the two-dimensional map data, and determining out-of-standard indexes in different grids; setting similarity coefficients according to the number of the superscalar indexes under different types of evaluation factors in a target area, acquiring evaluation factor type labels related to adjacent grids, calculating the similarity between the superscalar indexes, accumulating the superscalar index similarity of the same evaluation factor type standard sign, calling the corresponding similarity coefficients to weight the accumulated sum, and acquiring the final similarity between the adjacent grids; when the final similarity accords with a preset similarity threshold, regarding two adjacent grids as the same subarea, and generating a segmentation result of the subarea after traversing all grids of the target area; and (3) performing principal component analysis in the superscalar index subsets corresponding to the subareas, and extracting principal components in the superscalar indexes.
FIG. 2 shows a flow chart of the invention for obtaining primary water quality indicators for different sub-areas.
According to the embodiment of the invention, the extracted main components are subjected to hierarchical clustering to obtain the primary selected water quality indexes of different subareas, specifically:
S202, processing main components in each sub-region through hierarchical clustering, judging distances through a dispersion square sum as a measurement function, constructing n classes according to the distances between every two main components, merging the classes with the minimum distances, and constructing new classes by taking the shortest distances as inter-class distances;
S204, calculating the distance between the new class and the current class, after iterative clustering, outputting a clustering result when a stopping condition is reached, acquiring simplified main components, and acquiring variance contribution rate representing importance degrees corresponding to the main components in different classes of clusters;
S206, acquiring the simplified evaluation factor category labels of the main components, presetting an index quantity threshold according to the importance degree, and selecting the corresponding quantity of out-of-standard indexes from the evaluation factor category labels of the main components as primary water quality indexes of the subareas.
The distance between the principal components is judged by using the sum of squares of the dispersion as a measurement function, the sum of squares of the dispersion represents the average distance between each element and other elements in each class, the average distances are squared and summed, the distance between the principal components is judged by using the sum of squares of the dispersion, the clustering error is reduced, the principal components are classified into a plurality of groups of data sets with stronger correlation by using hierarchical clustering, and the principal characteristics are determined so as to simplify the data sets and highlight the differences existing between the principal components. In different clusters of hierarchical clustering results, the importance degree is represented according to the variance contribution rate of the main component in the main component analysis, the number of the out-of-standard indexes is more screened as the importance degree is larger, the maximum value and the minimum value corresponding to the out-of-standard indexes are obtained under the evaluation factor type labels according to the evaluation factor type labels corresponding to the main component in different clusters, and the distance between each out-of-standard index and the maximum value of other out-of-standard indexes is calculatedAnd distance of minimum value/>Calculating the contribution rate/>, of each exceeding index according to the distanceAccumulating the contribution rates from large to small, and taking the first n indexes with the accumulated contribution rate more than or equal to 50%, wherein the selection quantity of the indexes is determined by the importance degree.
FIG. 3 shows a flow chart of the invention for obtaining time and space varying characteristics of the primary water quality indicator.
According to the embodiment of the invention, the time variation characteristic and the space variation characteristic are specifically:
S302, carrying out fusion according to primary selection water quality indexes of different subareas to obtain an index fusion sequence, optimizing a Seq2Seq model by utilizing an LSTM unit, and importing the index fusion sequence into the optimized Seq2Seq model for coding;
S304, setting an encoder and a decoder in the Seq2Seq model as LSTM units, updating the encoder in a plurality of time steps to obtain hidden states corresponding to the index fusion sequence, and importing the hidden states into the decoder for decoding and updating;
S306, introducing an attention mechanism into the decoder structure, reading output vectors in the hidden layer, distributing different attention weights, capturing effective characteristic information, and performing aggregation to generate time variation characteristics of groundwater quality of each subarea;
s308, utilizing time change characteristics and space distances among different subareas to represent correlations among the subareas, setting connection information among the different subareas according to the correlations, constructing an undirected graph by combining the distribution of the subareas, and acquiring an adjacent matrix based on the undirected graph;
S310, performing representation learning on the adjacent matrix through a bidirectional graph attention network, introducing a multi-head attention mechanism into a bidirectional graph attention layer, calculating attention coefficients of the characteristics of the neighborhood subregions by using the attention mechanism, and connecting the attention coefficients in series to respectively obtain new subregion node characteristic representations;
S312, combining the forward propagation feature matrix and the backward propagation feature matrix to obtain the spatial variation features of the groundwater quality of each subarea.
It should be noted that, the LSTM unit is used to optimize the Seq2Seq model, so that the model has a long-term memory function, and can allow the encoder to update in a plurality of time steps when the input time step and the output time step are different, obtain the hidden state of the final time step, and import the hidden state into the decoder to strengthen the memory function, and the hidden state at each time is updated with the hidden state and the cell state at the last time through the input at the current time, and the output vectors of all hidden layers in the decoder are read and distributed with different specific weights before the decoder generates the new state through the attention mechanism, so that the network can capture the time variation characteristics in a targeted manner, the introduction of the attention mechanism calculates the importance degree of each input by using the scoring function, and gives different weights, thereby capturing the effective information of each hidden layer, and effectively improving the accuracy of the time variation characteristics.
The two-way graph attention network is utilized to learn the graph structure corresponding to each subarea, attention is distributed to the node and the adjacent node set in the attention layer, nonlinear processing is conducted by introducing nonlinear activation function functions, a multi-head attention mechanism is introduced into the attention layer, each attention head can aggregate the characteristics of the characteristic space by adopting the attention mechanism, and more optimal model expression can be obtained after combining a plurality of outputs. The method comprises the steps of respectively obtaining graph structures in two directions from top to bottom and from bottom to top through a bidirectional graph attention network, outputting hidden characteristics in the two directions through the graph attention network, wherein the output characteristics of each sub-area node after graph attention aggregation operation are information sets of all sub-area nodes on an undirected graph, respectively carrying out series operation on feature matrixes output in two directions to obtain new sub-area node characteristic representation, extracting groundwater quality space change characteristics corresponding to sub-areas through the graph attention network, and aggregating more valuable space characteristics through a multi-head graph attention network based on all sub-area node characteristics in the water quality change process.
The prediction of the groundwater environment quality of the target area is carried out in each subarea by utilizing the time change characteristics and the space change characteristics by utilizing the deep learning methods such as LSTM and the like, training and verification are carried out by utilizing historical investigation data, and the deviation of water quality prediction data and current water quality data after the preset time is obtained; and selecting out the relative primary water quality indexes according to the deviation, sorting according to the deviation degree, and selecting out-of-standard indexes with the number corresponding to the sorting by using a k nearest neighbor method based on the primary water quality indexes in the sorting as potential water quality indexes, wherein the potential water quality indexes are similar indexes of the primary water quality indexes with overlarge current deviation, and represent potential pollution possibly facing the future of the target area.
The method is characterized in that a comprehensive evaluation model of the groundwater environment is established based on an analytic hierarchy process and fuzzy comprehensive evaluation in combination with primary water quality indexes and potential water quality indexes, and weights of different evaluation factor category labels are obtained through the analytic hierarchy process; the influence of maximum value on the evaluation structure is highlighted before the analytic hierarchy process is adopted, a maximum value index is added, the maximum value index max takes the maximum value of qualitative evaluation of various evaluation factors, and the analytic hierarchy process comprises the following steps:
Expert questionnaire scoring is carried out on the importance degree of each factor, and the number of questionnaire experts is not less than 10, so that each expert gives a factor importance matrix The matrix is an n×n-order square matrix, n=6 is the number of evaluation factor classes including max,/>The importance degree of the i-class factors to the j-class factors is represented as equal importance, 3 is slightly important, 5 is important, 7 is very important, 9 is extremely important, 2, 4, 6 and 8 are intermediate importance degrees,/>After scoring the importance score, then/>；
Recording deviceFor factor importance matrix given by mth expert, calculating geometric mean value/>, corresponding term of each expert factor importance matrixThe mean matrix is recorded as/>；
Calculating a weight coefficient by using the mean matrix A: listing the equationSolve the/>, in the equationAnd/>If there are multiple sets of solutions/>Maximum value/>Corresponding/>Is a weight coefficient;
calculating the consistency CR value to judge whether the A matrix investigation result is reasonable, ; Wherein the method comprises the steps ofRI is obtained by looking up a random consistency coefficient table: when n=6, RI takes 1.24. If CR is less than 0.1, the A matrix investigation result is considered to be reasonable, if CR is not less than 0.1, the A matrix investigation result is considered to be unreasonable, at the moment, the result is anonymously fed back to each expert, and the steps are repeated by re-questionnaire scoring;
by means of the weighting coefficients to be derived last Normalized and denoted/>Utilization/>Quantitatively evaluating the quality of the groundwater environment of the target area, evaluating the groundwater quality data of the target area by utilizing threshold information of the primary water quality index and the potential water quality index to obtain an index evaluation result, and digitizing the index evaluation result, namely I=1, II=2, III=3, IV=4 and V=5, and synthesizing the evaluation result/>，/>And comparing composite target evaluation results of the i-th factor with comprehensive evaluation results of different time to obtain quantitative evaluation results of the groundwater quality in the subareas. And comparing the comprehensive evaluation results at different times in each subarea, and aggregating the comparison results of all subareas to obtain the quantitative evaluation result of the groundwater quality of the target area.
FIG. 4 shows a block diagram of a quantitative evaluation system for the quality and time-space change of the groundwater environment in a region.
The second aspect of the invention also provides a quantitative evaluation system 4 for the space-time change of the quality of the regional groundwater environment, which comprises: the quantitative evaluation method program for the regional groundwater environment quality space-time change is implemented by the processor when executed by the processor, and comprises the following steps:
Acquiring historical investigation data of groundwater environment quality of a target area, carrying out data preprocessing on the historical investigation data, and screening out standard exceeding indexes corresponding to the preprocessed historical investigation data based on groundwater quality conventional factors;
Dividing the target area according to the standard exceeding index, obtaining main components corresponding to the standard exceeding index by utilizing main component analysis in each divided subarea block, and carrying out hierarchical clustering on the extracted main components to obtain primary selection water quality indexes of different subareas;
Acquiring time variation characteristics of groundwater quality of different subareas through primary selection of water quality indexes, analyzing correlation among the different subareas by utilizing the time variation characteristics in combination with geographic positions, and acquiring space variation characteristics of groundwater quality of the different subareas based on the correlation;
And feeding back the primary water quality index according to the time change characteristic and the space change characteristic, analyzing and obtaining a potential water quality index, constructing a comprehensive evaluation model through the primary water quality index and the potential water quality index, and generating a comprehensive quantitative evaluation result of the underground water quality of the target area.
The third aspect of the present invention also provides a computer readable storage medium, where the computer readable storage medium includes a quantitative evaluation method program for quality and time variation of regional groundwater environment, and when the quantitative evaluation method program for quality and time variation of regional groundwater environment is executed by a processor, the steps of the quantitative evaluation method for quality and time variation of regional groundwater environment are implemented.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or optical disk, or the like, which can store program codes.
Or the above-described integrated units of the invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The quantitative evaluation method for the space-time change of the quality of the regional groundwater environment is characterized by comprising the following steps:
Acquiring historical investigation data of groundwater environment quality of a target area, carrying out data preprocessing on the historical investigation data, and screening out standard exceeding indexes corresponding to the preprocessed historical investigation data based on groundwater quality conventional factors;
Dividing the target area according to the standard exceeding index, obtaining main components corresponding to the standard exceeding index by utilizing main component analysis in each divided subarea block, and carrying out hierarchical clustering on the extracted main components to obtain primary selection water quality indexes of different subareas;
Acquiring time variation characteristics of groundwater quality of different subareas through primary selection of water quality indexes, analyzing correlation among the different subareas by utilizing the time variation characteristics in combination with geographic positions, and acquiring space variation characteristics of groundwater quality of the different subareas based on the correlation;
And feeding back the primary water quality index according to the time change characteristic and the space change characteristic, analyzing and obtaining a potential water quality index, constructing a comprehensive evaluation model through the primary water quality index and the potential water quality index, and generating a comprehensive quantitative evaluation result of the underground water quality of the target area.
2. The quantitative evaluation method for the space-time change of the quality of the regional groundwater environment according to claim 1, wherein the method is characterized in that the method is based on the standard exceeding index corresponding to the historical investigation data after the screening pretreatment of the groundwater quality conventional factors, and specifically comprises the following steps:
Carrying out data integration and data cleaning on multi-source historical investigation data of the groundwater environment quality of a target area, obtaining corresponding water quality investigation results, marking the integrated and cleaned historical investigation data, and carrying out sliding window and normalization processing on the historical investigation data under different water quality labels;
Obtaining a groundwater quality conventional factor through literature retrieval, and classifying the indexes corresponding to the groundwater quality conventional factor according to the influence factors with exceeding indexes, wherein the indexes are sensory form factors, water chemistry type conventional factors, human life and agricultural activity influence factors, industrial activity influence factors and multi-factor influence factors respectively;
Acquiring an underground water quality monitoring instance, acquiring critical values of normal water quality monitoring data corresponding to different indexes in the underground water quality monitoring instance, generating threshold information according to the critical values, acquiring threshold sets of the indexes under different evaluation factor category labels, and constructing a threshold matrix;
comparing the preprocessed historical survey data according to the threshold matrix, and assigning 0 to indexes larger than the threshold in the matrix and 1 to indexes at other positions to realize screening of exceeding indexes in different types of evaluation factors.
3. The quantitative evaluation method for the spatial and temporal changes of the quality of the regional groundwater environment according to claim 1, wherein the target region is divided according to the exceeding index, and the main components corresponding to the exceeding index are obtained by using main component analysis in each divided sub-region block, specifically:
Acquiring two-dimensional map data of a target area, performing interpolation processing on the preprocessed historical survey data by using geographic position information in the historical survey data, performing grid processing on the two-dimensional map data, and determining out-of-standard indexes in different grids;
Setting similarity coefficients according to the number of the exceeding indexes under different types of evaluation factors in the target area, acquiring evaluation factor type labels related to adjacent grids, calculating the similarity between the exceeding indexes, calling the corresponding similarity coefficients to weight, and acquiring the final similarity between the adjacent grids;
when the final similarity accords with a preset similarity threshold, regarding two adjacent grids as the same subarea, and generating a segmentation result of the subarea after traversing all grids of the target area;
and (3) performing principal component analysis in the superscalar index subsets corresponding to the subareas, and extracting principal components in the superscalar indexes.
4. The quantitative evaluation method for the space-time change of the quality of the regional groundwater environment according to claim 1, wherein the extracted main components are subjected to hierarchical clustering to obtain primary selection water quality indexes of different subregions, and the method is specifically as follows:
Processing the main components in each subarea through hierarchical clustering, judging the distance by taking the sum of squares of the deviations as a measurement function, constructing n classes according to the distance between every two main components, merging the classes with the minimum distance, and constructing a new class by taking the shortest distance as the distance between the classes;
After iterative clustering is performed, when a stopping condition is reached, a clustering result is output, a simplified main component is obtained, and variance contribution rate representing importance degrees corresponding to the main components in different clusters are obtained;
And acquiring the simplified evaluation factor class labels of the main components, presetting an index quantity threshold according to the importance degree, and selecting a corresponding quantity of standard exceeding indexes from the evaluation factor class labels of the main components as primary water quality indexes of the subareas.
5. The quantitative evaluation method for the space-time change of the quality of the regional groundwater environment according to claim 1, wherein the time change characteristic and the space change characteristic are specifically as follows:
according to the primary selected water quality indexes of different subareas, carrying out fusion to obtain an index fusion sequence, optimizing a Seq2Seq model by utilizing an LSTM unit, and importing the index fusion sequence into the optimized Seq2Seq model for coding;
setting an encoder and a decoder in a Seq2Seq model as LSTM units, updating the encoder by a plurality of time steps to obtain a hidden state corresponding to an index fusion sequence, and importing the hidden state into the decoder for decoding and updating;
Introducing an attention mechanism into a decoder structure, reading output vectors in a hidden layer, distributing different attention weights, capturing effective characteristic information, and performing aggregation to generate time variation characteristics of groundwater quality of each subarea;
Utilizing time change characteristics and space distances among different subareas to represent correlations among the subareas, setting connection information among the different subareas according to the correlations, constructing an undirected graph by combining the distribution of the subareas, and acquiring an adjacent matrix based on the undirected graph;
Performing representation learning on the adjacent matrix through a bidirectional graph attention network, introducing a multi-head attention mechanism into a bidirectional graph attention layer, calculating attention coefficients of the characteristics of the neighborhood subregions by using the attention mechanism, and connecting the attention coefficients in series to respectively obtain new subregion node characteristic representations;
and combining the forward propagation feature matrix and the backward propagation feature matrix to obtain the spatial variation features of the groundwater quality of each subarea.
6. The quantitative evaluation method for the space-time change of the quality of the regional groundwater environment according to claim 1, wherein the initially selected water quality index is fed back according to the time change characteristic and the space change characteristic, and potential water quality indexes are obtained through analysis, specifically:
predicting the groundwater environment quality of the target area by utilizing the time change characteristics and the space change characteristics in each subarea, training and verifying by using historical survey data, and obtaining the deviation of water quality prediction data after the preset time and current water quality data;
And selecting out the relative primary water quality indexes according to the deviation, sorting according to the deviation degree, and selecting out-of-standard indexes with the number corresponding to the sorting by using a k nearest neighbor method as potential water quality indexes based on the primary water quality indexes in the sorting.
7. The quantitative evaluation method for the regional groundwater environment quality space-time variation according to claim 1, wherein a comprehensive evaluation model is constructed by initially selecting water quality indexes and potential water quality indexes to generate a comprehensive quantitative evaluation result of the target regional groundwater quality, specifically:
Establishing a comprehensive evaluation model of the groundwater environment based on a hierarchical analysis method and fuzzy comprehensive evaluation in combination with the primary water quality index and the potential water quality index, and acquiring weights of different evaluation factor category labels through the hierarchical analysis method;
Evaluating the underground water quality data of the target area by utilizing threshold information of the initially selected water quality index and the potential water quality index to obtain an index evaluation result, digitizing the index evaluation result, combining the weight with the index evaluation result, and superposing to obtain a comprehensive evaluation result of the underground water quality of the subarea;
and comparing the comprehensive evaluation results at different times, and polymerizing the comparison results of all the subareas to obtain the quantitative evaluation result of the groundwater quality of the target area.
8. The quantitative evaluation system for the space-time change of the quality of the regional groundwater environment is characterized by comprising: the quantitative evaluation method for the regional groundwater environment quality space-time change is implemented by the processor when being executed by the processor as follows:
Acquiring historical investigation data of groundwater environment quality of a target area, carrying out data preprocessing on the historical investigation data, and screening out standard exceeding indexes corresponding to the preprocessed historical investigation data based on groundwater quality conventional factors;
Dividing the target area according to the standard exceeding index, obtaining main components corresponding to the standard exceeding index by utilizing main component analysis in each divided subarea block, and carrying out hierarchical clustering on the extracted main components to obtain primary selection water quality indexes of different subareas;
Acquiring time variation characteristics of groundwater quality of different subareas through primary selection of water quality indexes, analyzing correlation among the different subareas by utilizing the time variation characteristics in combination with geographic positions, and acquiring space variation characteristics of groundwater quality of the different subareas based on the correlation;
And feeding back the primary water quality index according to the time change characteristic and the space change characteristic, analyzing and obtaining a potential water quality index, constructing a comprehensive evaluation model through the primary water quality index and the potential water quality index, and generating a comprehensive quantitative evaluation result of the underground water quality of the target area.
9. The quantitative evaluation system for the spatial and temporal changes of the quality of the regional groundwater environment according to claim 8, wherein the temporal change features and the spatial change features are specifically as follows:
according to the primary selected water quality indexes of different subareas, carrying out fusion to obtain an index fusion sequence, optimizing a Seq2Seq model by utilizing an LSTM unit, and importing the index fusion sequence into the optimized Seq2Seq model for coding;
setting an encoder and a decoder in a Seq2Seq model as LSTM units, updating the encoder by a plurality of time steps to obtain a hidden state corresponding to an index fusion sequence, and importing the hidden state into the decoder for decoding and updating;
Introducing an attention mechanism into a decoder structure, reading output vectors in a hidden layer, distributing different attention weights, capturing effective characteristic information, and performing aggregation to generate time variation characteristics of groundwater quality of each subarea;
Utilizing time change characteristics and space distances among different subareas to represent correlations among the subareas, setting connection information among the different subareas according to the correlations, constructing an undirected graph by combining the distribution of the subareas, and acquiring an adjacent matrix based on the undirected graph;
Performing representation learning on the adjacent matrix through a bidirectional graph attention network, introducing a multi-head attention mechanism into a bidirectional graph attention layer, calculating attention coefficients of the characteristics of the neighborhood subregions by using the attention mechanism, and connecting the attention coefficients in series to respectively obtain new subregion node characteristic representations;
and combining the forward propagation feature matrix and the backward propagation feature matrix to obtain the spatial variation features of the groundwater quality of each subarea.
10. The quantitative evaluation system for the space-time change of the quality of the regional groundwater environment according to claim 8, wherein the initially selected water quality index is fed back according to the time change characteristic and the space change characteristic, and potential water quality indexes are obtained through analysis, specifically:
predicting the groundwater environment quality of the target area by utilizing the time change characteristics and the space change characteristics in each subarea, training and verifying by using historical survey data, and obtaining the deviation of water quality prediction data after the preset time and current water quality data;
And selecting out the relative primary water quality indexes according to the deviation, sorting according to the deviation degree, and selecting out-of-standard indexes with the number corresponding to the sorting by using a k nearest neighbor method as potential water quality indexes based on the primary water quality indexes in the sorting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410557746.6A CN118134120B (en) | 2024-05-08 | 2024-05-08 | Quantitative evaluation method and system for regional groundwater environment quality space-time change |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410557746.6A CN118134120B (en) | 2024-05-08 | 2024-05-08 | Quantitative evaluation method and system for regional groundwater environment quality space-time change |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118134120A true CN118134120A (en) | 2024-06-04 |
| CN118134120B CN118134120B (en) | 2024-07-12 |
Family
ID=91238023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410557746.6A Active CN118134120B (en) | 2024-05-08 | 2024-05-08 | Quantitative evaluation method and system for regional groundwater environment quality space-time change |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118134120B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913411A (en) * | 2016-05-10 | 2016-08-31 | 云南大学 | Lake water quality evaluation prediction system and method based on factor weighting model |
| US20170328878A1 (en) * | 2016-05-13 | 2017-11-16 | Chinese Research Academy Of Environmental Sciences | Rating evaluation method for groundwater pollution source intensity |
| CN109284921A (en) * | 2018-09-17 | 2019-01-29 | 北京工商大学 | Agricultural irrigation dynamic evaluation of water quality method based on Hidden Markov Model |
| US20200252283A1 (en) * | 2017-10-16 | 2020-08-06 | Chinese Research Academy Of Environmental Sciences | Multi-objective optimization method for groundwater pollution monitoring network |
| CN112288275A (en) * | 2020-10-29 | 2021-01-29 | 中水三立数据技术股份有限公司 | Groundwater water quality analysis and evaluation system and method based on Internet of things |
| KR20210080772A (en) * | 2019-12-23 | 2021-07-01 | 한국건설기술연구원 | Water quality analysis system using labeling of water quality data and learning of artificial neural networks |
| CN113325153A (en) * | 2021-06-18 | 2021-08-31 | 军事科学院军事医学研究院环境医学与作业医学研究所 | Water quality multi-parameter monitoring comprehensive information management system |
| CN114997546A (en) * | 2022-08-05 | 2022-09-02 | 天津市地质研究和海洋地质中心 | Comprehensive survey evaluation method, system and medium for monitoring well based on multi-source data |
| CN116609500A (en) * | 2023-06-02 | 2023-08-18 | 无锡点创科技有限公司 | Water quality data monitoring method based on Internet of things |
-
2024
- 2024-05-08 CN CN202410557746.6A patent/CN118134120B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105913411A (en) * | 2016-05-10 | 2016-08-31 | 云南大学 | Lake water quality evaluation prediction system and method based on factor weighting model |
| US20170328878A1 (en) * | 2016-05-13 | 2017-11-16 | Chinese Research Academy Of Environmental Sciences | Rating evaluation method for groundwater pollution source intensity |
| US20200252283A1 (en) * | 2017-10-16 | 2020-08-06 | Chinese Research Academy Of Environmental Sciences | Multi-objective optimization method for groundwater pollution monitoring network |
| CN109284921A (en) * | 2018-09-17 | 2019-01-29 | 北京工商大学 | Agricultural irrigation dynamic evaluation of water quality method based on Hidden Markov Model |
| KR20210080772A (en) * | 2019-12-23 | 2021-07-01 | 한국건설기술연구원 | Water quality analysis system using labeling of water quality data and learning of artificial neural networks |
| CN112288275A (en) * | 2020-10-29 | 2021-01-29 | 中水三立数据技术股份有限公司 | Groundwater water quality analysis and evaluation system and method based on Internet of things |
| CN113325153A (en) * | 2021-06-18 | 2021-08-31 | 军事科学院军事医学研究院环境医学与作业医学研究所 | Water quality multi-parameter monitoring comprehensive information management system |
| CN114997546A (en) * | 2022-08-05 | 2022-09-02 | 天津市地质研究和海洋地质中心 | Comprehensive survey evaluation method, system and medium for monitoring well based on multi-source data |
| CN116609500A (en) * | 2023-06-02 | 2023-08-18 | 无锡点创科技有限公司 | Water quality data monitoring method based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118134120B (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109034448B (en) | Trajectory prediction method based on vehicle trajectory semantic analysis and deep belief network | |
| CN111178611B (en) | Method for predicting daily electric quantity | |
| CN109657947A (en) | A kind of method for detecting abnormality towards enterprises ' industry classification | |
| CN105678428A (en) | Criminal suspicion probability prediction method and system | |
| CN114997546B (en) | Comprehensive survey evaluation method, system and medium for monitoring well based on multi-source data | |
| CN113554466A (en) | Short-term power consumption prediction model construction method, prediction method and device | |
| CN112084240B (en) | Intelligent identification and linkage treatment method and system for group renting | |
| CN115238197B (en) | Expert thinking model-based domain business auxiliary analysis method | |
| CN110889560A (en) | Express delivery sequence prediction method with deep interpretability | |
| CN112330441A (en) | Method for evaluating business value credit loan of medium and small enterprises | |
| Farjami et al. | A genetic-fuzzy algorithm for spatio-temporal crime prediction | |
| CN116776949A (en) | Machine learning chemical exploration data processing method and system based on mineral control element restriction | |
| Stracuzzi et al. | Quantifying Uncertainty to Improve Decision Making in Machine Learning. | |
| CN118134120B (en) | Quantitative evaluation method and system for regional groundwater environment quality space-time change | |
| Babu et al. | Water quality prediction using neural networks | |
| Morajda et al. | An enhancement of Kohonen neural networks for predictive analytics: Self-Organizing Prediction Maps | |
| CN117033923A (en) | Method and system for predicting crime quantity based on interpretable machine learning | |
| Gai et al. | Research on water quality spatiotemporal forecasting model based on ST-BIGRU-SVR neural network | |
| KR101280388B1 (en) | System and method for geospatial event occurrence prediction | |
| Sim et al. | Temporal Attention Gate Network With Temporal Decomposition for Improved Prediction Accuracy of Univariate Time-Series Data | |
| Yang et al. | Risk assessment and classification prediction for water environment treatment PPP projects | |
| Chen | Construction of a carbon neutral enterprise environmental performance assessment model based on transformer-GRU | |
| Chen et al. | An approach of multi-element fusion method for harmful algal blooms prediction | |
| Rai et al. | Predicting Crime Rate in Toronto | |
| CN117473435B (en) | Method for detecting false abnormal information of sudden public health event based on space-time characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |