CN110264094A - Evaluation method, equipment, storage medium and the device of heavy metal pollution of soil - Google Patents
Evaluation method, equipment, storage medium and the device of heavy metal pollution of soil Download PDFInfo
- Publication number
- CN110264094A CN110264094A CN201910552212.3A CN201910552212A CN110264094A CN 110264094 A CN110264094 A CN 110264094A CN 201910552212 A CN201910552212 A CN 201910552212A CN 110264094 A CN110264094 A CN 110264094A
- Authority
- CN
- China
- Prior art keywords
- heavy metal
- pollution
- concentration value
- neural network
- network model
- 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.)
- Pending
Links
- 229910001385 heavy metal Inorganic materials 0.000 title claims abstract description 177
- 239000002689 soil Substances 0.000 title claims abstract description 102
- 238000011156 evaluation Methods 0.000 title claims abstract description 72
- 238000003062 neural network model Methods 0.000 claims abstract description 109
- 238000012360 testing method Methods 0.000 claims abstract description 99
- 238000000034 method Methods 0.000 claims description 36
- 238000012549 training Methods 0.000 claims description 16
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 229910052751 metal Inorganic materials 0.000 claims description 4
- 239000002184 metal Substances 0.000 claims description 4
- 210000004218 nerve net Anatomy 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 210000005036 nerve Anatomy 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000003915 air pollution Methods 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000003900 soil pollution Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
Abstract
The invention discloses a kind of evaluation methods of heavy metal pollution of soil, equipment, storage medium and device, the present invention chooses several first test points from region to be evaluated, the first coordinate information and the first heavy metal concentration value of first test point are obtained respectively, based on first coordinate information and the first heavy metal concentration value, the class of pollution of the heavy metal pollution of soil in the region to be evaluated is determined by the first default neural network model, when evaluating heavy metal pollution of soil, introduce preset neural network model, and it is different from the subjective judgement that the evaluation result in existing evaluation method depends on people, evaluation method of the invention makes evaluation result more objective, accurately.
Description
Technical field
The present invention relates to Soil Contamination Evaluation technical field more particularly to a kind of evaluation method of heavy metal pollution of soil,
Equipment, storage medium and device.
Background technique
Currently, the research to heavy metal pollution of soil, is broadly divided into two classes: first is that oneself is acquired, due to sampling at
This is higher, and this is the mode for belonging to smallest number sample study, and still, the data of sample are very few, and data will lack to research
Soil range representativeness, be affected to the accuracy of result of study;Second is that utilizing others with reference to disclosed various documents
Sample data studied, still, largely using other people samples, it cannot be guaranteed that the authenticity of data.In addition, traditional soil
Evaluation of Heavy Metals Pollution relies on the subjective judgement of people, and the accuracy and reasonability of evaluation result are all lacking.
Summary of the invention
The main purpose of the present invention is to provide a kind of evaluation method of heavy metal pollution of soil, equipment, storage medium and
Device, it is intended to which during solving current soil Evaluation of Heavy Metals Pollution, sample size is few, and evaluation result is to personal subjective judgement
Dependence is big, the technical problem of evaluation result inaccuracy.
To achieve the above object, the present invention provides a kind of evaluation method of heavy metal pollution of soil, the method includes with
Lower step:
Several first test points are chosen from region to be evaluated;
The first coordinate information and the first heavy metal concentration value of first test point are obtained respectively;
Based on first coordinate information and the first heavy metal concentration value, institute is determined by the first default neural network model
State the class of pollution of the heavy metal pollution of soil in region to be evaluated.
Preferably, described after choosing several first test points in region to be evaluated, the method also includes:
Several second test points are chosen from the region to be evaluated, and obtain the second coordinate letter of each second test point
Breath;
Based on second coordinate information, the second of second test point is determined by the second default neural network model
Heavy metal concentration value;
Correspondingly, described to be based on first coordinate information and the first heavy metal concentration value, pass through the first default nerve net
Network model determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated, specifically includes:
Based on first coordinate information, the first heavy metal concentration value, the second coordinate information and the second heavy metal concentration value,
The class of pollution of the heavy metal pollution of soil in the region to be evaluated is determined by the first default neural network model.
Preferably, described to be based on first coordinate information and the first heavy metal concentration value, pass through the first default nerve net
Before network model determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated, the method also includes:
Obtain several sample areas information and the corresponding class of pollution of each sample areas information, the sample areas packet
Include the coordinate information and heavy metal concentration value of several test points in each sample areas;
The described first default mind is established according to the sample areas information and the corresponding class of pollution of each sample areas information
Through network model.
Preferably, described according to the sample areas information and the corresponding class of pollution foundation of each sample areas information
First default neural network model, specifically includes:
Obtain initial neural network model;
By the sample areas information and the corresponding class of pollution of each sample areas information, to the initial neural network
Model is trained, using the initial neural network model after training as the first default neural network model.
Preferably, first coordinate information for obtaining first test point respectively and the first heavy metal concentration value it
Afterwards, the method also includes:
Obtain initial neural network model;
Based on first coordinate information and the first heavy metal concentration value, the initial neural network model is instructed
Practice, using initial neural network model after training as the described second default neural network model.
Preferably, first coordinate information for obtaining first test point respectively and the first heavy metal concentration value it
Afterwards, the method also includes:
The first heavy metal concentration value is normalized respectively, is obtained corresponding with each first heavy metal concentration value
Target heavy metal concentration value;
Correspondingly, described to be based on first coordinate information and the first heavy metal concentration value, pass through the first default nerve net
Network model determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated, specifically includes:
Based on first coordinate information and target heavy metal concentration value, institute is determined by the first default neural network model
State the class of pollution of the heavy metal pollution of soil in region to be evaluated.
Preferably, the first heavy metal concentration value is normalized by following formula, is obtained and each first
The corresponding target heavy metal concentration value of heavy metal concentration value,
Wherein, XiFor i-th of first heavy metal concentration values, YiFor with XiCorresponding target heavy metal concentration value, XmaxFor number
It is worth maximum first heavy metal concentration value, XminFor the smallest first heavy metal concentration value of numerical value.
In addition, to achieve the above object, the present invention also provides a kind of pollution evaluation equipment of heavy metal-polluted soil, the equipment
It include: memory, processor and the dirt for being stored in the heavy metal-polluted soil that can be run on the memory and on the processor
Assessment process is contaminated, the pollution evaluation program of the heavy metal-polluted soil realizes soil as described above when being executed by the processor
The step of pollution evaluation method of heavy metal.
In addition, to achieve the above object, the present invention also provides a kind of storage medium, being stored with soil on the storage medium
The pollution evaluation program of heavy metal is realized as described above when the pollution evaluation program of the heavy metal-polluted soil is executed by processor
The step of pollution evaluation method of heavy metal-polluted soil.
In addition, to achieve the above object, the present invention also provides a kind of pollution evaluation device of heavy metal-polluted soil, the soil
The pollution evaluation device of heavy metal includes:
Module is chosen, for choosing several first test points from region to be evaluated;
Module is obtained, for obtaining the first coordinate information and the first heavy metal concentration value of first test point respectively;
Determining module passes through the first default nerve for being based on first coordinate information and the first heavy metal concentration value
Network model determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated.
In the present invention, several first test points are chosen from region to be evaluated, obtain first test point respectively
First coordinate information and the first heavy metal concentration value are based on first coordinate information and the first heavy metal concentration value, by the
One default neural network model determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated, to heavy metal-polluted soil
When pollution is evaluated, preset neural network model is introduced, and the evaluation result for being different from existing evaluation method relies primarily on
In the subjective judgement of people, evaluation method of the invention makes evaluation result more objective, accurate.
Detailed description of the invention
Fig. 1 is the device structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to;
Fig. 2 is the flow diagram of the pollution evaluation method first embodiment of heavy metal-polluted soil of the present invention;
Fig. 3 is the flow diagram of the pollution evaluation method second embodiment of heavy metal-polluted soil of the present invention;
Fig. 4 is the functional block diagram of the pollution evaluation device first embodiment of heavy metal-polluted soil of the present invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is the device structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to.
As shown in Figure 1, the equipment may include: processor 1001, such as CPU, communication bus 1002, user interface
1003, network interface 1004, memory 1005.Wherein, communication bus 1002 is for realizing the connection communication between these components.
User interface 1003 may include display screen (Display), optional user interface 1003 can also include standard wireline interface,
Wireless interface.Network interface 1004 optionally may include standard wireline interface and wireless interface (such as Wi-Fi interface).Storage
Device 1005 can be high speed RAM memory, be also possible to stable memory (non-volatile memory), such as disk
Memory.Memory 1005 optionally can also be the storage server independently of aforementioned processor 1001.
It will be understood by those skilled in the art that structure shown in Fig. 1 does not constitute the pollution to the heavy metal-polluted soil
The restriction of valuator device may include perhaps combining certain components or different components than illustrating more or fewer components
Arrangement.
As shown in Figure 1, as may include operating device, network communication mould in a kind of memory 1005 of storage medium
The pollution evaluation program of block, Subscriber Interface Module SIM and heavy metal-polluted soil.
In equipment shown in Fig. 1, network interface 1004 is mainly used for connecting background server, with the background server
Carry out data communication;User interface 1003 is mainly used for connecting user equipment;The equipment calls storage by processor 1001
The pollution evaluation program of the heavy metal-polluted soil stored in device 1005, and execute the dirt of heavy metal-polluted soil provided in an embodiment of the present invention
Contaminate evaluation method.
The equipment calls the pollution evaluation program of the heavy metal-polluted soil stored in memory 1005 by processor 1001,
And execute following operation:
Several first test points are chosen from region to be evaluated;
The first coordinate information and the first heavy metal concentration value of first test point are obtained respectively;
Based on first coordinate information and the first heavy metal concentration value, institute is determined by the first default neural network model
State the class of pollution of the heavy metal pollution of soil in region to be evaluated.
Further, processor 1001 can call the pollution evaluation journey of the heavy metal-polluted soil stored in memory 1005
Sequence also executes following operation:
Several second test points are chosen from the region to be evaluated, and obtain the second coordinate letter of each second test point
Breath;
Based on second coordinate information, the second of second test point is determined by the second default neural network model
Heavy metal concentration value;
Based on first coordinate information, the first heavy metal concentration value, the second coordinate information and the second heavy metal concentration value,
The class of pollution of the heavy metal pollution of soil in the region to be evaluated is determined by the first default neural network model.
Further, processor 1001 can call the pollution evaluation journey of the heavy metal-polluted soil stored in memory 1005
Sequence also executes following operation:
Obtain several sample areas information and the corresponding class of pollution of each sample areas information, the sample areas packet
Include the coordinate information and heavy metal concentration value of several test points in each sample areas;
The described first default mind is established according to the sample areas information and the corresponding class of pollution of each sample areas information
Through network model.
Further, processor 1001 can call the pollution evaluation journey of the heavy metal-polluted soil stored in memory 1005
Sequence also executes following operation:
Obtain initial neural network model;
By the sample areas information and the corresponding class of pollution of each sample areas information, to the initial neural network
Model is trained, using the initial neural network model after training as the first default neural network model.
Further, processor 1001 can call the pollution evaluation journey of the heavy metal-polluted soil stored in memory 1005
Sequence also executes following operation:
Obtain initial neural network model;
Based on first coordinate information and the first heavy metal concentration value, the initial neural network model is instructed
Practice, using initial neural network model after training as the described second default neural network model.
Further, processor 1001 can call the pollution evaluation journey of the heavy metal-polluted soil stored in memory 1005
Sequence also executes following operation:
The first heavy metal concentration value is normalized respectively, is obtained corresponding with each first heavy metal concentration value
Target heavy metal concentration value;
Based on first coordinate information and target heavy metal concentration value, institute is determined by the first default neural network model
State the class of pollution of the heavy metal pollution of soil in region to be evaluated.
In the present embodiment, several first test points are chosen from region to be evaluated, obtain first test point respectively
The first coordinate information and the first heavy metal concentration value, be based on first coordinate information and the first heavy metal concentration value, pass through
First default neural network model determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated, to a soil huge sum of money
Belong to pollution when being evaluated, introduce preset neural network model, and be different from the evaluation result of existing evaluation method mainly according to
Rely the subjective judgement in people, evaluation method of the invention makes evaluation result more objective, accurate.
Based on above-mentioned hardware configuration, the embodiment of the pollution evaluation method of heavy metal-polluted soil of the present invention is proposed.
It is the flow diagram of the pollution evaluation method first embodiment of heavy metal-polluted soil of the present invention referring to Fig. 2, Fig. 2.
In the first embodiment, the heavy metal-polluted soil pollution evaluation method the following steps are included:
Step S10: several first test points are chosen from region to be evaluated.
It should be noted that " second " in " first " and " the second test point " in " the first test point " in this programme
It is only intended to not constitute any restrictions to test point to the progress point of different types of test point, likewise, " first sits
" second " of " first " and " the second coordinate information " of mark information " is also only intended to carry out area to different types of coordinate information
Point, do not constitute any restrictions to coordinate information.
It is understood that the test point chosen is more, evaluation result is more accurate.But the test point of selection is too many, after
Continuous test process just needs to spend more costs.Therefore, when choosing test point, choosing can be determined according to specific circumstances
The number of the test point taken, the present embodiment are without restriction to this.
In addition, either choose how many a test points, the test point of selection all should be evenly distributed in it is described to be evaluated
In region, to keep the test point chosen more representative to the region to be evaluated, subsequent evaluation result also will more
Accurately.
Step S20: the first coordinate information and the first heavy metal concentration value of first test point are obtained respectively.
It should be noted that the first coordinate information in the present embodiment is longitude, latitude and the high level etc. of the first test point
The information of specific location of first test point in the region to be evaluated can be reacted.
In the concrete realization, first coordinate information can be after choosing the first test point, to the first test point phase
The coordinate information answered measures or searches corresponding map and obtains, and the first heavy metal concentration value can be described first
Position where test point is sampled, and according to relevant testing standard, carries out relevant test acquisition implementing room, certainly,
It can also be obtained by consulting the Research Literature having disclosed, however, it will be understood that obtained by consulting literatures first
The authenticity of heavy metal concentration value can not be guaranteed.
Further, in order to enable data preferably to adapt to transmission function, the error rate in calculating process is reduced, meter is accelerated
Speed and the degree of convergence are calculated, it, can also be to first weight after obtaining first coordinate information and the first heavy metal concentration value
Metal concentration value is converted, that is, is normalized, and target heavy metal corresponding with each first heavy metal concentration value is obtained
Concentration value is correspondingly based on first coordinate information and the first heavy metal concentration value subsequent, passes through the first default nerve
Network model determines the step of class of pollution of the heavy metal pollution of soil in the region to be evaluated specifically: based on described
First coordinate information and the more category concentration values of target weight, the soil in the region to be evaluated is determined by the first default neural network model
The class of pollution of earth heavy metal pollution.
Further, in this embodiment the first heavy metal concentration value is normalized by following formula,
Target heavy metal concentration value corresponding with each first heavy metal concentration value is obtained,
Wherein, XiFor i-th of first heavy metal concentration values, YiFor with XiCorresponding target heavy metal concentration value, XmaxFor number
It is worth maximum first heavy metal concentration value, XminFor the smallest first heavy metal concentration value of numerical value.
Step S30: it is based on first coordinate information and the first heavy metal concentration value, passes through the first default neural network mould
Type determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated.
It is understood that in the heavy metal-polluted soil for determining the region to be evaluated by the first default neural network model
Before the class of pollution of pollution, need first to establish the described first default neural network model.
In specific implementation, the described first default neural network model can be established in the following manner:
Obtain several sample areas information and the corresponding class of pollution of each sample areas information, the sample areas packet
Include the coordinate information and heavy metal concentration value of several test points in each sample areas;
The described first default mind is established according to the sample areas information and the corresponding class of pollution of each sample areas information
Through network model.
It is possible to further obtain initial neural network model first, pass through the sample areas information and each sample area
The corresponding class of pollution of domain information is trained the initial neural network model, by the initial neural network mould after training
Type is as the first default neural network model.
When specific implementation, available several sample areas and the corresponding class of pollution of each sample areas, and obtain initial
Neural network model, using sample areas as the input of initial network model, using the class of pollution of each sample areas as initial
The target of neural network model exports, and is trained to the initial neural network model, obtains the initial neural network mould
Type exports the error between reality output based on the target, according to the error, to institute to the reality output of sample areas
The parameter stated in initial neural network model is updated, until the error between target output and reality output can connect in user
By in range, using the initial neural network model after training as the described first default neural network model.
In the present embodiment, several first test points are chosen from region to be evaluated, obtain first test point respectively
First coordinate information and the first heavy metal concentration value are based on first coordinate information and the first heavy metal concentration value, by the
One default neural network model determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated, to heavy metal-polluted soil
When pollution is evaluated, preset neural network model is introduced, and the evaluation result for being different from existing evaluation method relies primarily on
In the subjective judgement of people, evaluation method of the invention makes evaluation result more objective, accurate.
It is the flow diagram of the pollution evaluation method second embodiment of heavy metal-polluted soil of the present invention, base referring to Fig. 3, Fig. 3
In above-mentioned embodiment shown in Fig. 2, the second embodiment of the pollution evaluation method of heavy metal-polluted soil of the present invention is proposed.
In a second embodiment, after the step S10, the method also includes:
Step S40: choosing several second test points from the region to be evaluated, and obtains the second of each second test point
Coordinate information.
It is understood that when the heavy metal-polluted soil concentration for treating evaluation region is evaluated, the number of test points of introducing
Mesh is more, and the confidence level of evaluation result is higher.
Step S50: being based on second coordinate information, determines second test by the second default neural network model
Second heavy metal concentration value of point.
It is understood that in the second heavy metal for determining second test point by the second default neural network model
Before concentration value, need first to establish the described second default neural network model.
Specifically, the described second default neural network model can be established in the following manner:
Obtain initial neural network model;
Based on first coordinate information and the first heavy metal concentration value, the initial neural network model is instructed
Practice, using initial neural network model after training as the described second default neural network model.
It should be noted that the first coordinate information in the present embodiment can include but is not limited to the warp of the first test point
Distance, the distance apart from nearest highway, the first test point region of degree, latitude, high level, distance the factory group of pollution recently
Air pollution index and water environmental quality index, i.e. the first coordinate information may include it is all it is can obtaining with it is described first survey
The relevant location information of pilot.
It is understood that the information content for including in first coordinate information is bigger, to the initial neural network mould
The training of type is more advantageous, correspondingly, by the described second default neural network model to the second weight of second test point
The prediction of metal concentration value will be more accurate.
In specific training, available initial neural network model, using the first coordinate information as initial network model
Input, using the corresponding first heavy metal depth value of each first sample information as initial neural network model target export,
The initial neural network model is trained based on preset activation primitive, obtains the initial neural network model to sample
The reality output of one's respective area, based on the error between target output and reality output, according to the error, to described initial
Parameter in neural network model is updated, until the error between target output and reality output is in user's tolerance interval
It is interior, using the initial neural network model after training as the described second default neural network model.
Correspondingly, the step S30, specifically includes:
Step S301: based on first coordinate information, the first heavy metal concentration value, the second coordinate information and second huge sum of money
Belong to concentration value, the pollution etc. of the heavy metal pollution of soil in the region to be evaluated is determined by the first default neural network model
Grade.
In the present embodiment, using the forecast function of neural network model, obtained by the second default neural network model more
Second heavy metal concentration value of a second test point is based on the first coordinate information, the first heavy metal concentration value, the second coordinate information
With the second heavy metal concentration value, the heavy metal pollution of soil in the region to be evaluated is determined by the first default neural network model
The class of pollution ensure that the accuracy of sample data while increasing sample size, to further improve evaluation
As a result accuracy.
In addition, the embodiment of the present invention also proposes a kind of storage medium, heavy metal-polluted soil is stored on the storage medium
Pollution evaluation program realizes following operation when the pollution evaluation program of the heavy metal-polluted soil is executed by processor:
Several first test points are chosen from region to be evaluated;
The first coordinate information and the first heavy metal concentration value of first test point are obtained respectively;
Based on first coordinate information and the first heavy metal concentration value, institute is determined by the first default neural network model
State the class of pollution of the heavy metal pollution of soil in region to be evaluated.
Further, following operation is also realized when the pollution evaluation program of the heavy metal-polluted soil is executed by processor:
Several second test points are chosen from the region to be evaluated, and obtain the second coordinate letter of each second test point
Breath;
Based on second coordinate information, the second of second test point is determined by the second default neural network model
Heavy metal concentration value;
Based on first coordinate information, the first heavy metal concentration value, the second coordinate information and the second heavy metal concentration value,
The class of pollution of the heavy metal pollution of soil in the region to be evaluated is determined by the first default neural network model.
Further, following operation is also realized when the pollution evaluation program of the heavy metal-polluted soil is executed by processor:
Obtain several sample areas information and the corresponding class of pollution of each sample areas information, the sample areas packet
Include the coordinate information and heavy metal concentration value of several test points in each sample areas;
The described first default mind is established according to the sample areas information and the corresponding class of pollution of each sample areas information
Through network model.
Further, following operation is also realized when the pollution evaluation program of the heavy metal-polluted soil is executed by processor:
Obtain initial neural network model;
By the sample areas information and the corresponding class of pollution of each sample areas information, to the initial neural network
Model is trained, using the initial neural network model after training as the first default neural network model.
Further, following operation is also realized when the pollution evaluation program of the heavy metal-polluted soil is executed by processor:
Obtain initial neural network model;
Based on first coordinate information and the first heavy metal concentration value, the initial neural network model is instructed
Practice, using initial neural network model after training as the described second default neural network model.
Further, following operation is also realized when the pollution evaluation program of the heavy metal-polluted soil is executed by processor:
The first heavy metal concentration value is normalized respectively, is obtained corresponding with each first heavy metal concentration value
Target heavy metal concentration value;
Based on first coordinate information and target heavy metal concentration value, institute is determined by the first default neural network model
State the class of pollution of the heavy metal pollution of soil in region to be evaluated.
In the present embodiment, several first test points are chosen from region to be evaluated, obtain first test point respectively
The first coordinate information and the first heavy metal concentration value, be based on first coordinate information and the first heavy metal concentration value, pass through
First default neural network model determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated, to a soil huge sum of money
Belong to pollution when being evaluated, introduce preset neural network model, and be different from the evaluation result of existing evaluation method mainly according to
Rely the subjective judgement in people, evaluation method of the invention makes evaluation result more objective, accurate.
It is the functional block diagram of the pollution evaluation device first embodiment of heavy metal-polluted soil of the present invention, base referring to Fig. 4, Fig. 4
In the pollution evaluation method of the heavy metal-polluted soil, propose that the first of the pollution evaluation device of heavy metal-polluted soil of the present invention is implemented
Example.
In the present embodiment, the pollution evaluation device of the heavy metal-polluted soil includes:
Module 10 is chosen, for choosing several first test points from region to be evaluated.
It should be noted that " second " in " first " and " the second test point " in " the first test point " in this programme
It is only intended to not constitute any restrictions to test point to the progress point of different types of test point, likewise, " first sits
" second " of " first " and " the second coordinate information " of mark information " is also only intended to carry out area to different types of coordinate information
Point, do not constitute any restrictions to coordinate information.
It is understood that the test point chosen is more, evaluation result is more accurate.But the test point of selection is too many, after
Continuous test process just needs to spend more costs.Therefore, when choosing test point, choosing can be determined according to specific circumstances
The number of the test point taken, the present embodiment are without restriction to this.
In addition, either choose how many a test points, the test point of selection all should be evenly distributed in it is described to be evaluated
In region, to keep the test point chosen more representative to the region to be evaluated, subsequent evaluation result also will more
Accurately.
Module 20 is obtained, for obtaining the first coordinate information and the first heavy metal concentration of first test point respectively
Value.
It should be noted that the first coordinate information in the present embodiment is longitude, latitude and the high level etc. of the first test point
The information of specific location of first test point in the region to be evaluated can be reacted.
In the concrete realization, first coordinate information can be after choosing the first test point, to the first test point phase
The coordinate information answered measures or searches corresponding map and obtains, and the first heavy metal concentration value can be described first
Position where test point is sampled, and according to relevant testing standard, carries out relevant test acquisition implementing room, certainly,
It can also be obtained by consulting the Research Literature having disclosed, however, it will be understood that obtained by consulting literatures first
The authenticity of heavy metal concentration value can not be guaranteed.
Further, in order to enable data preferably to adapt to transmission function, the error rate in calculating process is reduced, meter is accelerated
Speed and the degree of convergence are calculated, it, can also be to first weight after obtaining first coordinate information and the first heavy metal concentration value
Metal concentration value is converted, that is, is normalized, and target heavy metal corresponding with each first heavy metal concentration value is obtained
Concentration value is correspondingly based on first coordinate information and the first heavy metal concentration value subsequent, passes through the first default nerve
Network model determines the step of class of pollution of the heavy metal pollution of soil in the region to be evaluated specifically: based on described
First coordinate information and the more category concentration values of target weight, the soil in the region to be evaluated is determined by the first default neural network model
The class of pollution of earth heavy metal pollution.
Further, in this embodiment the first heavy metal concentration value is normalized by following formula,
Target heavy metal concentration value corresponding with each first heavy metal concentration value is obtained,
Wherein, XiFor i-th of first heavy metal concentration values, YiFor with XiCorresponding target heavy metal concentration value, XmaxFor number
It is worth maximum first heavy metal concentration value, XminFor the smallest first heavy metal concentration value of numerical value.
Determining module 30 passes through the first default mind for being based on first coordinate information and the first heavy metal concentration value
The class of pollution of the heavy metal pollution of soil in the region to be evaluated is determined through network model.
It is understood that in the heavy metal-polluted soil for determining the region to be evaluated by the first default neural network model
Before the class of pollution of pollution, need first to establish the described first default neural network model.
In specific implementation, the described first default neural network model can be established in the following manner:
Obtain several sample areas information and the corresponding class of pollution of each sample areas information, the sample areas packet
Include the coordinate information and heavy metal concentration value of several test points in each sample areas;
The described first default mind is established according to the sample areas information and the corresponding class of pollution of each sample areas information
Through network model.
It is possible to further obtain initial neural network model first, pass through the sample areas information and each sample area
The corresponding class of pollution of domain information is trained the initial neural network model, by the initial neural network mould after training
Type is as the first default neural network model.
When specific implementation, available several sample areas and the corresponding class of pollution of each sample areas, and obtain initial
Neural network model, using sample areas as the input of initial network model, using the class of pollution of each sample areas as initial
The target of neural network model exports, and is trained to the initial neural network model, obtains the initial neural network mould
Type exports the error between reality output based on the target, according to the error, to institute to the reality output of sample areas
The parameter stated in initial neural network model is updated, until the error between target output and reality output can connect in user
By in range, using the initial neural network model after training as the described first default neural network model.
In the present embodiment, several first test points are chosen from region to be evaluated, obtain first test point respectively
First coordinate information and the first heavy metal concentration value are based on first coordinate information and the first heavy metal concentration value, by the
One default neural network model determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated, to heavy metal-polluted soil
When pollution is evaluated, preset neural network model is introduced, and the evaluation result for being different from existing evaluation method relies primarily on
In the subjective judgement of people, evaluation method of the invention makes evaluation result more objective, accurate.
It will be appreciated that each module in the pollution evaluation device of the heavy metal-polluted soil is also used to realize in the above method
Each step, details are not described herein.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the device that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or device.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
The use of word first, second, and third does not indicate any sequence, these words can be construed to title.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal intelligent TV (can be mobile phone, calculate
Machine, server, air conditioner or network intelligence TV etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of evaluation method of heavy metal pollution of soil, which is characterized in that the described method includes:
Several first test points are chosen from region to be evaluated;
The first coordinate information and the first heavy metal concentration value of first test point are obtained respectively;
Based on first coordinate information and the first heavy metal concentration value, by the first default neural network model determine it is described to
The class of pollution of the heavy metal pollution of soil of evaluation region.
2. the method as described in claim 1, which is characterized in that it is described chosen from region to be evaluated several first test points it
Afterwards, the method also includes:
Several second test points are chosen from the region to be evaluated, and obtain the second coordinate information of each second test point;
Based on second coordinate information, second huge sum of money of second test point is determined by the second default neural network model
Belong to concentration value;
Correspondingly, described to be based on first coordinate information and the first heavy metal concentration value, pass through the first default neural network mould
Type determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated, specifically includes:
Based on first coordinate information, the first heavy metal concentration value, the second coordinate information and the second heavy metal concentration value, pass through
First default neural network model determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated.
3. method according to claim 2, which is characterized in that described dense based on first coordinate information and the first heavy metal
Angle value, by the first default neural network model determine the heavy metal pollution of soil in the region to be evaluated the class of pollution it
Before, the method also includes:
Several sample areas information and the corresponding class of pollution of each sample areas information are obtained, the sample areas information includes each
The coordinate information and heavy metal concentration value of several test points in sample areas;
The described first default nerve net is established according to the sample areas information and the corresponding class of pollution of each sample areas information
Network model.
4. method as claimed in claim 3, which is characterized in that described to be believed according to the sample areas information and each sample areas
It ceases the corresponding class of pollution and establishes the described first default neural network model, specifically include:
Obtain initial neural network model;
By the sample areas information and the corresponding class of pollution of each sample areas information, to the initial neural network model
It is trained, using the initial neural network model after training as the first default neural network model.
5. method as claimed in claim 4, which is characterized in that the first coordinate letter for obtaining first test point respectively
After breath and the first heavy metal concentration value, the method also includes:
Obtain initial neural network model;
Based on first coordinate information and the first heavy metal concentration value, the initial neural network model is trained, it will
Initial neural network model after training is as the described second default neural network model.
6. the method as described in claim 1, which is characterized in that the first coordinate letter for obtaining first test point respectively
After breath and the first heavy metal concentration value, the method also includes:
The first heavy metal concentration value is normalized respectively, obtains mesh corresponding with each first heavy metal concentration value
Indicated weight metal concentration value;
Correspondingly, described to be based on first coordinate information and the first heavy metal concentration value, pass through the first default neural network mould
Type determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated, specifically includes:
Based on first coordinate information and target heavy metal concentration value, by the first default neural network model determine it is described to
The class of pollution of the heavy metal pollution of soil of evaluation region.
7. method as claimed in claim 6, which is characterized in that carried out by following formula to the first heavy metal concentration value
Normalized obtains target heavy metal concentration value corresponding with each first heavy metal concentration value,
Wherein, XiFor i-th of first heavy metal concentration values, YiFor with XiCorresponding target heavy metal concentration value, XmaxMost for numerical value
The first big heavy metal concentration value, XminFor the smallest first heavy metal concentration value of numerical value.
8. a kind of valuator device of heavy metal pollution of soil, which is characterized in that the equipment includes: memory, processor and deposits
Store up the assessment process for the heavy metal pollution of soil that can be run on the memory and on the processor, the soil huge sum of money
Belong to the heavy metal-polluted soil realized as described in any one of claims 1 to 7 when the assessment process polluted is executed by the processor
The step of evaluation method of pollution.
9. a kind of storage medium, which is characterized in that be stored with the assessment process of heavy metal pollution of soil, institute on the storage medium
State the soil realized as described in any one of claims 1 to 7 when the assessment process of heavy metal pollution of soil is executed by processor
The step of evaluation method of heavy metal pollution.
10. a kind of evaluating apparatus of heavy metal pollution of soil, which is characterized in that the evaluating apparatus packet of the heavy metal pollution of soil
It includes:
Module is chosen, for choosing several first test points from region to be evaluated;
Module is obtained, for obtaining the first coordinate information and the first heavy metal concentration value of first test point respectively;
Determining module passes through the first default neural network for being based on first coordinate information and the first heavy metal concentration value
Model determines the class of pollution of the heavy metal pollution of soil in the region to be evaluated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910552212.3A CN110264094A (en) | 2019-06-24 | 2019-06-24 | Evaluation method, equipment, storage medium and the device of heavy metal pollution of soil |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910552212.3A CN110264094A (en) | 2019-06-24 | 2019-06-24 | Evaluation method, equipment, storage medium and the device of heavy metal pollution of soil |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110264094A true CN110264094A (en) | 2019-09-20 |
Family
ID=67921092
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910552212.3A Pending CN110264094A (en) | 2019-06-24 | 2019-06-24 | Evaluation method, equipment, storage medium and the device of heavy metal pollution of soil |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110264094A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111505241A (en) * | 2020-04-26 | 2020-08-07 | 深圳市宇驰检测技术股份有限公司 | Method, device, equipment and medium for evaluating pollution level of soil around enterprise |
CN113837474A (en) * | 2021-09-27 | 2021-12-24 | 北京信息科技大学 | Regional soil heavy metal pollution index prediction method and device |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105181936A (en) * | 2015-09-25 | 2015-12-23 | 南京大学 | Method for evaluating soil heavy metal pollution degree |
KR20170007902A (en) * | 2015-07-13 | 2017-01-23 | 광주과학기술원 | Reliability evaluation method for stabilized heavy metal-contaminated soil |
-
2019
- 2019-06-24 CN CN201910552212.3A patent/CN110264094A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20170007902A (en) * | 2015-07-13 | 2017-01-23 | 광주과학기술원 | Reliability evaluation method for stabilized heavy metal-contaminated soil |
CN105181936A (en) * | 2015-09-25 | 2015-12-23 | 南京大学 | Method for evaluating soil heavy metal pollution degree |
Non-Patent Citations (2)
Title |
---|
王鸿等: "基于BP神经网络的耕地土壤重金属污染评价――以宜宾市翠屏区土壤重金属污染评价为例", 《农业与技术》 * |
胡大伟等: "基于ANN的土壤重金属分布和污染评价研究", 《长江流域资源与环境》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111505241A (en) * | 2020-04-26 | 2020-08-07 | 深圳市宇驰检测技术股份有限公司 | Method, device, equipment and medium for evaluating pollution level of soil around enterprise |
CN113837474A (en) * | 2021-09-27 | 2021-12-24 | 北京信息科技大学 | Regional soil heavy metal pollution index prediction method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109389128B (en) | Automatic extraction method and device for electric imaging logging image characteristics | |
CN105139301B (en) | A kind of guidance method based on BP neural network | |
CN108629323A (en) | A kind of integrated providing method of scenic spot tourist chain type trip | |
CN107688906B (en) | Multi-method fused transmission line meteorological element downscaling analysis system and method | |
CN108227041A (en) | Horizontal visibility forecasting procedure based on website measured data and model results | |
CN108876021B (en) | Medium-and-long-term runoff forecasting method and system | |
CN107920362A (en) | A kind of LTE network performance estimating method based on film micro area | |
CN105740991A (en) | Climate change prediction method and system for fitting various climate modes based on modified BP neural network | |
CN106980603B (en) | Soil sulphur element content prediction method based on soil types merger and multiple regression | |
CN107063273A (en) | Real-time map data update system and method | |
CN107239967A (en) | House property information processing method, device, computer equipment and storage medium | |
CN109800807A (en) | The training method and classification method and device of sorter network, electronic equipment | |
CN110264094A (en) | Evaluation method, equipment, storage medium and the device of heavy metal pollution of soil | |
CN112506972B (en) | User resident area positioning method and device, electronic equipment and storage medium | |
CN107798425A (en) | A kind of space-time based on big data obscures degrees of exposure assessment system and method | |
CN105868102B (en) | A kind of mobile terminal application test systems and method based on computer vision | |
CN106385693A (en) | Telecommunication fraud method for virtual number segments | |
CN109871622A (en) | A kind of low-voltage platform area line loss calculation method and system based on deep learning | |
CN108549817A (en) | A kind of software security flaw prediction technique based on text deep learning | |
CN104679942A (en) | Construction land bearing efficiency measuring method based on data mining | |
CN110377846A (en) | Social networks method for digging, device, storage medium and computer equipment | |
Köppelová et al. | Application of exponential smoothing models and arima models in time series analysis from telco area | |
CN109995549B (en) | Method and device for evaluating flow value | |
CN106844626B (en) | Method and system for simulating air quality by using microblog keywords and position information | |
CN104217088B (en) | The optimization method and system of operator's mobile service resource |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190920 |
|
RJ01 | Rejection of invention patent application after publication |