CN107516168A - A kind of Synthetic Assessment of Eco-environment Quality method - Google Patents
A kind of Synthetic Assessment of Eco-environment Quality method Download PDFInfo
- Publication number
- CN107516168A CN107516168A CN201710748309.2A CN201710748309A CN107516168A CN 107516168 A CN107516168 A CN 107516168A CN 201710748309 A CN201710748309 A CN 201710748309A CN 107516168 A CN107516168 A CN 107516168A
- Authority
- CN
- China
- Prior art keywords
- eco
- data
- environmental
- learning algorithm
- environment
- 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
Classifications
-
- 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to ecological environment field, the present invention proposes a kind of Synthetic Assessment of Eco-environment Quality method, including：S1, Index System of Eco-environmental Quality is built based on PSR model theories；S2, extract the Indices of Ecological based on multi-source data basis；S3, overall merit is carried out to eco-environmental quality based on enhancing learning algorithm.The method of the present invention is new, high-precision Synthetic Assessment of Eco-environment Quality method.
Description
Technical field
The present invention relates to ecological environment field, more particularly to based on a kind of Synthetic Assessment of Eco-environment Quality method.
Background technology
Synthetic Assessment of Eco-environment Quality applies to the technology of ecological environment integrated status on comparative analysis geographical space
Method, due to showing as the Nonlinear Mapping of complexity between the numerous evaluation points and eco-environmental quality of selection, simultaneously as
Ecological environment in itself intrinsic complexity it is uncertain, so far, still without forming a kind of unified method.ANN
Network, which possesses, imitates the performance that human brain knowledge is fitted all nonlinear function mappings.By numerous commonly used high praises of disciplinary study person
BP neural network, because it is fast according to sample training pace of learning, fit non-linear curve ability is strong, and network structure is compared with other god
It is more simple through network, attempt to apply it in Ecology Environment Evaluation by the exploration of numerous scholars, to Ecology Environment Evaluation
Nonlinear Mapping relation between the factor and eco-environmental quality has carried out good description.But because ecological environment state is one
The fuzzy objective attribute of complexity, and BP neural network does not possess identification ambiguity uncertainty ability, so it is not high to judge precision.
Membership function concept in fuzzy theory can carry out the calculating of relative defects to different brackets degree residing for ecological environment state,
The ambiguity for being evaluated object itself preferably is explained, the relative status for describing each attribute of ground surface environment situation have been carried out directly
See statement.Fuzzy reasoning in fuzzy theory and Learning Algorithm are attempted to be mutually combined, structure enhancing learning algorithm,
To carry out clearly objectively description to ecological environment state.
20 end of the century OECD of the world (Organization for Economic Co-operation and
Development, OECD) carry out Ecology Environment Evaluation research project, initiate " pressure (Pressure)-state
(State)-response (Response) " theoretical system, has established the technology and method of Contemporary Ecological Environment management and evaluation study
Where the reason for basis, the model framework discuss problem present in our times environmental situation, and problem occurs and solve to ask
These three sustained development theories of the approach and meanses of topic, its theoretical frame are praised highly by numerous scholars." pressure (Pressure) "
Index is primarily referred to as social production activity to natural terrain or the annoyance level of the ecosystem, that is, reflects bad interference to ecosystem
Load caused by system；" state (State) " index refers to the excellent degree of ecosystem current background state, i.e. ecological environment is intrinsic
Overview；" response (Response) " index refers to human society to realize phase that man and nature environmental harmony sustainable developments are taken
Ecological environmental protection behave is closed, its object is to eliminate, mitigate, prevent bad interference shadow of the human production activity to ecological environment
Ring, be in ecosystem management measure can quantized segment.
Enhancing study develops from animal learning, stochastic approximation and optimal control scheduling theory, is a kind of online without tutor
Learning art, from ambient condition to action mapping study so that Agent takes optimal strategy according to maximum award value；Agent
The status information in environment is perceived, search strategy (which kind of strategy can produce maximally effective study) selects optimal action, from
And cause the change of state and obtain a delay return value, valuation functions are updated, after completing a learning process, entrance is next
The learning training of wheel, repetitive cycling iteration, until the condition for meeting entirely to learn, terminate study.Generally, it is exactly learning machine
Device constantly does autonomous interaction with environment, during interaction with long-range income come instruct instantly this what decision-making done,
Go to adjust the optimality of decision-making with environment interaction by constantly.Enhancing learns the application that succeeded in many fields, than
Such as automatic helicopter, robot control, cell phone network route, marketing decision, Industry Control, efficient web page index etc..
The content of the invention
For the problems of the prior art, the present invention proposes a kind of Synthetic Assessment of Eco-environment Quality method, including：
S1, Index System of Eco-environmental Quality is built based on PSR model theories；
S2, extract the Indices of Ecological based on multi-source data basis；
S3, overall merit is carried out to eco-environmental quality based on enhancing learning algorithm.
The beneficial effects of the method for the present invention includes：
The method of the present invention carries out information extraction conclusion to multi-source data, and the earth's surface that its data content includes degree of precision is covered
Lid data (more fully, information is more abundant for classification), dem data, detailed environmental monitoring station data are (annual, per hour
Air index data), it is natural that and range statistics yearbook data etc., wherein ground mulching data content reflect earth's surface in region
Surface condition and the spatial depiction of Humane Factors distribution, dem data reflect the spatial distribution, ring that surface configuration changes in region
Border monitoring station data carry out record, range statistics yearbook data in detail to the air quality change in region and reflected in region
Population, economic development, the relevant information such as Facilities Construction.
The method of the present invention based on multi-source data, constructs region environment matter using PSR model theories as guidance
Assessment indicator system is measured, appraisement system is related to urban construction, population, arable land, landform, vegetation, water environment, air quality, landscape
Degree of fragmentation, biological habitat, Ecological rehabilitation and social education of science and technology environmental protection development degree etc., and from ecological pressure,
Three ecological state, Eco response different dimensions are carried out on room and time yardstick to the research area natural ecological environment quality
Analysis and evaluation, analysis result system, comprehensively, it is reliable, have and stress.
Expert's priori is carried out quantification treatment by the method for the present invention, and builds priori storehouse, and the knowledge base can be
Continue to expand in follow-up research application perfect so that the environmental quality presented herein based on deep learning network zoology is comprehensive
Existing ripe expertise knowledge can be received by closing evaluation method, and it is directed to a kind of extendible perfect expert's priori
Knowledge application technology method.
The approach application enhancing learning algorithm integrated evaluating method of the present invention carries out studying area's Eco-Environmental Synthetic Analyses, makes
It is objective really by using BP neural network learning method with the complexity and uncertainty of fuzzy theory emulated ecological environment quality
Determine evaluation criterion weight, it is intended that realize comprehensive objective, the true and reliable environment quality model of a synthesis, Fang Nengke
Scientific principle solves different change in time and space yardsticks, complex ecosystem variation tendency, draws accurate evaluation, thus guides policymaker in life
The wise decision-making of science is formulated in state environmental management.
Brief description of the drawings
Fig. 1 is the flow chart of the method for the present invention.
Fig. 2 is the Index System of Eco-environmental Quality frame diagram based on PSR models of present example.
Fig. 3 is that the Synthetic Assessment of Eco-environment Quality index system of present example illustrates table.
Fig. 4 is the Eco-Environmental Synthetic Analyses indication information extractive technique stream based on multi-source data basis of present example
Cheng Tu.
Fig. 5 is the flow chart of the Synthetic Assessment of Eco-environment Quality method based on enhancing study of present example.
Fig. 6 is the enhancing learning algorithm model autonomous learning result of application example of the present invention.
Fig. 7 is that extendible expert's priori of present example quantifies explanation table.
Fig. 8 is the enhancing learning algorithm model accuracy test verification result of application example of the present invention.
Fig. 9 is Beijing's each district Synthetic Assessment of Eco-environment Quality figure in 2007 of application example of the present invention.
Figure 10 is Beijing's each district Synthetic Assessment of Eco-environment Quality figure in 2015 of application example of the present invention.
Figure 11 is that Beijing 2007 of application example of the present invention and each district Synthetic Assessment of Eco-environment Quality in 2015 are united
Meter figure.
Embodiment
Embodiments of the present invention are described with reference to the accompanying drawings, wherein identical part is presented with like reference characters.
In the case where not conflicting, the technical characteristic in following embodiment and embodiment can be mutually combined.
As shown in figure 1, the method for the present invention includes：
S1, ecology is built based on PSR (pressure-state-response, Pressure-State-Response) model theory
Environmental quality assessment index system, the system include eco-environmental pressure, ecological environment state and eco-environmental changing three
Individual evaluation points, each evaluation points are influenceed by multiple evaluation indexes.
PSR theoretical frames describe the relation of interdependence and hair of the mankind and environmental system from sustainable development aspect
Exhibition, Indices of Ecological layering selection is carried out using the theoretical frame, possesses preferable theoretical property and structural.
Eco-Environmental Synthetic Analyses are related to multidisciplinary, multi-field, therefore when choosing evaluation index, should consider multiple
Aspect, choose appropriate index so that the eco-environmental quality in the appropriate image study region of evaluation result energy is horizontal.
Fig. 2 shows an example.In this embodiment, Index System of Eco-environmental Quality be related to three evaluation because
Son：Eco-environmental pressure, ecological environment state and eco-environmental changing.These three dimensions are representative local area ecologicals
The evaluation points of environmental quality.Under each evaluation points, multiple evaluation indexes are further related to, in this embodiment, evaluation refers to
Mark be related to urban construction, population, arable land, landform, vegetation, water environment, air quality, Scenic Bridges, biological habitat,
Ecological rehabilitation and social education of science and technology environmental protection development degree etc., following 12 indexs are determined on this basis：Population is close
Degree, roading density, construction land area accounting, cultivated area accounting；Terrain slope, habitat quality index, water conservation index,
Forest and sod coverage rate, air quality index, undivided plaque area ratio；Protection zone area ratio, education and science's environmental protection expenditure ratio.Tool
Body index implication explanation is shown in Fig. 3.
Referring again to Fig. 1, in S2, the Indices of Ecological based on multi-source data basis is extracted.Fig. 4 show in more detail extraction
Techniqueflow chart.
S2-1, with ground mulching grouped data, dem data (digital elevation model, Digital Elevation
Model), environmental monitoring station data and range statistics yearbook data are data source, carry out data prediction.The number
Data preprocess includes：The many factors involved by Eco-Environmental Synthetic Analyses are sought in analysis, and attempt to selected multi-source data
Pass through the pretreatment works such as space overlapping, Height Analysis, mean analysis and key message screening.
S2-2, space intersection is carried out to earth's surface cover classification data and statistic unit, extracts the gradient of dem data, is calculated
The average of environment measuring station data, screening areas statistical yearbook data, to extract Eco-Environmental Synthetic Analyses index.Specific bag
Include：Construction land area accounting, cultivated area accounting, life are calculated based on ground mulching grouped data and Administrative boundaries data at county level
The indexs such as border performance figure, water conservation index, Forest and sod coverage rate；Calculated based on road data and Administrative boundaries data at county level
The index such as roading density and undivided plaque area accounting；Terrain slope value is extracted based on dem data；Based on statistical yearbook data
Obtain the density of population and education and science's environmental protection expenditure accounting of each phase of area two；Each district is calculated based on environmental monitoring station data
Air quality index year average.
Referring again to Fig. 1, in S3, overall merit is carried out to eco-environmental quality based on enhancing learning algorithm.
Idiographic flow is as shown in Figure 5：
S3-1, priori storehouse is established, the quantization modulation of corresponding achievement data is carried out to it.Collect country in practical application
The relevant criterion of issue, existing scientific research personnel deliver experience general in the technological achievement or production application of announcement
Knowledge, the quantization modulation of corresponding achievement data is carried out to it.Fig. 6 shows an example.
S3-2, random uniform interpolation is carried out to priori storehouse, is expanded, strengthens the study sample of learning algorithm with generation
Notebook data.
S3-3, it is determined that enhancing learning algorithm structure and its parameter.Specifically include：
Enhancing learning algorithm is foundation sample data to determine mode input dimension, node in hidden layer and output node
Number.The input that algorithm is calculated in enhancing study is certain region by normalized each achievement data (habitat quality in such as this experiment
The data such as index, water conservation index are simultaneously normalized using mapminmax functional based methods), it is that the region is given birth to that it, which is exported,
State environmental quality grade evaluation (using being divided into five grades in this experiment, using numeral 1,2 ..., 5 represent ecology respectively
Environmental quality grade is by poor to excellent), it carries out the optimal of eco-environmental quality grade according to each attribute information of input ecological environment
Change expression, the enhancing for carrying out algorithm model by sample data first learns, then by the precision of check algorithm model whether
Reach requirement and decide whether to further enhance learning training, when algorithm model precision reaches requirement, input into
Each attribute information of eco-environmental quality in row region to be evaluated is evaluated.
According to training data, enhancing learning algorithm structure of the invention is：12 input nodes, 13 hidden layer nodes with
And 1 output node.And using Gauss π membership function structure fuzzy set, the center of Gauss π membership function and width are initial
Value is random to be determined, Fuzzy Inference Model use T-S Fuzzy Inference Models, statement variable P0, P1, P2 ..., and P12 is for representing T-S
Fuzzy inference rule coefficient, decline the weights of learning algorithm adjustment enhancing learning algorithm by BP neural network steepest.
Preferably, method of the invention also includes carrying out data normalization to learning sample data.Calculated to enhance strong study
Data are normalized by method operational efficiency, and normalizing is carried out to input data using Matlab software Mapminmax functional based methods
Change.
S3-4, enhancing learning algorithm carry out autonomous learning.
Strengthen learning algorithm by setting algorithm iteration number and minimum error values to start to learn, when iterations or mould
When type minimal error reaches requirement, enhancing learning algorithm terminates.
S3-5, examine enhancing learning algorithm model accuracy.
The enhancing learning algorithm model succeeded in school is tested by test data, by test result, checked
Whether enhancing learning algorithm model reaches requirement, enters if reaching and applies in next step, is needed if not up into one
Step is learnt, so that reaching requirement, if not reaching requirement, returns to S3-4.
In S3-6, when enhancing learning algorithm model measurement precision reaches requirement, then input evaluating data carries out ecological environment
Quality overall evaluation.
In S3-7, each district Synthetic Assessment of Eco-environment Quality result is exported.
Example
Using the district of Beijing 16 as test block, enhancing learning algorithm comprehensive evaluation model is integrated in eco-environmental quality
Application in evaluation, which has been made to explore, to be attempted, and experimental result is as follows：
1st, using Matlab R2016a softwares, enhancing learning algorithm model is realized.Enhancing learning algorithm passes through to sample number
Reach convergence according to repeatedly study is carried out, i.e. algorithm output error is less than the minimum error values initially set.All in all, structure
It is higher to strengthen learning algorithm model running efficiency, the phenomenon that can not be fitted does not occur, illustrates that its service behaviour is good.To model
The change of learning outcome error precision is analyzed (see Fig. 6), it is found that the max calculation error of each step training of network is less than
0.005, computational accuracy is higher, reaches requirement.
2nd, enhancing learning algorithm model measurement assay is shown in Fig. 7, and the enhancing learning algorithm succeeded in school examines sample to 10000
This is carried out back sentencing inspection, and experimental result is understood, does not occur misjudgement phenomenon, it can thus be appreciated that network training works well, enhancing study
Self-teaching, fuzzy reasoning and the robustness of algorithm are verified.
3rd, Fig. 8, Fig. 9 are shown in the district of Beijing 16 Synthetic Assessment of Eco-environment Quality result of 2007 and 2015.
From Figure 10-11, between 2007 to 2015, Chaoyang District eco-environmental quality reduces a grade, and Tongzhou District ecology ring
Border quality rises a grade, and significant change does not occur for remaining each district eco-environmental quality；From each district all in all, Huairou
Area, Mentougou District, Miyun County, Yanqing County eco-environmental quality are higher ranked, and Dongcheng District, Xicheng District and Daxing District ecological environment
Credit rating is poor.
Embodiment described above, it is the present invention more preferably embodiment, those skilled in the art is at this
The usual variations and alternatives carried out in the range of inventive technique scheme should all include within the scope of the present invention.
Claims (10)
- A kind of 1. Synthetic Assessment of Eco-environment Quality method, it is characterised in that including：S1, Index System of Eco-environmental Quality is built based on PSR model theories；S2, extract the Indices of Ecological based on multi-source data basis；S3, overall merit is carried out to eco-environmental quality based on enhancing learning algorithm.
- 2. Synthetic Assessment of Eco-environment Quality method according to claim 1, it is characterised in thatIn S1, the system includes three eco-environmental pressure, ecological environment state and eco-environmental changing evaluation points, Each evaluation points are influenceed by multiple evaluation indexes.
- 3. Synthetic Assessment of Eco-environment Quality method according to claim 2, it is characterised in thatThe multiple evaluation index includes：The density of population, roading density, construction land area accounting, cultivated area accounting；Landform The gradient, habitat quality index, water conservation index, Forest and sod coverage rate, air quality index, undivided plaque area ratio；Protect Protect area's area ratio and education and science's environmental protection expenditure ratio.
- 4. Synthetic Assessment of Eco-environment Quality method according to claim 1, it is characterised in that step S2 includes：S2-1, using ground mulching grouped data, dem data, environmental monitoring station data and range statistics yearbook data as number According to source, data prediction is carried out；S2-2, space intersection is carried out to earth's surface cover classification data, extracts the terrain slope of dem data, computing environment measuring station The year average of point data, screening areas statistical yearbook data, to extract Eco-Environmental Synthetic Analyses index.
- 5. Synthetic Assessment of Eco-environment Quality method according to claim 1, it is characterised in that step S3 includes：S3-1, priori storehouse is established, the quantization modulation of corresponding achievement data is carried out to it；S3-2, random uniform interpolation is carried out to priori storehouse, is expanded, strengthens the learning sample number of learning method with generation According to；S3-3, it is determined that enhancing learning algorithm structure and its parameter；S3-4, enhancing learning algorithm carry out autonomous learning；S3-5, enhancing learning algorithm model accuracy is examined, if not up to required, returns to S3-4；S3-6, reach requirement when strengthening learning model measuring accuracy, then input data to be evaluated and carry out eco-environmental quality synthesis Evaluation.
- 6. Synthetic Assessment of Eco-environment Quality method according to claim 5, it is characterised in that in step S3-3, institute State enhancing learning algorithm input be certain region pass through each achievement data, its export be to the Regional Eco-environmental Quality etc. Level evaluation.
- 7. Synthetic Assessment of Eco-environment Quality method according to claim 6, it is characterised in thatIn step S3-3, the enhancing learning algorithm structure is：12 input nodes, 13 hidden layer nodes and 1 it is defeated Egress.
- 8. Synthetic Assessment of Eco-environment Quality method according to claim 7, it is characterised in thatThe enhancing learning algorithm is using Gauss π membership function structure fuzzy set, the center of Gauss π membership function and width Initial value determines at random, and Fuzzy Inference Model uses T-S Fuzzy Inference Models, statement variable P0, P1, P2 ..., and P12 is used for table Show T-S fuzzy inference rule coefficients.
- 9. Synthetic Assessment of Eco-environment Quality method according to claim 8, it is characterised in that also include：Decline the weights of learning algorithm adjustment enhancing learning algorithm by BP neural network steepest.
- 10. Synthetic Assessment of Eco-environment Quality method according to claim 9, it is characterised in thatIn step S3-3, data normalization is carried out to learning sample data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710748309.2A CN107516168A (en) | 2017-08-28 | 2017-08-28 | A kind of Synthetic Assessment of Eco-environment Quality method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710748309.2A CN107516168A (en) | 2017-08-28 | 2017-08-28 | A kind of Synthetic Assessment of Eco-environment Quality method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107516168A true CN107516168A (en) | 2017-12-26 |
Family
ID=60724309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710748309.2A Pending CN107516168A (en) | 2017-08-28 | 2017-08-28 | A kind of Synthetic Assessment of Eco-environment Quality method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107516168A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108305021A (en) * | 2018-03-29 | 2018-07-20 | 华南农业大学 | A kind of requisition-compensation balance Performance Evaluation Methods under the model based on PSR |
| CN109740292A (en) * | 2019-01-30 | 2019-05-10 | 中国测绘科学研究院 | A kind of urban population spatial distribution evaluation method and device based on multiple agent |
| CN110298010A (en) * | 2019-06-27 | 2019-10-01 | 李达维 | The ecological environment of ecological engineering of landscape measures system |
| CN110321932A (en) * | 2019-06-10 | 2019-10-11 | 浙江大学 | A kind of whole city city air quality index estimation method based on depth multisource data fusion |
| CN110555586A (en) * | 2019-07-22 | 2019-12-10 | 北京英视睿达科技有限公司 | ecological monitoring method and device based on hotspot grid |
| CN110906986A (en) * | 2019-12-11 | 2020-03-24 | 内蒙古工业大学 | Grassland ecological monitoring system and method based on Internet of things |
| CN113155191A (en) * | 2021-04-16 | 2021-07-23 | 浙江农林大学 | Urban area ecological environment monitoring method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104835103A (en) * | 2015-05-11 | 2015-08-12 | 大连理工大学 | Mobile network health evaluation method based on neural network and fuzzy comprehensive evaluation |
| CN106934233A (en) * | 2017-03-09 | 2017-07-07 | 江西理工大学 | A kind of rare-earth mining area environmental pressure quantitative estimation method and system based on PSR models |
-
2017
- 2017-08-28 CN CN201710748309.2A patent/CN107516168A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104835103A (en) * | 2015-05-11 | 2015-08-12 | 大连理工大学 | Mobile network health evaluation method based on neural network and fuzzy comprehensive evaluation |
| CN106934233A (en) * | 2017-03-09 | 2017-07-07 | 江西理工大学 | A kind of rare-earth mining area environmental pressure quantitative estimation method and system based on PSR models |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108305021A (en) * | 2018-03-29 | 2018-07-20 | 华南农业大学 | A kind of requisition-compensation balance Performance Evaluation Methods under the model based on PSR |
| CN109740292A (en) * | 2019-01-30 | 2019-05-10 | 中国测绘科学研究院 | A kind of urban population spatial distribution evaluation method and device based on multiple agent |
| CN110321932A (en) * | 2019-06-10 | 2019-10-11 | 浙江大学 | A kind of whole city city air quality index estimation method based on depth multisource data fusion |
| CN110298010A (en) * | 2019-06-27 | 2019-10-01 | 李达维 | The ecological environment of ecological engineering of landscape measures system |
| CN110555586A (en) * | 2019-07-22 | 2019-12-10 | 北京英视睿达科技有限公司 | ecological monitoring method and device based on hotspot grid |
| CN110906986A (en) * | 2019-12-11 | 2020-03-24 | 内蒙古工业大学 | Grassland ecological monitoring system and method based on Internet of things |
| CN113155191A (en) * | 2021-04-16 | 2021-07-23 | 浙江农林大学 | Urban area ecological environment monitoring method |
| CN113155191B (en) * | 2021-04-16 | 2022-03-11 | 浙江农林大学 | Urban area ecological environment monitoring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107516168A (en) | A kind of Synthetic Assessment of Eco-environment Quality method | |
| Ayodele et al. | A multi-criteria GIS based model for wind farm site selection using interval type-2 fuzzy analytic hierarchy process: The case study of Nigeria | |
| Noorollahi et al. | Using artificial neural networks for temporal and spatial wind speed forecasting in Iran | |
| Haktanır et al. | A novel picture fuzzy CRITIC & REGIME methodology: Wearable health technology application | |
| CN109858647A (en) | A kind of Regional Flooding Hazard Risk Assessment and predictor method coupling GIS and GBDT algorithm | |
| CN109659933A (en) | A kind of prediction technique of power quality containing distributed power distribution network based on deep learning model | |
| CN108491969A (en) | Spatial Load Forecasting model building method based on big data | |
| CN105243435A (en) | Deep learning cellular automaton model-based soil moisture content prediction method | |
| CN107992968A (en) | Electric energy meter measurement error Forecasting Methodology based on integrated techniques of teime series analysis | |
| Ismail et al. | A hybrid model of self organizing maps and least square support vector machine for river flow forecasting | |
| Kişi | Evolutionary fuzzy models for river suspended sediment concentration estimation | |
| CN109376907A (en) | Adapt to the high-voltage distribution network transformer substation load forecasting method of transmission and distribution network integration planning | |
| CN109360018A (en) | A kind of fuzzy zone land price estimation method based on artificial neural network | |
| CN114492922A (en) | Medium-and-long-term power generation capacity prediction method | |
| Fataei et al. | Industrial state site selection using MCDM method and GIS in Germi, Ardabil, Iran | |
| CN108416502A (en) | A kind of Synthetic Assessment of Eco-environment Quality method | |
| CN110517494A (en) | Forecasting traffic flow model, prediction technique, system, device based on integrated study | |
| Roisenberg et al. | A hybrid fuzzy-probabilistic system for risk analysis in petroleum exploration prospects | |
| Feng et al. | Analysis on fuzzy risk of landfall typhoon in Zhejiang province of China | |
| CN110827134A (en) | Power grid enterprise financial health diagnosis method | |
| Zhu et al. | Analysis of human resource allocation model for tourism industry based on improved BP neural network | |
| Feng et al. | Application of possibility-probability distribution in risk analysis of landfall hurricane—A case study along the east coast of the United States | |
| Weifeng et al. | On rural typologies with neural network method: Case study on Xining region | |
| Khan et al. | Irrigation water requirement prediction through various data mining techniques applied on a carefully pre-processed dataset | |
| Moazami et al. | Fuzzy inference and multi-criteria decision making applications in pavement rehabilitation prioritization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171226 |