CN109002627A - Urban planning scheme heat island simulating and predicting method based on grey neural network CA model - Google Patents
Urban planning scheme heat island simulating and predicting method based on grey neural network CA model Download PDFInfo
- Publication number
- CN109002627A CN109002627A CN201810850147.8A CN201810850147A CN109002627A CN 109002627 A CN109002627 A CN 109002627A CN 201810850147 A CN201810850147 A CN 201810850147A CN 109002627 A CN109002627 A CN 109002627A
- Authority
- CN
- China
- Prior art keywords
- heat island
- model
- urban
- island
- simulation
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression 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
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Operations Research (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Neurology (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The present invention provides a kind of urban planning scheme heat island simulating and predicting method based on grey neural network CA model, and step includes: 1) to be collected to the urban green space of influence heat island simulation and forecast, hardened ground, architectural composition, plot ratio, site coverage, water body data；2) each factor cuclear density in each cut zone is calculated；3) regression equation is established；Model training and inspection are carried out using grey neural network CA model according to typical weather test result and regression parameter, the result exported after qualified is the tropical island effect of simulation and forecast programme.The present invention provides the control appraisal procedures of cities and towns outdoor thermal environment.According to the spacial influence factor of urban heat island, under given meteorological condition, simulate the urban heat island strength spatial distribution of any time, the distribution etc. of the hardened grounds such as architectural composition, green space layout, the road/square in town planning can be adjusted according to analog result, provide strong analysis tool for ecology town planning.
Description
Technical field
The present invention relates to a kind of urban planning scheme heat island simulating and predicting method based on grey neural network CA model.
Background technique
Urban heat island (urban heat island, UHI) is the city phenomenon higher than rural area temperature around.1833,
British Howard (Howard) proposes urban heat land effect in Scientific Magazine " London weather " for the first time.180 years subsequent west
Square various countries have just carried out the widely research about urban heat island, so the document in terms of this is also to emerge one after another.Urban Thermal
Island effect is to change at any time with the variation of geospatial location.Tropical island effect is studied, being divided by object is surface temperature
With two kinds of Air Close To The Earth Surface temperature.From search time, there is the Changeement of long-term, also has a year Changeement, there are also days
Changeement.Research range have up to a hundred square kilometres from macroscopic view to tens microcosmic square meters.Different spaces, different time, no
Same level, tropical island effect have the characteristics that different, therefore start must these three clear problems for research.Heat island research is main to be used
Ground observation, remote-sensing inversion, meteorologic model method.
Liu Jing, Zhu Yuemei etc. study the energy between building interior weather and city local climate using numerical computation method
Amount and substance transitive relation, but model needs given in macroscopic aspect it is perfect.Tribute fine jade utilizes the CA model of neural network, simplifies mould
The complicated urban heat island spatial variations process of prediction is fitted, and simulates the land used for urban and rural construction projects temperature landscape of Urumqi City.
Feng little Gang, the UHI-CA-Markov model carried using Clark University's IDRISI software, simulation and forecast Xi'an urban heat island
Effect proposes that the heat island area of Xi'an, Strong Urban Heat Island area are slightly reduced, room temperature area, Lutao area be slightly increased, strong Lutao area not
Become.Luo Qing is based on digital image analysis town thermal island special efficacy prediction technique, using by establishing DEM, using region as node,
Flow openings have applied for technical solution as branch.Peng Zhen is based on multivariate linear model, carries out the measurement of Heat Island.
Urban planning is less to the analog study of urban heat land effect, to urban heat land effect during urban planning
Polarization reduction research is also relatively fewer, is some qualitative discussions mostly, lacks specific operation, specific to greenery patches, air duct etc.
Space layout lacks quantitative scientific basis, more lacks detailed land-use style layout parameter and mining inetesity changes thermal environment
The research of variable size.Consider that single-factor influence factor is more, as Li Yanming closes Beijing's greening amount and tropical island effect intensity
Quantitative analysis has been done by system, and gas above bottom and its greenery patches is adjusted to the canopy on Hefei greenery patches meadow and forest land trees in tight equality
Layer temperature is analyzed.Zhang little Li, the analog studies such as Li Lei are primarily directed to current city heat island and urban construction macroscopic view area
Domain property.
Either numerical model, city canopy, cellular automata, existing research are all based on large scale or smaller ruler
Degree, WRF simulate scale and are lower than 3km2Resolution ratio is difficult to accurately simulate, and existing cellular Automation Model is also in 120m scale
Earth's surface heat island, be mostly that can not realize docking for Real Atmosphere temperature with true city based on the indexes such as NDBI, DNVI,
It is difficult to be connected with the index of physical planning design object, let alone practical application.Moreover, using neural network and ash at present
Color system research heat island mostly uses and is based on time GM (1,1) model, and simulation of the model to atural object because of the present circumstance
Prediction is also not suitable for very much, because GM (1,1) model is the prediction carried out based on time series data to future, and heat island is pre-
Survey is the prediction of many factors superposition combined influence based on synchronization.
Summary of the invention
The object of the present invention is to provide one kind to be based on grey neural network CA (cellular automata cellular automata)
The urban planning scheme heat island simulating and predicting method of model can carry out Simulation evaluation based on the controlling indicator of planning.
The technical solution of the present invention is as follows: a kind of urban planning scheme heat island simulation based on grey neural network CA model is pre-
Survey method, step include:
1) planning region data information to be assessed is collected: to influencing the urban green space of heat island simulation and forecast, hardened ground, build
Layout, plot ratio, site coverage, water body data are built to be collected；
2) density drawing is based on using mobile search method, be calculated plot ratio in each cut zone, site coverage,
Water body, afforestation coverage rate, the cuclear density of hardened ground rate；According to plot ratio, hardened ground rate, site coverage, Water Surface Ratio, greenery patches
Planning region is divided at least nine region by rate, and the website of measurement temperature and humidity is equipped in each region1；Website distribution should be opposite
Uniformly；
3) based on research area's test data establish regression model, establish plot ratio, site coverage, water body, afforestation coverage rate,
The regression equation of hardened ground；It is carried out according to typical weather test result and regression parameter using grey neural network CA model
Model training and inspection, the result exported after qualified are the tropical island effect of simulation and forecast programme.
Preferably, the calculating of cuclear density is using spatially certain point as core in step 2), and range content is long-pending at a certain distance
Rate, site coverage, water body, afforestation coverage rate, the hardened ground rate gross area and land area ratio indicate, calculation formula
Are as follows:
Wherein: K () is cuclear density equation；wiFor the weighted value of space i, indicated using two-value；A is the face of filter window
Product, h are the threshold range of space behavior, and n is the pixel number in threshold range, and d is the dimension of data.
Preferably, the dimension of the data is two-dimentional, and d=2, calculation formula (1) simplifies are as follows:
Preferably, the step 3) specifically:
S1, five space variables of simulation for extracting heat island construct the independent variable shadow of CA model using Heat Island as dependent variable
The factor of sound, establishes recurrence of the single factor test of hardened ground, plot ratio, site coverage, afforestation coverage rate, Water Surface Ratio to tropical island effect
Model；
The wherein calculation method of Heat Island are as follows: by a certain moment, the city temperature of a certain spatial position and suburb rural
The difference of mean temperature, as the Heat Island of the at a time position, calculation formula are as follows:
In formula: the Heat Island at a certain moment Δ T on the ij of spatial positionijIt indicates；Surface temperature on the ij of spatial position
Then use TijIt indicates；It is the mean temperature of suburb rural point；
S2, the cellular for determining CA model, the Neighbourhood parameter plan of establishment；It determines that quadrangle is cellular shape, is selected according to data
Determine resolution ratio, maximum resolution is 15 meters；Cellular neighborhood definition is using extension mole type:
NMoore={ vi=(vix,viy)||vix-v0x|+|viy-voy|≤r,(vix,viy)∈Z2, according to regression model, in advance
Survey hardened ground, plot ratio, site coverage, afforestation coverage rate, Water Surface Ratio single factor test to influence value t1, t2 of heat island, t3,
t4,t5；
S3, networking rule is trained, firstly, establishing GM (0, N) according to single factor test predicted value t1, t2, t3, t4, t5
Model2；Then, the error for calculating gray prediction simulates error using neural network；It is finally that GM (0, N) model is pre-
Measured value is added with neuron network simulation predicted value；
S4, the CA model that five space variables in region to be predicted are substituted into simulated training, carry out heat island simulation, can obtain
To analog result, CA model isWherein, cellular ij is expressed as in the state of time t+1 and tWithTransformation rule function indicates with f,It is the spatial development situation of the neighborhood on the ij of position, Con is total constraint item
Part, N represent cellular number.
Preferably, each factor is to the influencing mechanism parameter of heat island in the step 3), and take following parameter: hardened ground is empty
Between susceptibility metric radius be 15m, greening covering spatial sensitivity scale radius be 15m, building floor area ratio spatial sensitivity ruler
Degree radius is 230m, and site coverage spatial sensitivity scale radius is 130m, and Water Surface Ratio spatial sensitivity scale radius is 200m.
The present invention does not consider wind speed, i.e., each data are measured in the case where 3 meter per second of mean wind speed, determines evaluation Urban Thermal
Island environment and hot comfort meet National Technical regulation.The present invention is according to national standard --- and " urban climate evaluation regulation " is wanted
It asks, is lower than 3 meter per seconds in mean wind speed, determines that evaluation urban heat island environment and hot comfort do not consider wind speed, meet National Technical
Regulation.
Beneficial effects of the present invention are as follows:
The present invention provides the control appraisal procedures of cities and towns outdoor thermal environment.According to the spacial influence factor of urban heat island,
Under given meteorological condition, the urban heat island strength spatial distribution of any time is simulated, cities and towns can be adjusted according to analog result
Distributions of hardened grounds such as architectural composition, green space layout, road/square in planning etc. provide effectively for ecology town planning
Analysis tool.After the present invention carries out gray prediction, simulation again simulates error with neural network, and analog result is mended to ash
Color system prediction uses GM (0, N) model during prediction, GM (0, N) is suitble to the prediction of multivariable, little with time relationship,
Variable of the invention is numerous, but unrelated with time dimension, therefore can be more acurrate using the result of GM (0, N) modeling.This hair
Bright CA uses variable neighborhood size, and calculating is more flexible, more acurrate, meets each variable to the sensitive scales of the difference of heat island, if
The factor that sensibility is small under the scale can be made to be added using unified scale to calculate, to increase error.
Detailed description of the invention
Fig. 1 is the planning simulation evaluation method principle framework of town thermal island of the present invention.
Fig. 2 is that mobile search method of the present invention calculates signal.
Fig. 3 is cuclear density calculation method of the present invention signal.
Fig. 4 is CA core algorithm principle process of the present invention.
Fig. 5 is the accuracy comparison (14:00) that heat island and actual observation are simulated in the embodiment of the present invention 2.
Fig. 6 is the accuracy comparison (8:00-20:00) that heat island and actual observation are simulated in the embodiment of the present invention 2.
Fig. 7 is that the planning area scheme promotion that the present invention is carried out according to analogue observation is suggested.
Specific embodiment
For a better understanding of the present invention, below with specific example come the technical solution that the present invention will be described in detail, but this
Invention is not limited thereto.
Embodiment 1
One, planning region data information to be assessed is collected, selects Climate measurement time and test according to standard chosen below
Place: first, rainfall influence is avoided in heat island observation；Second, mean wind speed is close to 3m/s；Third considers site coverage, volume
Rate, arrives the factors such as water body distance, roading density, ratio of green space at hardened ground rate, has both considered Macroscopic Factors it is further contemplated that microcosmic website is all
The factor enclosed selects 18 observation points.(table 1) is tested according to above-mentioned standard selection 18, Tianjin point.
1 observation point title of table, number, coordinate, elevation
Two, regression equation is established
Using test data and plot ratio, site coverage, ratio of green space, Water Surface Ratio, hardened ground rate (also known as core plot ratio,
Core site coverage, core afforestation coverage rate, core Water Surface Ratio, core stiff dough rate), being determined property analytic function returns, and specifies each influence
The scale and equation of factor.It is as follows to analyze result:
Microcosmic point:
Hardened ground rate and the linear fit effect of Heat Island are best.It is y=2.19x+ that fit equation, which is respectively as follows: equation,
2.11 R2For 0.28, F 6.21.
The linear fit effect of core ratio of green space and Heat Island is best.Fit equation is respectively as follows: y=-1.79x+3.57, R2
For 0.32, F 6.81.
Macroscopic aspect:
Heat Island changes in a linear relationship, equation y=0.97x+1.77, R with core plot ratio2It is for 0.46, F
13.56。
Site coverage and the linear fit effect of Heat Island are best.Fit equation is respectively as follows: y=-4.62x+4.44, R2
For 0.26, F 5.61.
The linear fit effect of core Water Surface Ratio and Heat Island is best.It is y=-23.99x+ that fit equation, which is respectively as follows: equation,
4.06 R2For 0.82, F 28.23.
The linear fit effect of core ratio of green space and Heat Island is best.Fit equation is respectively as follows: y=-1.8x+3.5, R2For
0.41, F 7.53.
Three, model training and verifying
5 space variables are substituted into grey CA model, carry out model training.By the actual measurement number of analog result and 18 websites
According to carrying out calculating analysis, the Heat Island simulation and forecast precision of evaluation model.Simulation and forecast is as the result is shown: simulation root-mean-square error
It is 0.55, R2It is 0.6, confidence level 0.01, this shows that the simulation and forecast precision of model is reliable.
According to the heat island strength simulation that is averaged in the daytime of this model as a result, Spatial Distribution Pattern and heat island decrease can be carried out
The formulation of programme.
Machine is acted on according to the heat island of heat island analog result and core plot ratio, core ratio of green space, core Water Surface Ratio, core stiff dough rate etc.
System mainly chooses important water system and is widened and dug part water body, forms the blue corridor of a plurality of cooling, alleviates inner city heat island effect
It answers.Existing water system is contacted into perforation, while connecting the water body in large of inner city and periphery as " cool down blue core ", shape
At the blue corridor system of center cooling of " three horizontal ones and four vertical ones ".More open city river network spatial framework is formed, in favor of guiding suburb
The low-temperature airflow in area enters downtown area by the blue corridor system that cools down, as shown in Figure 5.
Embodiment 2
Selected 20, Beijing's case area test point, simulation show higher (such as Fig. 6 and 7 of precision of the present invention with actual measurement comparison
It is shown).14:00 Heat Island and simulation assessment result show that error is 0.09 DEG C, mean error 1.4%；8:00-18:00
Average heat island and simulation assessment result show that error is 0.12 DEG C, mean error 3.5%.
Bibliography
1, the Formation & evolution mechanism of yellow shining spring urban heat island and Planning Countermeasures study University Of Tianjin doctoral thesis .2014
2, the such as Liu Sifeng gray system theory and its application Science Press the 7th edition, 2017.
Claims (5)
1. a kind of urban planning scheme heat island simulating and predicting method based on grey neural network CA model, step include:
1) planning region data information to be assessed is collected: to urban green space, the hardened ground, building cloth for influencing heat island simulation and forecast
Office, plot ratio, site coverage, water body data are collected；
2) density drawing is based on using mobile search method, hardened ground in each cut zone, plot ratio, building is calculated
Density, afforestation coverage rate, the cuclear density of Water Surface Ratio；According to hardened ground, plot ratio, site coverage, afforestation coverage rate, the water surface
Planning region is divided at least nine region by rate, and the website of measurement temperature and humidity is equipped in each region；
3) regression model is established based on research area's test data, establishes plot ratio, site coverage, water body, afforestation coverage rate, hardening
The regression equation on ground；Model is carried out using grey neural network CA model according to typical weather test result and regression parameter
Training and inspection, the result exported after qualified are the tropical island effect of simulation and forecast programme.
2. urban planning scheme heat island simulating and predicting method according to claim 1, it is characterised in that: step 2) center is close
The calculating of degree using spatially certain point as core, at a certain distance range content product rate, site coverage, water body, afforestation coverage rate,
The ratio of the hardened ground rate gross area and land area indicates, calculation formula are as follows:
Wherein: K () is cuclear density equation；wiFor the weighted value of space i, indicated using two-value；A is the area of filter window, and h is
The threshold range of space behavior, n are the pixel number in threshold range, and d is the dimension of data.
3. urban planning scheme heat island simulating and predicting method according to claim 2, it is characterised in that: the dimension of the data
Number is two-dimentional, d=2, and calculation formula (1) simplifies are as follows:
4. urban planning scheme heat island simulating and predicting method according to claim 3, it is characterised in that: the step 3) tool
Body are as follows:
S1, extract heat island five space variables of simulation, using Heat Island as dependent variable, building CA model independent variable influence because
Element establishes the single factor test of hardened ground, plot ratio, site coverage, afforestation coverage rate, Water Surface Ratio to the recurrence mould of tropical island effect
Type；
The wherein calculation method of Heat Island are as follows: by a certain moment, the city temperature of a certain spatial position and suburb rural are average
The difference of temperature, as the Heat Island of the at a time position, calculation formula are as follows:
In formula: the Heat Island at a certain moment Δ T on the ij of spatial positionijIt indicates；Surface temperature on the ij of spatial position is then used
TijIt indicates；It is the mean temperature of suburb rural point；
S2, the cellular for determining CA model, the Neighbourhood parameter plan of establishment；Determine that quadrangle is cellular shape, according to selected point of data
Resolution, maximum resolution are 15 meters；Cellular neighborhood definition is using extension mole type: NMoore={ vi=(vix,viy)||vix-v0x|+
|viy-voy|≤r,(vix,viy)∈Z2, according to regression model, predict hardened ground, plot ratio, site coverage, greening covering
Rate, Water Surface Ratio single factor test to influence value t1, t2, t3, t4, t5 of heat island；
S3, networking rule is trained, firstly, establishing GM (0, N) model according to single factor test predicted value t1, t2, t3, t4, t5；
Then, the error for calculating gray prediction simulates error using neural network；Finally by GM (0, N) model predication value and
Neuron network simulation predicted value is added；
S4, the CA model that five space variables in region to be predicted are substituted into simulated training, carry out heat island simulation, mould can be obtained
Intend as a result, CA model isWherein, cellular ij is expressed as in the state of time t+1 and tWithTransformation rule function indicates with f,It is the spatial development situation of the neighborhood on the ij of position, Con is total constraint condition, N generation
List cell born of the same parents' number.
5. urban planning scheme heat island simulating and predicting method according to claim 4, it is characterised in that: in the step 3)
Each factor takes following parameter: micro-scale to the influencing mechanism parameter of heat island: hardened ground spatial sensitivity scale radius is
15m, greening covering spatial sensitivity scale radius is 15m；Daytime in macro-scale, greening covering space 250m radius sensibility
Most strong, building floor area ratio spatial sensitivity scale radius is 230m, and site coverage spatial sensitivity scale radius is 130m, the water surface
Rate spatial sensitivity scale radius is 200m.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810850147.8A CN109002627A (en) | 2018-07-28 | 2018-07-28 | Urban planning scheme heat island simulating and predicting method based on grey neural network CA model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810850147.8A CN109002627A (en) | 2018-07-28 | 2018-07-28 | Urban planning scheme heat island simulating and predicting method based on grey neural network CA model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109002627A true CN109002627A (en) | 2018-12-14 |
Family
ID=64598354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810850147.8A Pending CN109002627A (en) | 2018-07-28 | 2018-07-28 | Urban planning scheme heat island simulating and predicting method based on grey neural network CA model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109002627A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110069885A (en) * | 2019-05-05 | 2019-07-30 | 重庆师范大学 | A kind of " three lives " space optimization method based on external ecology functional localization |
| CN110210112A (en) * | 2019-05-29 | 2019-09-06 | 武汉理工大学 | Couple the urban heat land effect Scene Simulation method of land use planning |
| CN111523777A (en) * | 2020-04-09 | 2020-08-11 | 辽宁百思特达半导体科技有限公司 | Novel smart city system and application method thereof |
| CN112348239A (en) * | 2020-10-27 | 2021-02-09 | 中国建筑科学研究院有限公司 | Method for predicting intensity of artificial green land on heat island of alleviation city |
| CN113254554A (en) * | 2021-04-21 | 2021-08-13 | 哈尔滨工业大学（深圳） | Urban block heat island modeling method and system based on map capture and cluster learning |
| CN116882034A (en) * | 2023-09-06 | 2023-10-13 | 武汉大学 | Urban three-dimensional greening distribution method based on three-dimensional simulation |
| CN117668507A (en) * | 2024-01-31 | 2024-03-08 | 广东海洋大学 | Urban heat island effect evaluation method based on atmospheric analysis data |
| CN117974912A (en) * | 2024-04-02 | 2024-05-03 | 山东省国土测绘院 | Urban planning live-action three-dimensional simulation system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106021751A (en) * | 2016-05-26 | 2016-10-12 | 上海海洋大学 | Land utilization change simulation method for coastal zone based on CA and SAR |
| CN107808212A (en) * | 2017-10-09 | 2018-03-16 | 南京邮电大学 | Solar energy collecting power forecasting method based on grey neural network |
-
2018
- 2018-07-28 CN CN201810850147.8A patent/CN109002627A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106021751A (en) * | 2016-05-26 | 2016-10-12 | 上海海洋大学 | Land utilization change simulation method for coastal zone based on CA and SAR |
| CN107808212A (en) * | 2017-10-09 | 2018-03-16 | 南京邮电大学 | Solar energy collecting power forecasting method based on grey neural network |
Non-Patent Citations (4)
| Title |
|---|
| 毛澄映: "《软件维护中风险分析与故障管理策略研究》", 31 March 2010, 中国科学技术大学出版社 * |
| 陆勉: "《基于灰色神经网络的郁江流域灾害性洪水预测》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈信 等: "《人-机-环境系统工程总论》", 31 December 2000, 北京航空航天大学出版社 * |
| 黄焕春: "《城市热岛的形成演化机制与规划对策研究》", 《中国博士学位论文全文数据库 工程科技Ⅰ辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110069885A (en) * | 2019-05-05 | 2019-07-30 | 重庆师范大学 | A kind of " three lives " space optimization method based on external ecology functional localization |
| CN110210112A (en) * | 2019-05-29 | 2019-09-06 | 武汉理工大学 | Couple the urban heat land effect Scene Simulation method of land use planning |
| CN111523777A (en) * | 2020-04-09 | 2020-08-11 | 辽宁百思特达半导体科技有限公司 | Novel smart city system and application method thereof |
| CN112348239A (en) * | 2020-10-27 | 2021-02-09 | 中国建筑科学研究院有限公司 | Method for predicting intensity of artificial green land on heat island of alleviation city |
| CN113254554A (en) * | 2021-04-21 | 2021-08-13 | 哈尔滨工业大学（深圳） | Urban block heat island modeling method and system based on map capture and cluster learning |
| CN113254554B (en) * | 2021-04-21 | 2023-09-26 | 哈尔滨工业大学（深圳） | Urban block heat island modeling method and system based on map capturing and cluster learning |
| CN116882034A (en) * | 2023-09-06 | 2023-10-13 | 武汉大学 | Urban three-dimensional greening distribution method based on three-dimensional simulation |
| CN116882034B (en) * | 2023-09-06 | 2023-11-17 | 武汉大学 | Urban three-dimensional greening distribution method based on three-dimensional simulation |
| CN117668507A (en) * | 2024-01-31 | 2024-03-08 | 广东海洋大学 | Urban heat island effect evaluation method based on atmospheric analysis data |
| CN117668507B (en) * | 2024-01-31 | 2024-04-05 | 广东海洋大学 | Urban heat island effect evaluation method based on atmospheric analysis data |
| CN117974912A (en) * | 2024-04-02 | 2024-05-03 | 山东省国土测绘院 | Urban planning live-action three-dimensional simulation system |
| CN117974912B (en) * | 2024-04-02 | 2024-06-04 | 山东省国土测绘院 | Urban planning live-action three-dimensional simulation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109002627A (en) | Urban planning scheme heat island simulating and predicting method based on grey neural network CA model | |
| Hammerberg et al. | Implications of employing detailed urban canopy parameters for mesoscale climate modelling: a comparison between WUDAPT and GIS databases over Vienna, Austria | |
| CN105243435B (en) | A kind of soil moisture content prediction technique based on deep learning cellular Automation Model | |
| CN108701274A (en) | A kind of small scale air quality index prediction technique in city and system | |
| Hu et al. | Analysis of the spatial and temporal variations of land surface temperature based on local climate zones: A case study in Nanjing, China | |
| He et al. | Future air temperature projection in high-density tropical cities based on global climate change and urbanization–a study in Singapore | |
| Potgieter et al. | Combining high-resolution land use data with crowdsourced air temperature to investigate intra-urban microclimate | |
| CN110472782A (en) | A kind of data determination method, device, equipment and storage medium | |
| Yang et al. | Evaluation of a diagnostic equation for the daily maximum urban heat island intensity and its application to building energy simulations | |
| WO2024152865A1 (en) | Meteorological-station-based ecosystem carbon-water flux calculation method and system | |
| CN108764527A (en) | A kind of Soil organic carbon pool space-time dynamic prediction suitable environment Variable Selection method | |
| Tehrani et al. | Predicting solar radiation in the urban area: A data-driven analysis for sustainable city planning using artificial neural networking | |
| Tong et al. | Mapping the urban natural ventilation potential by hydrological simulation | |
| Boccalatte et al. | Mapping the urban heat Island at the territory scale: An unsupervised learning approach for urban planning applied to the Canton of Geneva | |
| Yang et al. | Transforming and validating urban microclimate data with multi-sourced microclimate datasets for building energy modelling at urban scale | |
| CN117172037B (en) | Distributed hydrologic forecasting method, device, computer equipment and medium | |
| Najian et al. | Evaluating critical weather parameters using machine learning models | |
| Liu et al. | Association analysis on spatiotemporal characteristics of block-scale urban thermal environments based on a field mobile survey in Guangzhou, China | |
| CN117932737A (en) | Street block planning evaluation and optimization method based on pollutant exposure risk map | |
| Agüera-Pérez et al. | Spatial persistence in wind analysis | |
| KR20050063616A (en) | Wind resource mapping method | |
| Acero et al. | Urban climate multi-scale modelling in Bilbao (Spain): a review | |
| CN116193369B (en) | Resident population generation rate estimation method based on mobile phone signaling data | |
| CN117114176A (en) | Land utilization change prediction method and system based on data analysis and machine learning | |
| Sperati et al. | A new Wind Atlas to support the expansion of the Italian wind power fleet |
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: 20181214 |
|
| RJ01 | Rejection of invention patent application after publication |