CN108804394A - A kind of construction method of city noctilucence total amount-urban population regression model - Google Patents
A kind of construction method of city noctilucence total amount-urban population regression model Download PDFInfo
- Publication number
- CN108804394A CN108804394A CN201810501619.9A CN201810501619A CN108804394A CN 108804394 A CN108804394 A CN 108804394A CN 201810501619 A CN201810501619 A CN 201810501619A CN 108804394 A CN108804394 A CN 108804394A
- Authority
- CN
- China
- Prior art keywords
- city
- noctilucence
- urban population
- total amount
- 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
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Computation (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of construction methods of city noctilucence total amount-urban population regression model, including carry out the collection of city-level cities' urban population statistical data, screening, draw a circle to approve training sample and test sample；Landsat-8 remote sensing images are pre-processed, the built-up areas polar plot of training sample and test sample is obtained by support vector cassification and sorted clustering processing；The ambient noise that NPP/VIIRS images are rejected using built-up areas polar plot and threshold method, calculates totality intensity of light TNL (TotalofNighttimeLight)；To the city noctilucence total amount and urban population correlation analysis of training sample, establishes regression model and Rationality Assessment is made to model.One aspect of the present invention has incorporated multi-data source in terms of NPP-VIIRS image denoisings, on the other hand, takes full advantage of real-time, the objectivity of remote sensing image, reflects the spatial distribution of urban population, and be of great significance to the prediction and assessment of city population data.
Description
Technical field
The invention belongs to remote sensing social economy geoscience applications technical field, more particularly to a kind of city noctilucence total amount-cities and towns
The construction method of population regression model.
Background technology
An important factor for population is as urban development, science, effectively management population are reasonable to promotion city quality, government
Development policies is formulated to be of great significance.In recent years, Chinese Urbanization's paces are accelerated, and a large amount of populations pour in city.However, city
The sustainable growth of city's population also makes the contradiction between urban population, resource, environment more and more prominent, and seriously affect city can
Sustainable development.Existing demographic data mostlys come from the population registration material or census data of public security department, these
The update cycle of data is long, is difficult to reflect the actual spatial distribution of population.
Nighttime light data can detect the light of the varying strengths of generations such as city, small-scale residential block, be monitoring
The valid data source of mankind's activity.NPP/VIIRS(National Polar-orbiting Partnership/Visible
Infrared Imaging Radiaometer Suite, national polar region cooperation satellite/visible infra-red radiation imager day and night wave
Section) nighttime light data is second generation nighttime light data product, compared to first generation nighttime light data DMSP/OLS
(Defense Meteorological Satellite Program ' s Operational Linescan System, it is military
Meteorological satellite plan/linear scanning system), VIIRS sensors are imaged wide cut 3000km, and spatial resolution is about 500m, to same
Regional daytime daily is imaged twice, has higher sensitivity to night lights, can more accurately reflect earth's surface population point
The spatial information of cloth is particularly suited for the research of human economic society activity etc..But the product do not remove flame,
Gas burning, volcano and aurora, corresponding ambient noise also do not filter.
Invention content
Goal of the invention：In order to overcome the deficiencies in the prior art, the present invention to provide a kind of for NPP-VIIRS images
In the ambient noise that does not filter out, propose to classify the method for carrying out denoising based on remote sensing image, and utilize night lights and people
The correlation of mouth, the city noctilucence total amount-urban population for taking full advantage of the advantages such as real-time, the objectivity of remote sensing image return
The construction method of model.
Technical solution：To achieve the above object, the present invention provides a kind of city noctilucence total amount-urban population regression model
Construction method includes the following steps：
(1) the urban population statistical data that year grade in all parts of the country city is obtained from database, chooses the city of 30 prefecture-level cities
Town demographic data carrys out subsequent builds city noctilucence total amount-urban population regression model as model training sample, then chooses in addition
The urban population data of 30 prefecture-level cities carry out the reasonability of the subsequent authentication model as model measurement sample；
(2) the annual cloud amount of the prefecture-level city chosen from database obtaining step (1) is less than 8% Landsat-8 images,
It is pre-processed and obtains Landsat-8 pre-treatment images；
(3) the monthly nighttime light data of the prefecture-level city chosen from database obtaining step (1), and calculate monthly noctilucence
The average brightness value of image, and then obtain annual noctilucence image；
(4) the Landsat-8 pre-treatment images obtained in step (2) are subjected to resampling, to the year obtained in step (3)
Degree noctilucence image carries out projection and resampling；
(5) utilize SVM (Support Vector Machine, support vector machines) algorithms to the weight that is obtained in step (4)
Landsat-8 pre-treatment images after sampling are classified；
(6) denoising is carried out to the annual noctilucence image that step (4) generates, and model training sample and mould is calculated
The night lights total amount TNL values of type test sample；
(7) the city noctilucence total amount-urban population regression model for being trained sample city is established and comparison：It establishes multiple
Regression model carries out the regression equation goodness of fit comparison for multiple regression models in training sample city, obtains and fit well on
The regression equation of city the noctilucence total amount and urban population of training sample, as city noctilucence total amount-urban population regression model；
(8) Rationality Assessment is carried out to the city noctilucence total amount of foundation-urban population regression model：It will be in step (6)
The TNL values in model measurement sample city substitute into city noctilucence total amount-urban population regression model in step (7), acquire test specimens
The urban population predicted value in this city calculates the urban population predicted value and urban population GDP predicted values in each test sample city
Between relative error, if average relative error be less than 20%, the regression model is reasonable, if average relative error is more than or equal to
20% return to step (7).
Further, pretreated be as follows is carried out to low cloud cover Landsat-8 images in the step (2)：
(2.1) radiation calibration processing is done to low cloud cover Landsat-8 images；
(2.2) atmospheric correction is made to image obtained by step (2.1)；
(2.3) image obtained by step (2.2) is spliced and is cut, obtain training sample city and test sample city
Landsat-8 pre-treatment images.
Further, Landsat-8 pre-treatment images and annual noctilucence image are projected in the step (4) and again
Sampling is as follows：
(4.1) it is 500m by Landsat-8 pre-treatment image resamplings；
(4.2) annual noctilucence image is projected, resampling processing, wherein projection pattern is thrown for Lambert orientation equivalance
Shadow, while setting the value of X and Y to 500m.
Further, classified to Landsat-8 pre-treatment images using SVM algorithm in the step (5) specific
Steps are as follows：
(5.1) earth's surface image is combined, feature decision is done to Landsat-8 pre-treatment images, is by visual observation divided into image
Three classes：Built-up areas, waters, other；
(5.2) post-classification comparison is made to the preliminary classification result of step (5.1)；
(5.3) final classification of step (5.2) is utilized as a result, generating built-up areas polar plot.
Further, denoising is carried out to the annual noctilucence image of generation in the step (6) to be as follows：
(6.1) the noctilucence shadow obtained using the built-up areas polar plot that step (5.3) obtains as mask extraction step (4.2)
Picture obtains primary completed region of the city NPP/VIIRS night lights remote sensing images；
(6.2) 0.3 is filtered out as noise lowest threshold the primary completed region of the city NPP/VIIRS obtained by step (6.1)
Ambient noise in night lights remote sensing image obtains final completed region of the city NPP-VIIRS night lights remote sensing images；
(6.3) distinguish the final completed region of the city NPP-VIIRS night lights remote sensing images that statistic procedure (6.3) obtains
The TNL values in model training sample city, model measurement sample city.
Further, the city noctilucence total amount-urban population regression model in sample city is trained in the step (7)
It establishes and is as follows with comparison：The TNL values in the model training sample city that step (6) is obtained, will as independent variable X
The model training sample urban population statistical value that step (1) obtains establishes city noctilucence total amount-cities and towns respectively as dependent variable Y
Population Exponential Regression Model, city noctilucence total amount-urban population logistic regression models, city noctilucence total amount-urban population are linear
Regression model, and calculate the coefficient of determination R of above three model2Index：R1 2For the decision system of TNL-GDP Exponential Regression Models
Number, R2 2For the coefficient of determination of TNL-GDP logistic regression models, R3 2For the coefficient of determination of TNL-GDP linear regression model (LRM)s；
Wherein coefficient of determination R2Calculation formula be：
Wherein, Y_actual is the urban population statistical value in each model training sample city, and Y_predict is each model instruction
Practice the urban population predicted value in sample city, Y_mean is the average urban population statistical value in model training sample city；
R is calculated by above-mentioned formula1 2、R2 2And R3 2, and judge R1 2、R2 2And R3 2In which numerical value highest, selection determines
The highest regression model of coefficient is determined as final city noctilucence total amount-urban population regression model.
Advantageous effect：Compared with the prior art, the present invention has the following advantages：
The present invention is for ambient noise present in NPP-VIIRS images, using the classification results of optical remote sensing image as base
Plinth extracts the completed region of the city domain in noctilucence remote sensing image, and then the background that can be effective filtered out in noctilucence remote sensing image is made an uproar
Sound.
The present invention establishes the amendment city of gained after denoising by being closely connected between night lights total amount and population distribution
The regression model of city noctilucence total amount and urban population.
Description of the drawings
Fig. 1 is the overview flow chart of the present invention.
Specific implementation mode
The present invention is further described below in conjunction with the accompanying drawings.
As shown in Figure 1, a kind of construction method of city noctilucence total amount-urban population regression model of the present invention, packet
Include following steps：
(1) the urban population statistical data for summarizing grade in all parts of the country city in 2016, chooses the urban population of 30 prefecture-level cities
Data build city noctilucence total amount-urban population regression model as model training sample, then choose 30 other ground levels
The urban population data in city verify the reasonability of the model as model measurement sample；
(2) low cloud cover Landsat-8 images in 2016 are downloaded (it is required that cloud amount is less than in geographical spatial data cloud website
8%) it, and is pre-processed to obtain Landsat-8 pre-treatment images；
(3) in NOAA (National Oceanic and Atmospheric Administration, American National sea
Ocean and Atmospheric Administration) website download 1-12 months NPP/VIIRS (National Polar-orbiting in 2016
Partnership/Visible Infrared Imaging Radiaometer Suite, national polar region cooperation satellite/visible
Infra-red radiation imager day and night wave band) nighttime light data, and use the raster symbol-base device in 10.3 softwares of ArcGIS
(Raster Calculator) tool calculates the average brightness value of 1-12 moonlit night optical images, and then obtains annual noctilucence image；
(4) the Landsat-8 pre-treatment images obtained in step (2) are subjected to resampling, to the year obtained in step (3)
Degree noctilucence image carries out projection and resampling；
(5) classified to the Landsat-8 pre-treatment images after the resampling that is obtained in step (4) using SVM algorithm；
(6) denoising is carried out to the annual noctilucence image that step (4) generates, and calculates TNL values (Total
Nighttime Light, night lights total amount)；
(7) the urban lighting total amount-urban population regression model for being trained sample is established and comparison：Step (6) are obtained
The TNL values in the model training sample city arrived are as independent variable X, the urban population for the model training sample that step (1) is obtained
Statistical data establishes city noctilucence total amount-urban population linear regression model (LRM), urban lighting total amount-city respectively as dependent variable Y
Town population Exponential Regression Model, urban lighting total amount-urban population logistic regression models, and calculate the decision of above three model
Coefficients R2Index,：R1 2For the coefficient of determination of city noctilucence total amount-urban population linear regression model (LRM), R2 2For city noctilucence total amount-
The coefficient of determination of urban population Exponential Regression Model, R3 2For the decision system of city noctilucence total amount-urban population logistic regression models
Number.R2Value shows that the variable X of equation is stronger to the interpretability of Y closer to 1, this model is fitted data also preferable.
Wherein coefficient of determination R2Calculation formula be：
Wherein, Y_actual is the urban population statistical value in each model training sample city, and Y_predict is each model instruction
Practice the urban population predicted value in sample city, Y_mean is the average urban population statistical value in model training sample city；Pass through
R is calculated in above-mentioned formula1 2、R2 2And R3 2, and judge R1 2、R2 2And R3 2In which numerical value highest, select the coefficient of determination it is highest
Regression model is as final regression model；
(8) Rationality Assessment is carried out to the city noctilucence total amount of foundation-urban population regression model：Obtained by step 7
City noctilucence total amount-urban population regression model, the TNL values in the model measurement sample city obtained by step (6.4) are substituted into,
The urban population predicted value for acquiring test sample city, calculate the urban population statistical value in each test sample city and predicted value it
Between relative error, if average relative error be less than 20%, then it is assumed that the regression model is reasonable.
Further, pretreated be as follows is carried out to low cloud cover Landsat-8 images in the step (2)：
(2.1) use the general calibration tool Radiometric Calibration under 5.1 softwares of ENVI to low cloud cover
Landsat-8 images do radiation calibration processing.It needs that the required data type of FLAASH atmospheric corrections, tool is arranged during this
Body parameter setting is as follows：Calibrate type selective radiation rate data (Radiance), storage sequence (Interleave) be arranged BIL or
Person BIP, data type (DataType) are Float types, radiance data unit regulation coefficient (Scale Factor) adjustment
It is 0.1.Spectral profile is checked when showing radiation calibration result images, it can be seen that the numerical value after calibration is concentrated mainly on 0-10 models
In enclosing, unit is μ W/ (cm2*sr*nm)。
(2.2) use the FLAASH Atmospheric Correction tools in 5.1 softwares of ENVI to step (2.1)
Gained image makees atmospheric correction:The geographical coordinate of image, determines central point longitude and latitude Scene obtained by automatic obtaining step (2.1)
Center Location；It selects sensor type SensorType for Landsat-8OLI, obtains its corresponding sensor height
And the resolution ratio of image data；This image imaging time is obtained, is recorded to relative parameters setting；Atmospheric models parameter
(Atmospheric Model) is selected to be selected according to the rule of imaging time and latitude information；In order to reduce result storage space,
Acquiescence reflectivity is multiplied by 10000, and output reflection rate range becomes 0~10000.
(2.3) image obtained by step (2.2) is spliced and is cut, obtain training sample city and test sample city
Landsat-8 pre-treatment images：Image obtained by step (2.2) is carried out using the Seamless Mosaic in ENVI 5.1
Splicing, the even color method provided is Histogram Matching；In Corlor Correction options, Histogram is chosen
Matching；Selection automatically generates edge fit line in Seamlines；Resampling Method select Cubic
Convolution.The image that splicing is completed is cut using ENVI 5.1 and prefecture-level city's administration polar plot, in Subset Data
In from ROIs Parameters panels, following parameter is set：Mask pixels output of ROI？：Yes；Mask
Background Value background values：0.
Further, resampling is carried out to the Landsat-8 pre-treatment images obtained in step (2) in the step (4),
Projection is carried out to the annual noctilucence image obtained in step (3) and resampling is as follows：
(4.1) it is 500m by Landsat-8 pre-treatment image resamplings：Use the Resize Data works in ENVI 5.1
Output X Pixel Size and Output Y Pixel Size are disposed as 500m, Resampling modes are arranged by tool
For Nearest Neighbor；
(4.2) annual noctilucence image is projected, again using the Project Raster tools in 10.3 softwares of ArcGIS
Sampling processing, projection pattern are Lambert orientation equivalance (Lambert Azimuthal Equal Area) projection, at the same by X and
The value of Y is set as 500m.
Further, classified to Landsat-8 pre-treatment images using SVM algorithm in the step (5) specific
Steps are as follows：
(5.1) the earth's surface image in Google Earth softwares is combined, feature is done to Landsat-8 pre-treatment images and is sentenced
Not, image is divided into three classes by visual observation：Built-up areas, waters, other (vegetation, arable lands etc.)；Use the figure layer in ENVI 5.1
Manager (Layer Manager) irises out the ROI (Region of Interest, area-of-interest) of three of the above classification；Point
Class device selects SVM (Support Vector Machine, support vector machines), the parameter values of svm classifier setting as follows：
Kernel Type are Radial Basis Function, Gamma in Kernel Function=0.143, Penalty
Parameter=100, Pyramid Level=0.Preliminary classification result is obtained after svm classifier.
(5.2) post-classification comparison is made to the preliminary classification result of step (5.1), mainly utilizes the cluster in ENVI 5.1
Function does clustering processing to residential land classification results, and parameter Operator Size Rows are that the core of mathematical morphology operators is big
It is small, its numerical value is set as 7, by obtaining final classification results after processing；
(5.3) final classification of step (5.2) is utilized as a result, generating built-up areas polar plot：Use turning in ENVI 5.1
Vector is arranged in Raster to Vector Parameters panels in tool vector Classification to Vector
Output parameter is built-up areas.
Further, denoising is carried out to the annual noctilucence image of generation in the step (6) to be as follows：
(6.1) the Extraction tools in 10.3 softwares of ArcGIS are used, are sweared with the built-up areas that step (5.3) obtains
It is distant to obtain primary completed region of the city NPP/VIIRS night lights for the noctilucence image that spirogram is obtained as mask extraction step (4.2)
Feel image；
(6.2) condition in raster symbol-base device (Raster Calculator) tool in 10.3 softwares of ArcGIS is used
Computing function filters out as noise lowest threshold the primary completed region of the city NPP/VIIRS nights obtained by step (6.1) by 0.3
Ambient noise in light remote sensing image obtains final completed region of the city NPP-VIIRS night lights remote sensing images；
(6.3) the Reclassify tools in 10.3 softwares of ArcGIS are used, statistic procedure (6.3) obtains most respectively
The model training sample city of whole completed region of the city NPP-VIIRS night lights remote sensing images, the TNL in model measurement sample city
Value.
The above is only a preferred embodiment of the present invention, it should be pointed out that：For the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (6)
1. a kind of construction method of city noctilucence total amount-urban population regression model, which is characterized in that include the following steps：
(1) the urban population statistical data that year grade in all parts of the country city is obtained from database, chooses people from cities and towns of 30 prefecture-level cities
Mouth data carry out subsequent builds city noctilucence total amount-urban population regression model as model training sample, then choose other 30
The urban population data of a prefecture-level city carry out the reasonability of the subsequent authentication model as model measurement sample；
(2) the annual cloud amount of the prefecture-level city chosen from database obtaining step (1) is less than 8% Landsat-8 images, carries out
It pre-processes and obtains Landsat-8 pre-treatment images；
(3) the monthly nighttime light data of the prefecture-level city chosen from database obtaining step (1), and calculate monthly noctilucence image
Average brightness value, and then obtain annual noctilucence image；
(4) the Landsat-8 pre-treatment images obtained in step (2) are subjected to resampling, to the annual night obtained in step (3)
Optical image carries out projection and resampling；
(5) classified to the Landsat-8 pre-treatment images after the resampling that is obtained in step (4) using SVM algorithm；
(6) denoising is carried out to the annual noctilucence image that step (4) generates, and model training sample and model survey is calculated
The night lights total amount TNL values of sample sheet；
(7) the city noctilucence total amount-urban population regression model for being trained sample city is established and comparison：Establish multiple recurrence
Model carries out the regression equation goodness of fit comparison for multiple regression models in training sample city, obtains and fit well on training
The regression equation of city the noctilucence total amount and urban population of sample, as city noctilucence total amount-urban population regression model；
(8) Rationality Assessment is carried out to the city noctilucence total amount of foundation-urban population regression model：By the model in step (6)
The TNL values in test sample city substitute into city noctilucence total amount-urban population regression model in step (7), acquire test sample city
The urban population predicted value in city calculates between the urban population predicted value in each test sample city and urban population GDP predicted values
Relative error, if average relative error be less than 20%, the regression model is reasonable, if average relative error be more than or equal to 20%
Then return to step (7).
2. a kind of construction method of city noctilucence total amount-urban population regression model according to claim 1, feature exist
In pretreated to the progress of low cloud cover Landsat-8 images in the step (2) to be as follows：
(2.1) radiation calibration processing is done to low cloud cover Landsat-8 images；
(2.2) atmospheric correction is made to image obtained by step (2.1)；
(2.3) image obtained by step (2.2) is spliced and is cut, obtain training sample city and test sample city
Landsat-8 pre-treatment images.
3. a kind of construction method of city noctilucence total amount-urban population regression model according to claim 1, feature exist
In the specific steps of projection and resampling are carried out in the step (4) to Landsat-8 pre-treatment images and annual noctilucence image
It is as follows：
(4.1) it is 500m by Landsat-8 pre-treatment image resamplings；
(4.2) annual noctilucence image is projected, resampling processing, wherein projection pattern is Lambert orientation authalic projection, together
When set the value of X and Y to 500m.
4. a kind of construction method of city noctilucence total amount-urban population regression model according to claim 1, feature exist
Classified to Landsat-8 pre-treatment images using SVM algorithm in, the step (5) and is as follows：
(5.1) earth's surface image is combined, feature decision is done to Landsat-8 pre-treatment images, image is divided into three classes by visual observation：
Built-up areas, waters, other；
(5.2) post-classification comparison is made to the preliminary classification result of step (5.1)；
(5.3) final classification of step (5.2) is utilized as a result, generating built-up areas polar plot.
5. a kind of construction method of city noctilucence total amount-urban population regression model according to claim 4, feature exist
In, in the step (6) to the annual noctilucence image of generation carry out denoising be as follows：
(6.1) the noctilucence image obtained using the built-up areas polar plot that step (5.3) obtains as mask extraction step (4.2), is obtained
Take primary completed region of the city NPP/VIIRS night lights remote sensing images；
(6.2) 0.3 is filtered out as noise lowest threshold the primary completed region of the city NPP/VIIRS nights obtained by step (6.1)
Ambient noise in light remote sensing image obtains final completed region of the city NPP-VIIRS night lights remote sensing images；
(6.3) model for the final completed region of the city NPP-VIIRS night lights remote sensing images that statistic procedure (6.2) obtains respectively
The TNL values in training sample city, model measurement sample city.
6. a kind of construction method of city noctilucence total amount-urban population regression model according to claim 1, feature exist
In the city noctilucence total amount-urban population regression model for being trained sample city in the step (7) is established and the tool of comparison
Steps are as follows for body：The TNL values in the model training sample city that step (6) is obtained obtain step (1) as independent variable X
Model training sample urban population statistical value establishes city noctilucence total amount-urban population index return mould respectively as dependent variable Y
Type, city noctilucence total amount-urban population logistic regression models, city noctilucence total amount-urban population linear regression model (LRM), and calculate
The coefficient of determination R of above three model2Index：R1 2For the coefficient of determination of TNL-GDP Exponential Regression Models, R2 2It is TNL-GDP pairs
The coefficient of determination of number regression model, R3 2For the coefficient of determination of TNL-GDP linear regression model (LRM)s；
Wherein coefficient of determination R2Calculation formula be：
Wherein, Y_actual is the urban population statistical value in each model training sample city, and Y_predict is each model training sample
The urban population predicted value in this city, Y_mean are the average urban population statistical values in model training sample city；
R is calculated by above-mentioned formula1 2、R2 2And R3 2, and judge R1 2、R2 2And R3 2In which numerical value highest, selection determine system
The highest regression model of number is as final city noctilucence total amount-urban population regression model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810501619.9A CN108804394A (en) | 2018-05-23 | 2018-05-23 | A kind of construction method of city noctilucence total amount-urban population regression model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810501619.9A CN108804394A (en) | 2018-05-23 | 2018-05-23 | A kind of construction method of city noctilucence total amount-urban population regression model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108804394A true CN108804394A (en) | 2018-11-13 |
Family
ID=64091393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810501619.9A Pending CN108804394A (en) | 2018-05-23 | 2018-05-23 | A kind of construction method of city noctilucence total amount-urban population regression model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108804394A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784667A (en) * | 2018-12-21 | 2019-05-21 | 中国科学院遥感与数字地球研究所 | A kind of vacant monitoring method in house based on noctilucence remotely-sensed data |
| CN110765885A (en) * | 2019-09-29 | 2020-02-07 | 武汉大学 | City expansion detection method and device based on heterogeneous luminous remote sensing image |
| CN111414820A (en) * | 2020-03-11 | 2020-07-14 | 长光卫星技术有限公司 | Urban population density acquisition method based on noctilucent images |
| CN111597949A (en) * | 2020-05-12 | 2020-08-28 | 中国科学院城市环境研究所 | NPP-VIIRS night light data-based urban built-up area extraction method |
| CN112115844A (en) * | 2020-09-15 | 2020-12-22 | 中国科学院城市环境研究所 | Urban population data analysis method based on multi-source remote sensing image and road network data |
| CN113033277A (en) * | 2020-12-02 | 2021-06-25 | 湖南科技大学 | National economy estimation method and device based on noctilucent remote sensing data |
| CN113610346A (en) * | 2021-07-02 | 2021-11-05 | 华南农业大学 | Village development potential evaluation and village classification method and device based on multi-source data |
| CN115713691A (en) * | 2022-11-21 | 2023-02-24 | 武汉大学 | Pixel-level electric power popularity estimation method and device based on noctilucent remote sensing |
| CN116503274A (en) * | 2023-04-07 | 2023-07-28 | 中山大学 | Image color homogenizing method and device based on image overlapping area |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012127094A1 (en) * | 2011-03-23 | 2012-09-27 | Servicio Andaluz De Salud | Isolated cells from the blood of the coronary sinus, and uses thereof |
| CN106650618A (en) * | 2016-11-15 | 2017-05-10 | 中山大学 | Random forest model-based population data spatialization method |
| CN107133693A (en) * | 2017-04-26 | 2017-09-05 | 华中师范大学 | Provinces and cities of China life expectancy sequential encryption estimation and its with noctilucence time and space usage method |
| CN107368922A (en) * | 2017-07-20 | 2017-11-21 | 华中师范大学 | Average Price of City Residence predictor method based on nighttime light intensity |
-
2018
- 2018-05-23 CN CN201810501619.9A patent/CN108804394A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012127094A1 (en) * | 2011-03-23 | 2012-09-27 | Servicio Andaluz De Salud | Isolated cells from the blood of the coronary sinus, and uses thereof |
| CN106650618A (en) * | 2016-11-15 | 2017-05-10 | 中山大学 | Random forest model-based population data spatialization method |
| CN107133693A (en) * | 2017-04-26 | 2017-09-05 | 华中师范大学 | Provinces and cities of China life expectancy sequential encryption estimation and its with noctilucence time and space usage method |
| CN107368922A (en) * | 2017-07-20 | 2017-11-21 | 华中师范大学 | Average Price of City Residence predictor method based on nighttime light intensity |
Non-Patent Citations (3)
| Title |
|---|
| KAIFANG SHI: "Evaluating the Ability of NPP-VIIRS Nighttime Light Data to Estimate the Gross Domestic Product and the Electric Power Consumption of China at Multiple Scales: A Comparison with DMSP-OLS Data", 《REMOTE SENSING》 * |
| 李翔 等: "基于夜间灯光数据和空间回归模型的城市常住人口格网化方法研究", 《地球信息科学》 * |
| 王若曦 等: "DMSP夜间灯光数据与Landsat数据结合的建成区提取研究", 《华中师范大学学报（自然科学版）》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784667A (en) * | 2018-12-21 | 2019-05-21 | 中国科学院遥感与数字地球研究所 | A kind of vacant monitoring method in house based on noctilucence remotely-sensed data |
| CN109784667B (en) * | 2018-12-21 | 2023-09-19 | 中国科学院遥感与数字地球研究所 | House space monitoring method based on noctilucent remote sensing data |
| CN110765885A (en) * | 2019-09-29 | 2020-02-07 | 武汉大学 | City expansion detection method and device based on heterogeneous luminous remote sensing image |
| CN111414820A (en) * | 2020-03-11 | 2020-07-14 | 长光卫星技术有限公司 | Urban population density acquisition method based on noctilucent images |
| CN111597949B (en) * | 2020-05-12 | 2023-04-11 | 中国科学院城市环境研究所 | NPP-VIIRS night light data-based urban built-up area extraction method |
| CN111597949A (en) * | 2020-05-12 | 2020-08-28 | 中国科学院城市环境研究所 | NPP-VIIRS night light data-based urban built-up area extraction method |
| CN112115844B (en) * | 2020-09-15 | 2022-10-18 | 中国科学院城市环境研究所 | Urban population data analysis method based on multi-source remote sensing image and road network data |
| CN112115844A (en) * | 2020-09-15 | 2020-12-22 | 中国科学院城市环境研究所 | Urban population data analysis method based on multi-source remote sensing image and road network data |
| CN113033277A (en) * | 2020-12-02 | 2021-06-25 | 湖南科技大学 | National economy estimation method and device based on noctilucent remote sensing data |
| CN113610346A (en) * | 2021-07-02 | 2021-11-05 | 华南农业大学 | Village development potential evaluation and village classification method and device based on multi-source data |
| CN115713691A (en) * | 2022-11-21 | 2023-02-24 | 武汉大学 | Pixel-level electric power popularity estimation method and device based on noctilucent remote sensing |
| CN115713691B (en) * | 2022-11-21 | 2024-01-30 | 武汉大学 | Noctilucent remote sensing-based pixel-level power popularity rate estimation method and device |
| CN116503274A (en) * | 2023-04-07 | 2023-07-28 | 中山大学 | Image color homogenizing method and device based on image overlapping area |
| CN116503274B (en) * | 2023-04-07 | 2023-12-22 | 中山大学 | Image color homogenizing method and device based on image overlapping area |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108804394A (en) | A kind of construction method of city noctilucence total amount-urban population regression model | |
| CN108875583A (en) | A kind of TNL-GDP regression model construction method based on urban architecture classification | |
| CN106971146B (en) | Based on three water body exception remote sensing dynamic monitoring and controlling method, the device and system for looking into technology | |
| Berberoglu et al. | Assessing different remote sensing techniques to detect land use/cover changes in the eastern Mediterranean | |
| CN111046613B (en) | Optimal river channel calculation method based on path tracking and river network extraction method based on multi-temporal remote sensing image | |
| Naboureh et al. | An integrated object-based image analysis and CA-Markov model approach for modeling land use/land cover trends in the Sarab plain | |
| CN110232389A (en) | A kind of stereoscopic vision air navigation aid based on green crop feature extraction invariance | |
| CN107229929A (en) | A kind of license plate locating method based on R CNN | |
| CN110866494B (en) | Urban group extraction method and system based on optical remote sensing image | |
| CN110263717A (en) | It is a kind of incorporate streetscape image land used status determine method | |
| CN109858450A (en) | Ten meter level spatial resolution remote sensing image cities and towns extracting methods of one kind and system | |
| CN110046214A (en) | Vegetation class remote sensing information automatic identifying method based on vegetation distributed data base | |
| CN110110025A (en) | Regional population's density analog method based on characteristic vector space filter value | |
| CN115272860A (en) | Method and system for determining rice planting area, electronic device and storage medium | |
| CN109035223A (en) | A kind of intelligent evaluation method for satellite remote sensing images availability | |
| Xu et al. | A framework for land use scenes classification based on landscape photos | |
| Zhu et al. | Reducing mis-registration and shadow effects on change detection in wetlands | |
| Nelson et al. | Spatial statistical techniques for aggregating point objects extracted from high spatial resolution remotely sensed imagery | |
| CN110427961A (en) | A kind of rule-based and samples fusion architecture information extracting method and system | |
| Toda et al. | Determination of species-specific leaf angle distribution and plant area index in a cool-temperate mixed forest from UAV and upward-pointing digital photography | |
| Mugiraneza et al. | Spatiotemporal analysis of urban land cover changes in Kigali, Rwanda using multitemporal Landsat data and landscape metrics | |
| Jafarzadeh et al. | Increasing the spatial accuracy of the land use map using fusion of optical and radar images of Sentinel and Google Earth Engine | |
| Workie | Assessment of aboveground carbon stock in coniferous and broadleaf forests, using high spatial resolution satellite images | |
| Siljander et al. | A predictive modelling technique for human population distribution and abundance estimation using remote-sensing and geospatial data in a rural mountainous area in Kenya | |
| CN108399413A (en) | A kind of picture shooting region recognition and geographic positioning and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181113 |