CN106485360A - Segmental society's prediction of economic indexes method and system based on overall noctilucence remote sensing - Google Patents

Abstract

The present invention provides segmental society's prediction of economic indexes method and system based on overall noctilucence remote sensing, includings cutting image and extract the nighttime light intensity value total amount of target zone, the socio-economic indicator of extraction regional area；Assumed based on linear concordance, judge between the nighttime light intensity value total amount of global area and the nighttime light intensity value total amount of regional area, and between the nighttime light intensity value total amount of regional area and the socio-economic indicator of regional area, if there is the linear dependence meeting pre-conditioned threshold value；Build the segmental society's economic indicator quantitative inversion model based on overall noctilucence remote sensing when meeting, global area nighttime light intensity value total amount according to year to be predicted, it is predicted analyzing based on inverse model, the socio-economic indicator obtaining the accordingly regional area in year predicts the outcome, complete segmental society's economic dynamic development to estimate, estimation results automatically can be obtained in time, there is important market value.

Description

Local socioeconomic index prediction method and system based on global noctilucent remote sensing

Technical Field

The invention belongs to the field of remote sensing geography application, and relates to a local socioeconomic index quantitative inversion prediction method and system based on global noctilucent remote sensing.

Background

An Operational Line System (OLS) sensor mounted on a military Meteorological Satellite (DMSP) has a high photoelectric amplification capability because it uses a photomultiplier tube (PMT) at night. By utilizing the photoelectric amplification characteristic, the urban light, the urban fire light and even the glow with extremely low visibility can be detected, so that the device has the capability of clearly capturing the footprints of human activities in a dark background, and becomes unique data capable of monitoring the human economic activities. The available DMSP/OLS is long-time sequence data from 1992 to 2013, and guarantees that noctilucent remote sensing data is comparable between regions and between years. Therefore, the DMSP/OLS noctilucent remote sensing data is widely applied to urban space expansion research in a large regional range, economic and population estimation, urban electricity consumption and energy consumption analysis, carbon emission, light pollution and other environmental problem assessment.

However, the spatial resolution of the DMSP/OLS data is 2.7km, which is obtained by averaging 5 higher-resolution sensor data on the satellite, and such a low spatial resolution results in that the applications and researches based on the DMSP/OLS data are more concentrated on a larger area range of the city or above, while the applications and researches based on a small area of the DMSP/OLS night light data are rarely related. Meanwhile, the existing large-area modeling based on DMSP/OLS data is not strictly theoretically proved, and the rationality and the scientificity of model construction are not theoretically demonstrated.

Disclosure of Invention

The invention aims to provide a local socioeconomic index quantitative inversion prediction technical scheme based on global noctilucent remote sensing, aiming at the defects of the existing DMSP/OLS data in the application range (small scale) and the theoretical demonstration of model construction.

The technical scheme adopted by the invention provides a local socioeconomic index prediction method based on global noctilucent remote sensing, which comprises the following steps:

step 1, respectively taking a local area and a global area as target ranges, cutting out a noctilucent remote sensing image of the target range, and extracting the total SOL of nighttime light intensity values of the target range for a plurality of years;

step 2, extracting the social and economic indicators SEI of the local area for a plurality of years_Local；

Step 3, based on the linear consistency assumption, judging the total quantity SOL of the night light intensity values of the global area_GlobalSum of night light intensity values SOL associated with local area_LocalAnd total amount of night light intensity values SOL of local area_LocaSocial and economic indicators SEI with local areas_LocalAnd whether there is a linear correlation that satisfies a preset condition threshold, includes the substeps of,

and 3. step 3.1, judging SOL_GlobalAnd SOL_LocalWhether linear correlation meeting the preset condition threshold exists or not, the correlation coefficient calculation formula is as follows,

wherein (SOL)_Local)_iIs the total light quantity in the local area at the ith year night,is the average value of the total amount of local area night light, (SOL)_Global)_iIs the light total amount in the ith year night in the global area,is the expectation of the total amount of night light in the global area; n represents the total number of years, and the value of i is 1,2, … and N;

step 3.2, judging SOL_LocalAnd SEI_LocalWhether linear correlation meeting the preset condition threshold exists or not, the correlation coefficient calculation formula is as follows,

wherein (SOL)_Local)_iIs the total light quantity in the local area at the ith year night,is the average value of the total amount of local area night light, (SEI)_Local)_iIs the i-th year socioeconomic index value in the local area,the expectation of socioeconomic index values in local areas is obtained;

step 4, when the linear correlation condition in the step 3.1 and the step 3.2 is established, a local socioeconomic index quantitative inversion model based on global noctilucent remote sensing is constructed for predicting the development situation of the local socioeconomic, and the method comprises the following substeps,

step 4.1, the following ideal model is established and parameter estimation is carried out,

SEI_Local＝A+B×SOL_Global

wherein A and B are estimated model parameters;

step 4.2, according to the model parameters estimated in the step 4.1, a local socioeconomic index quantitative inversion model based on global noctilucent remote sensing is constructed as follows,

SEI_Local＝A+B×SOL_Global+ζ,ζ～N(0,σ²)

where ζ is the overall random error after perturbation, N (0, σ)²) Is normally distributed, with a mean of 0 and a variance of σ;

and step 5, according to the total night light intensity value of the global area of the year to be predicted, performing prediction analysis based on the local socioeconomic index quantitative inversion model based on the global noctilucent remote sensing and constructed in the step 4 to obtain the socioeconomic index prediction result of the local area of the corresponding year, and completing the prediction of the development situation of the local socioeconomic.

Moreover, the preset condition threshold is 0.8, and when | rho | is less than or equal to 1 is 0.8, the SOL is considered to be_GlobalAnd SOL_LocalOr SOL_LocalAnd SEI_LocalAre highly correlated.

Furthermore, in step 1 and step 5, the implementation of extracting the total amount of the night light intensity value comprises the following sub-steps,

step 1.1, converting a geographical projection coordinate system of DMSP/OLS noctilucent remote sensing data into Labert equal-area projection to obtain a DMSP/OLS raster image;

step 1.2, cutting out a DMSP/OLS raster image map of a target range according to a vector boundary image layer of the target range;

wherein n represents the number of pixel gray levels, DN_iBrightness value, M, representing picture elements of the ith level in the area_iRepresenting the total number of picture elements of the ith brightness level in the area, i being from 0 to n-1.

In addition, the prediction interval of 1-alpha of the prediction result obtained in the step 5 is as follows:

wherein α is the significance level, SOL₀SOL of global region for satisfying correlation condition, i.e. total night light intensity value of global region for year to be predicted, SEI₀Is SOL ═ SOL₀The observed value represents the social and economic index of the local area of the year to be predicted;is SEI₀(ii) an estimation of socio-economic indicators prediction results (SOL) representing a local area of the year to be predicted₀) Is the uncertainty of the predicted value.

The invention provides a local socioeconomic index prediction system based on global noctilucent remote sensing, which comprises the following modules:

the first module is used for cutting out a noctilucent remote sensing image of a target range by taking a local area and a global area as the target range respectively, and extracting the total SOL of nighttime light intensity values of the target range for a plurality of years;

a second module for extracting the social economic indicators SEI of the local area for several years_Local；

A third module for line-basedAssuming consistency, judging total SOL of night light intensity values of the global area_GlobalSum of night light intensity values SOL associated with local area_LocalAnd total amount of night light intensity values SOL of local area_LocaSocial and economic indicators SEI with local areas_LocalAnd whether there is a linear correlation satisfying a preset condition threshold, includes the following units,

unit 3.1 for judging SOL_GlobalAnd SOL_LocalWhether linear correlation meeting the preset condition threshold exists or not, the correlation coefficient calculation formula is as follows,

wherein (SOL)_Local)_iIs the total light quantity in the local area at the ith year night,is the average value of the total amount of local area night light, (SOL)_Global)_iIs the light total amount in the ith year night in the global area,is the expectation of the total amount of night light in the global area; n represents the total number of years, and the value of i is 1,2, … and N;

unit 3.2 for judging SOL_LocalAnd SEI_LocalWhether linear correlation meeting the preset condition threshold exists or not, the correlation coefficient calculation formula is as follows,

wherein (SOL)_Local)_iIs the total light quantity in the local area at the ith year night,is the average value of the total amount of local area night light, (SEI)_Local)_iIs the i-th year socioeconomic index value in the local area,the expectation of socioeconomic index values in local areas is obtained;

a fourth module for predicting the local socioeconomic development situation by constructing a local socioeconomic index quantitative inversion model based on global noctilucent remote sensing when the unit 3.1 and the unit 3.2 judge that the linear correlation condition is established, comprising a unit 4.1 for establishing the following ideal model and performing parameter estimation,

SEI_Local＝A+B×SOL_Global

wherein A and B are estimated model parameters;

a unit 4.2, according to the model parameters estimated by the unit 4.1, constructs a local social and economic index quantitative inversion model based on global noctilucent remote sensing as follows,

SEI_Local＝A+B×SOL_Global+ζ,ζ～N(0,σ²)

where ζ is the overall random error after perturbation, N (0, σ)²) Is normally distributed, with a mean of 0 and a variance of σ;

and the fifth module is used for carrying out prediction analysis on the basis of the local socioeconomic index quantitative inversion model based on the global noctilucent remote sensing and constructed by the fourth module according to the total night light intensity value of the global area of the year to be predicted to obtain the socioeconomic index prediction result of the local area of the corresponding year, and completing the prediction of the local socioeconomic development situation.

Moreover, the preset condition threshold is 0.8, and when | rho | is less than or equal to 1 is 0.8, the SOL is considered to be_GlobalAnd SOL_LocalOr SOL_LocalAnd SEI_LocalAre highly correlated.

Moreover, in the first module and the fifth module, the implementation of extracting the total amount of the night light intensity value comprises the following units,

the unit 1.1 is used for converting a geographical projection coordinate system of the DMSP/OLS noctilucent remote sensing data into a Labert equal-area projection to obtain a DMSP/OLS raster image;

a unit 1.2, configured to cut out a DMSP/OLS raster image map of the target range according to the vector boundary layer of the target range;

wherein n represents the number of pixel gray levels, DN_iBrightness value, M, representing picture elements of the ith level in the area_iRepresenting the total number of picture elements of the ith brightness level in the area, i being from 0 to n-1.

And the prediction interval of 1-alpha of the prediction result obtained by the fifth module is as follows:

wherein α is the significance level, SOL₀SOL of global region for satisfying correlation condition, i.e. total night light intensity value of global region for year to be predicted, SEI₀Is SOL ═ SOL₀The observed value represents the social and economic index of the local area of the year to be predicted;is SEI₀(ii) an estimation of socio-economic indicators prediction results (SOL) representing a local area of the year to be predicted₀) Is the uncertainty of the predicted value.

The technical scheme provided by the invention has the beneficial effects that: aiming at the defects of the existing research method and content of the noctilucent remote sensing image, a novel method for predicting a global-to-local quantitative inversion model based on night light data is provided, and the convertibility from the global noctilucent remote sensing image to the local noctilucent remote sensing image is theoretically deduced and proved. On the basis, the proposed ideal quantitative inversion model is optimized, the RANSAC algorithm can be used for improving the data quality, the uncertainty of model estimation is quantitatively analyzed, the application range of luminous remote sensing data is expanded, a new thought is provided for the research of global to local problems in the fields of research geography and other subjects, the estimation of social and economic indexes is more objective, and the interference of human factors is avoided. Different from the traditional statistical mode, a large amount of data in multiple aspects is needed, a large amount of manpower and material resources are occupied, and by utilizing the technical scheme provided by the invention, the estimated result can be automatically and timely obtained according to the total amount of the night light intensity values of the global area of the current year, so that the method has important market value.

Drawings

FIG. 1 is a flow diagram of an embodiment of the invention.

Fig. 2 is a schematic view of a noctilucent remote sensing image in Hubei province (global area) and Wuhan city (local area) according to an embodiment of the present invention.

FIG. 3 shows SOL before and after outlier rejection in an embodiment of the present invention_HubeiGDP from Wuhan City_WuhanFig. 3a is a schematic diagram of the linear regression prediction model before removing the abnormal value, and fig. 3b is a schematic diagram of the linear regression prediction model after removing the abnormal value.

FIG. 4 shows GDP before and after outlier rejection in an embodiment of the present invention_WuhanAnd SOL_HubeiThe prediction interval is compared with the diagram, FIG. 4a shows GDP before removing abnormal value_WuhanAnd SOL_HubeiThe prediction interval is illustrated schematically, and FIG. 4b shows GDP after removing abnormal values_WuhanAnd SOL_HubeiThe prediction interval is shown schematically.

Detailed Description

For better understanding of the technical solutions of the present invention, the following detailed description of the present invention is made with reference to the accompanying drawings and examples.

Referring to fig. 1, in the embodiment of the present invention, taking GDP quantitative inversion in martian city based on noctilucent remote sensing in north and Hu as an example, for Sum of Lights intensity values (SOL) and socioeconomic indicators (SEI), the total amount of the Lights intensity values at night in the global area is recorded as SOL_GlobalSOL in the corresponding experimental example_Hubei(ii) a The total night light intensity value of the local area is recorded as SOL_LocalSOL in the corresponding experimental example_Wuhan(ii) a Socio-economic designation of local area SEI_LocalGDP in the corresponding experimental example_Wuhan。

The night light intensity value of the embodiment is derived from DMSP/OLS noctilucent remote sensing data, and other data can be adopted in specific implementation, and the embodiment is not limited to DMSP/OLS.

The local socioeconomic index prediction method based on global noctilucent remote sensing in the embodiment is concretely realized by the following steps:

step 1, respectively taking a local area and a global area as target ranges, cutting out a noctilucent remote sensing image of the target range by using an extraction tool in ArcGIS, and obtaining SOL of the target range for a plurality of years through a Sum of Lights (SOL) calculation formula.

The specific implementation includes the following sub-steps,

step 1.1, converting a geographical projection coordinate system of DMSP/OLS noctilucent remote sensing data into Labert equal-area projection to obtain a DMSP/OLS raster image;

step 1.2, cutting out a DMSP/OLS raster image map of a target range from the result obtained in the step 1 according to the vector boundary layer of the target range;

step 1.3, the calculation method for obtaining the total SOL value of the night light intensity values in the target range by the statistical summation method is as follows:

wherein n represents the gray scale number of the pixel, and the DMSP/OLS noctilucent data records a 6-bit gray scale image, so that the gray scale is 6 powers of 2, namely 64 levels. DN_iBrightness value, M, representing picture elements of the ith level in the area_iThe total number of picture elements representing the ith brightness level in the region, i, is from 0 to n-1, so embodiments take from 0 to 63, and may take from 1 to 63 when calculated.

In specific implementation, the target range is a designated area, and the total amount of the night light intensity values can be extracted by taking the local area or the global area as the target range respectively according to needs. See fig. 2 for noctilucent remote sensing images in Hubei province (global area) and Wuhan city (local area).

Step 2, determining indexes (SEI) for measuring socioeconomic conditions of the local area, such as GDP (global data set) or population, and obtaining socioeconomic indexes SEI of corresponding years of the local area by looking up the national or regional statistical yearbook of the relevant indexes_Local；

According to the formula (1) and the related statistical yearbook, the SOL and GDP of the city of Wuhan are calculated in 10 years such as Hubei province in 1998, 2000, 2003, 2005, 2006, 2008, 2009, 2010, 2011, 2012 and the like, as shown in the following Table 1,

TABLE 1 SOL (SOL) of Hubei province_Hubei) GDP (GDP) of Wuhan City_Wuhan) (unit: wanyuan)

Step 3, based on the linear consistency assumption, judging the total quantity of the night light intensity values (SOL) of the global area according to the historical data obtained in the steps 1 and 2_Global) And local area SOL (SOL)_Local) And local area SOL (SOL)_Local) And local area Socio-Economic Indicators (SEI)_Local) And whether there is a strong linear correlation, includes the following sub-steps,

step 3.1, judging SOL_GlobalAnd SOL_LocalWhether strong linear correlation exists between the two correlation coefficients is determined by the following formula:

in the formula (2), (SOL)_Local)_iIs the total light quantity in the local area at the ith year night,is the average value of the total night light of local areas, and is measured by the sum of the local areas in N years (SOL)_Local)_iTaking the average to obtain (SOL)_Global)_iIs the light total amount in the ith year night in the global area,is the expectation (i.e., arithmetic mean) of the total amount of night light in the global area; n represents the total number of years, and the value of i is 1,2, … and N.

Step 3.2, judging SOL_LocalAnd SEI_LocalWhether strong linear correlation exists between the two correlation coefficients is determined by the following formula:

in the formula (3), SOL_LocalIs the total amount of night light in a local area (SOL)_Local)_iIs the total light quantity in the local area at the ith year night,is the average value of the total amount of local area night light, (SEI)_Local)_iIs the i-th year socioeconomic index value in the local area,is a expectation (i.e. arithmetic mean) of the socioeconomic indicator value in the local area.

The embodiment of the invention provides that when | ρ | ═ 0, SOL is indicated_GlobalAnd SOL_LocalOr SOL_LocalAnd SEI_LocalCompletely unrelated; when 0 < | ρ | < 0.3, SOL is considered_GlobalAnd SOL_LocalOr SOL_LocalAnd SEI_LocalNot related; when | rho | is less than or equal to 0.5 in the condition of 0.3, considering that SOL is equal to or less than 0.5_GlobalAnd SOL_LocalOr SOL_LocalAnd SEI_LocalLow degree of correlation; when | rho | is more than 0.5 and less than or equal to 0.8, the SOL is considered_GlobalAnd SOL_LocalOr SOL_LocalAnd SEI_LocalSignificant correlation; when | rho | is less than or equal to 1 is more than 0.8, the SOL is considered to be_GlobalAnd SOL_LocalOr SOL_LocalAnd SEI_LocalAre highly correlated.

The embodiment sets the correlation condition threshold to 0.8, and those skilled in the art can set other values in the specific implementation. If the correlation condition threshold is met, the condition with strong linear correlation is determined to be satisfied, the step 4 can be entered, if the correlation condition threshold is not met, the method is not suitable, and the flow is stopped. According to the formula (2) and the formula (3), the SOL is calculated_HubeiAnd SOL_WuhanAnd SOL_WuhanAnd GDP_WuhanAre respectively 0.9748 and 0.0.9122, and both the correlation coefficients satisfy rho ∈ (0.8, 1)]Linear correlation in step 3.1 and step 3.2The sexual condition is established.

Step 4, when the linear correlation condition in the step 3.1 and the step 3.2 is established, estimating the development situation of the local socioeconomic by constructing a local socioeconomic index quantitative inversion model based on the global noctilucent remote sensing, comprising the following substeps,

step 4.1, in order to construct a local socioeconomic index quantitative inversion model based on global noctilucent remote sensing, an ideal model is firstly constructed and parameter estimation is carried out:

according to SOL_GlobalAnd SOL_LocalAnd SOL_LocalAnd SEI_LocalThere is a strong correlation between them, and a regression model can be constructed as follows:

SOL_Local＝a_DN+b_DN×SOL_Global(4)

SEI_Local＝a_Local+b_Local×SOL_Local(5)

in the formula (II), SOL_GlobalSOL, SOL representing a Global region_LocalIndicating SOL, SEI in local areas_LocalIndicates SEI in a local area, a_DNAnd b_DN，a_LocalAnd b_LocalIs a coefficient.

Substituting formula (4) into formula (5) to obtain SEI_Local:

SEI_Local＝a_Local+b_Local×(a_DN+b_DN×SOL_Global) (6)

Further, let A ═ a_Local+b_Local×a_DN，B＝b_Local×b_DNThen, an ideal model is obtained as follows:

SEI_Local＝A+B×SOL_Global(7)

where A and B are the estimated model parameters.

SEI_LocalAnd SOL_GlobalAnd SEI_LocalAnd SOL_LocalThe principle of equivalence of the correlations proves to be as follows:

in the formula, ρ is a correlation coefficient between SEI of the local area and SOL of the local area, and ρ 'is a correlation coefficient between SEI of the local area and SOL of the global area, so that the correlation coefficient ρ from the local SOL to the local SEI is equal to the correlation coefficient ρ' from the global SOL to the local SEI.

In the specific implementation, when the linear regression prediction model parameter estimation is performed, the conventional RANSAC algorithm can be used, namely, firstly, a judgment criterion is made for input data, data which have a larger difference with the estimation parameter are iteratively eliminated, and then correct input data are reserved to solve the linear regression prediction model. The judgment criterion requires that at least one group of data is all model interior points under a certain confidence probability in the M groups of data, namely the following relations are required to be satisfied:

d＝1-(1-(1-θ)^q)^M(9)

in the formula, θ represents the error rate of data (i.e. the proportion of outliers in the original data), q is the minimum data size required for calculating the model parameters, d is the confidence probability, and M is the number of sample groups. And according to the actual situation of the experimental data, calculating the minimum sampling number by setting the confidence probability d of the experimental data and the error rate theta of the data to estimate the final model parameters.

For example, using the existing RANSAC algorithm program, the SOL (SOL) of Hubei province of 10 years_Hubei) GDP (GDP) of Wuhan City_Wuhan) Inputting data into a RANSAC algorithm program, setting a confidence probability setting d to be 0.90 and the maximum iteration number to be 45 according to a formula (7), removing 7 th points and 8 th points, namely 2009 and 2010 data, and obtainingThe estimated parameters of the model were-3977.725, 0.013, respectively.

Step 4.2, according to the model parameters estimated in the step 4.1, constructing a local socioeconomic index quantitative inversion model based on global noctilucent remote sensing, which comprises the following steps:

SEI_Local＝A+B×SOL_Global+ζ,ζ～N(0,σ²) (10)

in the formula, SEI_LocalIs the SEI, SOL of the local area_GlobalIs the SOL of the global region, A and B are the parameters to be estimated, ζ is the overall random error after perturbation, N (0, σ)²) Is normally distributed with a mean of 0 and a variance of σ.

Considering disturbance existing in actual data, noise on slope and intercept can be comprehensively considered, and a GTLQTM disturbance model under actual disturbance is constructed. Thus, SEI_LocalAnd SOL_LocalThe expression of (c) can be written as:

in the formula (11) and the formula (12), i is the denominator for indicating the i-th observed data, m and n are the slopes, e 'and f' are the intercepts, and ω is_i'、μ_i'、η_i'、λ_i' is a random perturbation term added to the slope and intercept, respectively, obeying a normal distribution, SEI_LocalAnd SOL_GlobalThe expression of (a) is as follows:

wherein a and b are first order polynomial coefficients corresponding to slope and intercept.

Through substitution, the expression of the quantitative inversion conversion from the global to the local night light remote sensing image under the actual disturbance condition is obtained as follows:

SEI_Local＝A+B×SOL_Global+ζ (14)

in formula (14), SEI_LocalIs the SEI, SOL of the local area_GlobalThe SOL of the global area, A and B are parameters to be estimated, and zeta is the random error of the overall disturbed. And (3) obtaining a local socioeconomic index quantitative inversion model based on global noctilucent remote sensing according to the formula (14), as shown in the formula (10).

In the embodiment, according to a formula (10), a local socioeconomic index quantitative inversion model based on global noctilucent remote sensing after abnormal values are removed is constructed, wherein the model is that y is-3977.725 +0.013 × x, and y corresponds to SEI_LocalX corresponds to SOL_GlobalThe scatter plots before and after the elimination of the abnormal value are shown in fig. 3, according to the formula (10), a regression model y is constructed before the elimination of the abnormal value, wherein the regression model y is-1598.1072 +0.0091 × x (shown in fig. 3 a), and the coefficient R can be determined²0.6453, the regression model y after removing the outlier is-3977.7251 +0.013 × x (as shown in fig. 3 b), and the coefficient R can be determined²When the outliers are removed, 0.8709, the goodness of fit of the model is significantly improved.

And step 5, according to the total night light intensity value of the global area of the year to be predicted, performing prediction analysis based on the local socioeconomic index quantitative inversion model based on the global noctilucent remote sensing and constructed in the step 4 to obtain the socioeconomic index prediction result of the local area of the corresponding year, and completing the prediction of the development situation of the local socioeconomic.

And (3) the total quantity extraction mode of the night light intensity values of the global area to be predicted year is consistent with the step 1.

In practice, if a traditional statistical method is adopted, a large amount of data in many aspects is needed, a large amount of manpower and material resources are occupied, and the statistical result of the socioeconomic index is obtained after several years. By using the method provided by the invention, the estimated result can be automatically and timely obtained according to the total night light intensity value of the global area of the current year.

The technical scheme of the invention is adopted to carry out predictive analysis on the constructed local socioeconomic index quantitative inversion model based on global noctilucent remote sensing, and the 1-alpha prediction interval is as follows:

in the formula (II), SOL₀SOL of global region for satisfying correlation condition, i.e. total night light intensity value of global region for year to be predicted, SEI₀Is SOL ═ SOL₀The observed value of the place, namely the social and economic index of the local area of the year to be predicted;is SEI₀Estimating, namely predicting the social economic index prediction result of a local area of the year to be predicted; (SOL)₀) Is the uncertainty of the predicted (estimated) SOL, preferably, calculated as follows,

wherein,is a standard deviation estimate, t follows the student distribution,representing the distribution of studentsThe position of the branch point is divided into two parts,is the SOL of all years in the historical dataValue, sum of squares of total deviationsN is the number of observations, i.e. the total years of historical data, SOL_iThe degree of freedom is N-2, and α is the significance level, which is the total amount of the global regional night light intensity values of the ith year in the historical data.

According to equation (15), let α be 0.05, which gives a 95% confidence interval as shown in fig. 4. Comparing fig. 4a with fig. 4b, the 95% confidence bands in fig. 4b are narrower than those in fig. 4a, which shows that the model constructed after rejecting outliers is more likely to explain the sample condition than the regression model constructed before rejecting outliers as a whole.

Secondly, the uncertainty intervals of the minimum value, the maximum value and the mean value of x before and after the abnormal value is eliminated in the table 2 are compared, and x before the abnormal value is eliminated_minThe uncertainty interval at 372019 is (2376.96, 5512.57), with a variance of 7889.53, x_maxThe uncertainty interval at 953738 is (1749.74, 9516.04), with a variance of 7766.3, x_meanThe uncertainty interval at 591793 is (47.7678, 7477.54), with a magnitude of change of 7429.77; removing abnormal value x_minThe uncertainty interval at 372019 is (2299.77, 3432.44), with a variance of 5732.21, x_maxThe uncertainty interval at 953738 is (3518.76, 9283.2), with a variance of 5764.44, x_meanThe uncertainty interval at 569746 is (783.86, 6076.07), the variation range is 5292.21, the uncertainty interval is obviously reduced after the abnormal values are eliminated, and the reduction range of the uncertainty interval is approximately 2000 by taking the minimum value, the maximum value and the mean value of x as an example.

TABLE 2 GDP truth value and predicted value comparison in Wuhan City before and after eliminating abnormal values

In specific implementation, the method provided by the invention can realize automatic operation flow based on software technology, and can also realize a corresponding system in a modularized mode. The embodiment of the invention provides a local socioeconomic index prediction system based on global noctilucent remote sensing, which comprises the following modules:

the first module is used for cutting out a noctilucent remote sensing image of a target range by taking a local area and a global area as the target range respectively, and extracting the total SOL of nighttime light intensity values of the target range for a plurality of years;

a second module for extracting the social economic indicators SEI of the local area for several years_Local；

A third module for determining the total amount SOL of night light intensity values in the global area based on the assumption of linear consistency_GlobalSum of night light intensity values SOL associated with local area_LocalAnd total amount of night light intensity values SOL of local area_LocaSocial and economic indicators SEI with local areas_LocalAnd whether there is a linear correlation satisfying a preset condition threshold, includes the following units,

unit 3.1 for judging SOL_GlobalAnd SOL_LocalWhether linear correlation meeting the preset condition threshold exists or not, the correlation coefficient calculation formula is as follows,

wherein (SOL)_Local)_iIs the total light quantity in the local area at the ith year night,is the average value of the total amount of local area night light, (SOL)_Global)_iIs the light total amount in the ith year night in the global area,is the expectation of the total amount of night light in the global area; n represents the total number of years, and the value of i is 1,2, … and N;

unit 3.2 for judging SOL_LocalAnd SEI_LocalWhether linear correlation meeting the preset condition threshold exists or not, the correlation coefficient calculation formula is as follows,

wherein (SOL)_Local)_iIs the total light quantity in the local area at the ith year night,is the average value of the total amount of local area night light, (SEI)_Local)_iIs the i-th year socioeconomic index value in the local area,the expectation of socioeconomic index values in local areas is obtained;

a fourth module for predicting the local socioeconomic development situation by constructing a local socioeconomic index quantitative inversion model based on global noctilucent remote sensing when the unit 3.1 and the unit 3.2 judge that the linear correlation condition is established, comprising a unit 4.1 for establishing the following ideal model and performing parameter estimation,

SEI_Local＝A+B×SOL_Global

wherein A and B are estimated model parameters;

a unit 4.2, according to the model parameters estimated by the unit 4.1, constructs a local social and economic index quantitative inversion model based on global noctilucent remote sensing as follows,

SEI_Local＝A+B×SOL_Global+ζ,ζ～N(0,σ²)

where ζ is the overall random error after perturbation, N (0, σ)²) Is normally distributed, with a mean of 0 and a variance of σ;

and the fifth module is used for carrying out prediction analysis on the basis of the local socioeconomic index quantitative inversion model based on the global noctilucent remote sensing and constructed by the fourth module according to the total night light intensity value of the global area of the year to be predicted to obtain the socioeconomic index prediction result of the local area of the corresponding year, and completing the prediction of the local socioeconomic development situation.

The specific implementation of each module can refer to the corresponding step, and the detailed description of the invention is omitted.

The foregoing is a more detailed description of the present invention, taken in conjunction with the accompanying examples, and it is not intended that the invention be limited to the specific embodiments described herein. It will be understood by those skilled in the art that various changes in detail may be effected therein without departing from the scope of the invention as defined by the appended claims.

Claims (8)

1. A local socioeconomic index prediction method based on global noctilucent remote sensing is characterized by comprising the following steps:

step 1, respectively taking a local area and a global area as target ranges, cutting out a noctilucent remote sensing image of the target range, and extracting the total SOL of nighttime light intensity values of the target range for a plurality of years;

step 2, extracting the social and economic indicators SEI of the local area for a plurality of years_Local；

Step 3, based on linear consistency assumption, judging global areaTotal amount of light intensity at night SOL_GlobalSum of night light intensity values SOL associated with local area_LocalAnd total amount of night light intensity values SOL of local area_LocaSocial and economic indicators SEI with local areas_LocalAnd whether there is a linear correlation that satisfies a preset condition threshold, includes the substeps of,

step 3.1, judging SOL_GlobalAnd SOL_LocalWhether linear correlation meeting the preset condition threshold exists or not, the correlation coefficient calculation formula is as follows,

$\mathrm{\&rho;}=\frac{\underset{i=1}{\overset{N}{\&Sigma;}}\&lsqb;{\left({\mathrm{SOL}}_{Local}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SOL}}_{Local}}\&rsqb;\&CenterDot;\&lsqb;{\left({\mathrm{SOL}}_{Global}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SOL}}_{Global}}\&rsqb;}{\sqrt{\underset{i=1}{\overset{N}{\&Sigma;}}{({\left({\mathrm{SOL}}_{Local}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SOL}}_{Local}})}^2\&CenterDot;\underset{i=1}{\overset{N}{\&Sigma;}}{({\left({\mathrm{SOL}}_{Global}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SOL}}_{Global}})}^2}},\mathrm{\&rho;}\&Element;\&lsqb;-1,1\&rsqb;$

wherein (SOL)_Local)_iIs the total light quantity in the local area at the ith year night,is the average value of the total amount of local area night light, (SOL)_Global)_iIs the light total amount in the ith year night in the global area,is the expectation of the total amount of night light in the global area; n represents the total number of years, and the value of i is 1,2, … and N;

step 3.2, judging SOL_LocalAnd SEI_LocalWhether linear correlation meeting the preset condition threshold exists or not, the correlation coefficient calculation formula is as follows,

$\mathrm{\&rho;}=\frac{\underset{i=1}{\overset{N}{\&Sigma;}}\&lsqb;{\left({\mathrm{SOL}}_{Local}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SOL}}_{Local}}\&rsqb;\&CenterDot;\&lsqb;{\left({\mathrm{SEI}}_{Local}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SEI}}_{Local}}\&rsqb;}{\sqrt{\underset{i=1}{\overset{N}{\&Sigma;}}{({\left({\mathrm{SOL}}_{Local}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SOL}}_{Local}})}^2\&CenterDot;\underset{i=1}{\overset{N}{\&Sigma;}}{({\left({\mathrm{SEI}}_{Local}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SEI}}_{Local}})}^2}},\mathrm{\&rho;}\&Element;\&lsqb;-1,1\&rsqb;$

wherein (SOL)_Local)_iIs the total light quantity in the local area at the ith year night,is the average value of the total amount of local area night light, (SEI)_Local)_iIs the i-th year socioeconomic index value in the local area,the expectation of socioeconomic index values in local areas is obtained;

step 4, when the linear correlation condition in the step 3.1 and the step 3.2 is established, a local socioeconomic index quantitative inversion model based on global noctilucent remote sensing is constructed for predicting the development situation of the local socioeconomic, and the method comprises the following substeps,

step 4.1, the following ideal model is established and parameter estimation is carried out,

SEI_Local＝A+B×SOL_Global

wherein A and B are estimated model parameters;

step 4.2, according to the model parameters estimated in the step 4.1, a local socioeconomic index quantitative inversion model based on global noctilucent remote sensing is constructed as follows,

SEI_Local＝A+B×SOL_Global+ζ,ζ～N(0,σ²)

where ζ is the overall random error after perturbation, N (0, σ)²) Is normally distributed, with a mean of 0 and a variance of σ;

and step 5, according to the total night light intensity value of the global area of the year to be predicted, performing prediction analysis based on the local socioeconomic index quantitative inversion model based on the global noctilucent remote sensing and constructed in the step 4 to obtain the socioeconomic index prediction result of the local area of the corresponding year, and completing the prediction of the development situation of the local socioeconomic.

2. The local socioeconomic indicator prediction method based on global noctilucent remote sensing according to claim 1, characterized in that: the preset condition threshold value is 0.8, and when | rho | is less than or equal to 1 in the condition of 0.8, the SOL is considered to be_GlobalAnd SOL_LocalOr SOL_LocalAnd SEI_LocalAre highly correlated.

3. The local socioeconomic indicator prediction method based on global noctilucent remote sensing according to claim 1 or 2, characterized in that: in step 1 and step 5, the implementation of extracting the total amount of the night light intensity value comprises the following substeps,

step 1.1, converting a geographical projection coordinate system of DMSP/OLS noctilucent remote sensing data into Labert equal-area projection to obtain a DMSP/OLS raster image;

step 1.2, cutting out a DMSP/OLS raster image map of a target range according to a vector boundary image layer of the target range;

$SOL=\underset{i=1}{\overset{n-1}{\&Sigma;}}{\left(DN\right)}_i\&times;M_i$

wherein n represents the number of pixel gray levels, DN_iBrightness value, M, representing picture elements of the ith level in the area_iRepresenting the total number of picture elements of the ith brightness level in the area, i being from 0 to n-1.

4. The local socioeconomic indicator prediction method based on global noctilucent remote sensing according to claim 3, characterized in that: and 5, obtaining a prediction result, wherein the prediction interval of 1-alpha is as follows:

wherein α is the significance level, SOL₀SOL of global region for satisfying correlation condition, i.e. total night light intensity value of global region for year to be predicted, SEI₀Is SOL ═ SOL₀The observed value represents the social and economic index of the local area of the year to be predicted;is SEI₀(ii) an estimation of socio-economic indicators prediction results (SOL) representing a local area of the year to be predicted₀) Is the uncertainty of the predicted value.

5. A local socioeconomic index prediction system based on global noctilucent remote sensing is characterized by comprising the following modules:

the first module is used for cutting out a noctilucent remote sensing image of a target range by taking a local area and a global area as the target range respectively, and extracting the total SOL of nighttime light intensity values of the target range for a plurality of years;

a second module for extracting the social economic indicators SEI of the local area for several years_Local；

A third module for determining the total amount SOL of night light intensity values in the global area based on the assumption of linear consistency_GlobalSum of night light intensity values SOL associated with local area_LocalAnd total amount of night light intensity values SOL of local area_LocaSocial and economic indicators SEI with local areas_LocalAnd whether there is a linear correlation satisfying a preset condition threshold, includes the following units,

unit 3.1 for judging SOL_GlobalAnd SOL_LocalWhether linear correlation meeting the preset condition threshold exists or not, the correlation coefficient calculation formula is as follows,

$\mathrm{\&rho;}=\frac{\underset{i=1}{\overset{N}{\&Sigma;}}\&lsqb;{\left({\mathrm{SOL}}_{Local}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SOL}}_{Local}}\&rsqb;\&CenterDot;\&lsqb;{\left({\mathrm{SOL}}_{Global}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SOL}}_{Global}}\&rsqb;}{\sqrt{\underset{i=1}{\overset{N}{\&Sigma;}}{({\left({\mathrm{SOL}}_{Local}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SOL}}_{Local}})}^2\&CenterDot;\underset{i=1}{\overset{N}{\&Sigma;}}{({\left({\mathrm{SOL}}_{Global}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SOL}}_{Global}})}^2}},\mathrm{\&rho;}\&Element;\&lsqb;-1,1\&rsqb;$

wherein (SOL)_Local)_iIs the total light quantity in the local area at the ith year night,is the average value of the total amount of local area night light, (SOL)_Global)_iIs the light total amount in the ith year night in the global area,is the expectation of the total amount of night light in the global area; n represents the total number of years, and the value of i is 1,2, … and N;

unit 3.2 for judging SOL_LocalAnd SEI_LocalWhether linear correlation meeting the preset condition threshold exists or not, the correlation coefficient calculation formula is as follows,

$\mathrm{\&rho;}=\frac{\underset{i=1}{\overset{N}{\&Sigma;}}\&lsqb;{\left({\mathrm{SOL}}_{Local}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SOL}}_{Local}}\&rsqb;\&CenterDot;\&lsqb;{\left({\mathrm{SEI}}_{Local}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SEI}}_{Local}}\&rsqb;}{\sqrt{\underset{i=1}{\overset{N}{\&Sigma;}}{({\left({\mathrm{SOL}}_{Local}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SOL}}_{Local}})}^2\&CenterDot;\underset{i=1}{\overset{N}{\&Sigma;}}{({\left({\mathrm{SEI}}_{Local}\right)}_i-\stackrel{\&OverBar;}{{\mathrm{SEI}}_{Local}})}^2}},\mathrm{\&rho;}\&Element;\&lsqb;-1,1\&rsqb;$

wherein (SOL)_Local)_iIs the total light quantity in the local area at the ith year night,is the average value of the total amount of local area night light, (SEI)_Local)_iIs the i-th year socioeconomic index value in the local area,the expectation of socioeconomic index values in local areas is obtained;

the fourth module is used for predicting the development situation of the local socioeconomic by constructing a local socioeconomic index quantitative inversion model based on global noctilucent remote sensing when the unit 3.1 and the unit 3.2 judge that the linear correlation condition is established, and comprises the following units,

unit 4.1, building the following ideal model and performing parameter estimation,

SEI_Local＝A+B×SOL_Global

wherein A and B are estimated model parameters;

a unit 4.2, according to the model parameters estimated by the unit 4.1, constructs a local social and economic index quantitative inversion model based on global noctilucent remote sensing as follows,

SEI_Local＝A+B×SOL_Global+ζ,ζ～N(0,σ²)

where ζ is the overall random error after perturbation, N (0, σ)²) Is normally distributed, with a mean of 0 and a variance of σ;

and the fifth module is used for carrying out prediction analysis on the basis of the local socioeconomic index quantitative inversion model based on the global noctilucent remote sensing and constructed by the fourth module according to the total night light intensity value of the global area of the year to be predicted to obtain the socioeconomic index prediction result of the local area of the corresponding year, and completing the prediction of the local socioeconomic development situation.

6. The local socioeconomic indicator prediction system based on global night light remote sensing of claim 5, wherein: the preset condition threshold value is 0.8, and when | rho | is less than or equal to 1 in the condition of 0.8, the SOL is considered to be_GlobalAnd SOL_LocalOr SOL_LocalAnd SEI_LocalAre highly correlated.

7. The local socioeconomic indicator prediction system based on global night-light remote sensing according to claim 5 or 6, characterized in that: in the first module and the fifth module, the implementation of extracting the total amount of the night light intensity value comprises the following units,

the unit 1.1 is used for converting a geographical projection coordinate system of the DMSP/OLS noctilucent remote sensing data into a Labert equal-area projection to obtain a DMSP/OLS raster image;

a unit 1.2, configured to cut out a DMSP/OLS raster image map of the target range according to the vector boundary layer of the target range;

$SOL=\underset{i=1}{\overset{n-1}{\&Sigma;}}{\left(DN\right)}_i\&times;M_i$

wherein n represents the number of pixel gray levels, DN_iBrightness value, M, representing picture elements of the ith level in the area_iRepresenting the total number of picture elements of the ith brightness level in the area, i being from 0 to n-1.

8. The local socioeconomic indicator prediction system based on global night light remote sensing of claim 7, wherein: the prediction interval of 1-alpha of the prediction result obtained by the fifth module is as follows:

wherein α is the significance level, SOL₀SOL of global region for satisfying correlation condition, i.e. year to be predictedGlobal area total night light intensity value, SEI₀Is SOL ═ SOL₀The observed value represents the social and economic index of the local area of the year to be predicted;is SEI₀(ii) an estimation of socio-economic indicators prediction results (SOL) representing a local area of the year to be predicted₀) Is the uncertainty of the predicted value.