Method for evaluating urban complex pollution exposure based on multi-source big data and early warning device

Abstract

The application discloses a kind of based on multi-source big data's city compound pollution exposure evaluation method and early warning device, the method is by building including high-precision satellite remote sensing data, ground monitoring station data and mobile phone signaling data in multi-source database, realize including personnel density, traffic capacity, land cover type, blue and green infrastructure area, building density / height and compound pollution concentration in multi-source heterogeneous data fusion analysis, on this basis, a kind of multi-factor weighted assignment city compound pollution exposure risk assessment method is proposed, the evaluation method is coded and transformed, form executable independent operation program, and develop a kind of portable device that can be used for risk real-time early warning.The application is by efficient analysis of the interactive correlation mechanism between city compound air pollution and personnel, traffic, land use, blue and green facilities, space structure and other multi-source influencing factors, to realize the accurate assessment and early warning of compound category air pollution exposure risk.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of urban pollution exposure assessment, and particularly relates to a method for urban complex pollution exposure assessment based on multi-source big data and a warning device. BACKGROUND

[0002] Nowadays, air pollution has become the largest human environmental health risk worldwide, causing about 9 million deaths each year, equivalent to one-sixth of the world's death toll. Air pollution is also believed to be closely related to many health risks and premature deaths, of which it has been proven that exposure to PM2.5 is more likely to cause chronic cardiovascular diseases, respiratory diseases and lung cancer, and excessive O3 exposure can increase the probability of chronic obstructive pulmonary disease.

[0003] Since the 21st century, China's industrial development and urbanization process have led to a large influx of population into cities, a sharp increase in population density, and rapid development of industrial enterprises, resulting in a sharp decline in urban ecological environment quality. The massive emission of automobile exhaust and industrial waste gas has made the problem of urban air pollution in China increasingly serious, and more and more people are exposed to different types of air pollution (PM2.5, O3, NO2, etc.), i.e. so-called urban complex air pollution exposure, which poses a greater threat to human health. Therefore, it is urgent to carry out research on urban air pollution (especially complex pollution) exposure assessment so as to fully understand the pollution exposure level.

[0004] At present, urban air pollution exposure assessment mainly relies on population census data and pollutant concentration data of monitoring stations, and the distribution of urban air pollution exposure level is obtained by mathematical modeling calculation and other methods. However, the generation and diffusion process of urban air pollution is extremely complex and often affected by many different categories of factors, including urban spatial structure, land use and development, road traffic, and blue-green infrastructure, etc. For example, high-density development and land use of building function-intensive land can effectively reduce the private car ownership rate and travel distance, improve the efficiency of public transportation, and further reduce vehicle pollution emissions.

[0005] Urban air pollution is the result of the joint action of urban spatial form and wind environment. The existence of high-density development and large buildings hinders air flow to some extent, which is easy to form a static wind area and aggravate air pollution accumulation. Urban green space, lakes and wetlands and other blue-green facilities are widely considered to be an important means of reducing air pollution concentration. Therefore, in order to efficiently achieve urban air pollution exposure assessment, it is necessary to fully consider multi-dimensional factors such as personnel, traffic, land use, blue-green facilities, spatial structure, etc., to obtain relevant data and deeply explore the complex correlation between each factor and urban air pollution, so as to establish a scientific and reliable exposure assessment method for real-time warning, etc.

[0006] However, the assessment of urban air pollution exposure still faces the following challenges:

[0007] 1) The data of various factors such as personnel, traffic, land use, blue-green facilities, and spatial structure come from a wide range of sources and have many types. Existing research obtains multi-source spatio-temporal data of various factors through satellite remote sensing and ground observation. The format is complex, the information is redundant, and the fusion is inefficient, making it difficult to achieve efficient data analysis. The complex relationship between various factors and urban pollution is often ignored, and the pollution exposure risk is seriously underestimated.

[0008] 2) The composition of urban complex pollution is complex, often showing non-uniform dynamic propagation and diffusion characteristics, and there are significant interaction mechanisms between various pollutants. Existing research mainly focuses on exposure assessment and risk warning for single-type pollutants, and there is no reliable technology or device for exposure assessment and warning of complex pollutants, which may lead to a decrease in the efficiency of urban pollution fine control.

[0009] Therefore, in view of the above problems, an effective method is needed to systematically assess the exposure level of urban complex air pollution by making full use of multi-source big data, an advanced technology. On this basis, a device for real-time warning of pollution risk is developed to provide a scientific tool for government management departments to carry out urban complex pollution control. SUMMARY

[0010] In view of the problems existing in the prior art, the present application provides a method for assessing the exposure of urban complex pollution based on multi-source big data and a warning device. The interactive correlation mechanism between urban complex air pollution and multi-source influencing factors such as personnel, traffic, land use, blue-green facilities, and spatial structure is efficiently analyzed to achieve accurate assessment and warning of the exposure risk of complex air pollution.

[0011] To solve the above technical problems, the present application realizes the following technical scheme:

[0012] A method for assessing the exposure of urban complex pollution based on multi-source big data, comprising:

[0013] Step 1) Select a target area and divide its urban map into grids. The smallest grid unit obtained after grid division is used as the grid unit map for personnel density distribution calculation and pollution exposure assessment;

[0014] Step 2) Obtain personnel positioning (mobile phone signaling) data and population census data of the target area, and calculate the population density distribution data of each grid unit map in the target area;

[0015] Step 3) Obtain land satellite remote sensing high-resolution data of the target area, and calculate the traffic capacity distribution data, land cover type distribution data, blue-green infrastructure area data, and building density / height data of each unit grid map in the target area respectively based on the data;

[0016] Step 4) Obtain ground monitoring station data of the target area, and calculate the composite pollution concentration high-resolution distribution data of each unit grid map in the target area based on the land satellite remote sensing high-resolution data;

[0017] Step 5) Based on the calculated population density distribution data, traffic capacity data, land cover type data, blue-green infrastructure area data, building density / height data, and composite pollution concentration high-resolution distribution data, use the multi-source relationship data fusion (MSF) framework to build a multi-source database, and perform deep analysis of multi-source heterogeneous data to obtain a dimensionless multi-source database;

[0018] Step 6) According to the dimensionless multi-source database, extract urban characteristic factors of traffic capacity, land cover type, blue-green infrastructure area, and building density / height, then calculate the population density distribution data of each type of characteristic factor after weighting processing, and combine the dimensionless composite pollution concentration high-resolution distribution data to calculate the cumulative composite pollution concentration, and finally calculate the composite pollution exposure risk of the target area.

[0019] Further, in step 1, the mesh division technology based on ArcGIS is used to realize the mesh division of the city map of the target area, and the minimum mesh unit size of the city map of the target area after mesh division is 1km×1km.

[0020] Further, in step 2, the calculation method of the population density distribution data of each unit grid map in the target area is as follows:

[0021] First, the personnel positioning (mobile phone signaling) data and population census data of the target area are used as influencing factors to calculate the distance of each grid unit map to the influencing factors, and the distance data is classified according to 1 / 4 standard deviation (determining the number of classifications) and quantile (determining the range of each classification);

[0022] Then, according to the importance of different influencing factors (importance ranking: personnel positioning data > population census data), each distance data after classification is given a corresponding weight;

[0023] Finally, according to each distance data and the corresponding weight coefficient, the population density distribution data of each unit grid map in the target area is calculated.

[0024] Further, in step 3, the calculation methods of the traffic capacity distribution data, the land cover type distribution data, the blue-green infrastructure area data and the building density / height data of each unit grid map in the target area are as follows:

[0025] 1) The calculation method of the traffic capacity data is:

[0026] According to the characteristics of vehicles in the image, the texture feature extraction is performed on the land satellite remote sensing high-resolution data (satellite image) of the target area, the Local Binary Pattern (LBP) is calculated to obtain a texture feature image, and then the vehicles are classified by using a support vector machine, and the traffic capacity data of each unit grid map in the target area is calculated according to different vehicle types;

[0027] 2) The calculation method of the land cover type distribution data is:

[0028] Firstly, the GF-1 wide multispectral data, MODIS data and national forest resource continuous investigation fixed plot data are obtained through the land satellite remote sensing high-resolution data (satellite image) of the target area; then the obtained GF-1 wide multispectral data, MODIS data and national forest resource continuous investigation fixed plot data are preprocessed, including radiation calibration, geometric correction and projection conversion; then based on the principle of multi-scale segmentation, the preprocessed GF-1 wide multispectral data, MODIS data and national forest resource continuous investigation fixed plot data are segmented, and the features including spectrum, texture and shape are extracted; finally, the random forest algorithm is used for feature selection, and the CART algorithm is used for training and classification, and the land cover type distribution data of each unit grid map in the target area is obtained;

[0029] 3) The calculation method of the blue-green infrastructure area data is:

[0030] According to the spectral curve characteristics and experiments, the appropriate judgment threshold is determined by using the NDVI and MNDWI calculation formulas, and the blue-green infrastructure is extracted based on the land satellite remote sensing high-resolution data (satellite image) of the target area, and the blue-green infrastructure area data of each unit grid map in the target area is calculated;

[0031] 4) The calculation method of the building density / height data is:

[0032] By using the imaging geometric model of buildings and shadows, the building density / height data of each unit grid map in the target area is calculated by using a single high-resolution satellite remote sensing image in the land satellite remote sensing high-resolution data of the target area.

[0033] Further, in step 4, the calculation method of the composite pollution concentration high-resolution distribution data of each unit grid map in the target area is:

[0034] Through satellite remote sensing technology, the PM2.5, O3 and NO2 concentration fields of the target area are extracted, the diffusion distance of adjacent grid maps in the concentration field is calculated based on the divided grid map, the diffusion distance surface is obtained, and then the shortest path distance between each grid map and the ground monitoring station in the study area is calculated. Combined with the pollution monitoring data, the inverse distance weighted interpolation is carried out to realize the high-resolution interpolation of different types of pollutants, and finally the high-resolution distribution data of composite pollution concentration is obtained according to the distribution results of different types of pollution concentration.

[0035] Further, in step 5, the construction method of the dimensionless multi-source database is:

[0036] Firstly, the attribute data including personnel density distribution data, traffic capacity data, land cover type data, blue-green infrastructure area data, building density / height data and composite pollution concentration high-resolution distribution data are extracted to measure the similarity between the attribute data, the similarity distance is solved and the distance matrix is formed, and then the best matching result is found based on the obtained distance matrix, so that the sum of the distances between the matching attributes of all attribute data is minimized, that is, the preliminary screened multi-source database is obtained. Then, based on the preliminary screened multi-source database, the multi-source heterogeneous data deep analysis including multi-source data cleaning and dimensionless processing is realized through the data cleaning method based on dynamic configurable rules and the range standardization method, so as to obtain the dimensionless multi-source database; wherein,

[0037] 1) The specific steps of realizing multi-source data cleaning by using the data cleaning method based on dynamic configurable rules are:

[0038] The missing values are filled, the median of the same type of data is selected as the filling value, the standard deviation of the noise data is detected, the data consistency is further checked, that is, whether the data conforms to the pre-defined format is checked, and finally the redundant data detection is realized according to the similarity calculation;

[0039] 2) The range standardization method is used to realize the dimensionless processing of multi-source data, that is, the original data is mapped to the [0, 1] interval through linear transformation, so that data of different orders of magnitude can be compared and weighted;

[0040] Based on the above data analysis process, the dimensionless multi-source database is obtained, which includes dimensionless personnel density distribution data, dimensionless traffic capacity data, dimensionless land cover type data, dimensionless blue-green infrastructure area data, dimensionless building density / height data and dimensionless composite pollution concentration high-resolution distribution data.

[0041] Furthermore, in step 6, the method for assessing the risk of combined pollution exposure in the target area is as follows:

[0042] First, based on dimensionless data from a multi-source database of traffic capacity, land cover type, blue-green infrastructure area, and building density / height, urban characteristic factors for each factor are extracted using the entropy method. Then, these characteristic factors are used as weighting coefficients and multiplied by dimensionless population density distribution data to obtain weighted population density distribution data for each characteristic factor. Next, based on this weighted population density distribution data and combined with high-resolution distribution data of dimensionless compound pollution concentrations, the cumulative compound pollutant concentration is calculated. Finally, using the relative mortality rate calculation method from epidemiology, combined with the cumulative compound pollutant concentration, the compound pollution exposure risk of the target area is calculated.

[0043] An early warning device for urban compound pollution exposure risk includes a map display screen, a text display screen, and a switch mounted on the front of a housing; a hook mounted on the back of the housing; a wireless data receiver mounted on the side wall of the housing; and a processor, a power supply, and a memory mounted inside the housing.

[0044] The wireless data receiver is responsible for sending personnel location data to the backend, and for receiving the composite pollution exposure risk corresponding to the personnel's location calculated by the backend using the aforementioned urban composite pollution exposure assessment method based on multi-source big data.

[0045] The processor is responsible for combining the city grid coordinates to perform linear interpolation fitting on the received composite pollution exposure risk values ​​corresponding to the location of the person, to obtain a high-resolution composite pollution exposure risk distribution map and output it; and is also responsible for comparing the composite pollution exposure risk of the person's location with the set risk threshold based on the high-resolution composite pollution exposure risk distribution map, to obtain the comparison result and output it.

[0046] The map display screen is responsible for displaying a high-resolution composite pollution exposure risk distribution map output by the calculator;

[0047] The text display screen is responsible for displaying the comparison result between the combined pollution exposure risk of the personnel's location output by the calculator and the set risk threshold; when the combined pollution exposure risk of the personnel's location is greater than the set risk threshold, the text "Pollution Severely Exceeds Standard" is displayed; when the combined pollution exposure risk of the personnel's location is equal to the set risk threshold, the text "Pollution Exceeds Standard" is displayed; when the combined pollution exposure risk of the personnel's location is less than the set risk threshold, the text "Pollution Does Not Exceed Standard" is displayed.

[0048] The memory is responsible for storing the set risk threshold, the obtained personnel positioning data, the received composite pollution exposure risk value corresponding to the location of the personnel, the fitted high-resolution composite pollution exposure risk distribution map, and the comparison result of the composite pollution exposure risk of the location of the personnel and the set risk threshold.

[0049] The power supply is responsible for powering the operation device, the wireless data receiver, the map display screen, the text display screen and the memory.

[0050] The switch is responsible for the on-off of the power supply.

[0051] The hook is convenient for detachable connection with the personnel clothing.

[0052] A computer device comprises a processor, a memory, a communication interface and a communication bus, the processor, the memory and the communication interface complete communication with each other through the communication bus, the memory is used for storing at least one executable instruction, and the executable instruction makes the processor execute the operation corresponding to the above-mentioned urban composite pollution exposure evaluation method based on multi-source big data.

[0053] A computer readable storage medium, the computer storage medium stores at least one executable instruction, and the executable instruction makes the processor execute the operation corresponding to the above-mentioned urban composite pollution exposure evaluation method based on multi-source big data.

[0054] Compared with the prior art, the beneficial effects of the present application are:

[0055] 1. The present application constructs a multi-source database effectively fusing high-precision satellite remote sensing data, ground monitoring station data and mobile phone signaling data, realizes efficient fusion and analysis of multi-source heterogeneous data including personnel density, traffic capacity, land cover type, blue-green infrastructure area, building density and height, and composite pollutant concentration, and solves the problem of complex format, large-scale data and difficult lightweight analysis.

[0056] 2. The present application combines personnel positioning (mobile phone signaling) data and population census data to model and calculate the real-time distribution of personnel density, and considers different time periods (working days and non-working days, morning peak, evening peak and other time periods) to distinguish and consider the composite pollution exposure risk, thereby providing more accurate and reliable high-resolution personnel density distribution data for urban composite pollution exposure risk assessment.

[0057] 3. The application proposes a multi-factor (traffic capacity, land cover type, blue-green infrastructure area, and building density and height) weighted composite pollution exposure risk assessment method, extracts urban characteristic factors and calculates the cumulative composite pollution concentration, then introduces the relative risk mortality rate calculation method of epidemiology, and builds an evaluation model to scientifically and effectively quantify the exposure risk of different types of pollution.

[0058] 4. The application develops a portable device that can be used for real-time warning of composite pollution exposure risk, which can dynamically warn the pollution exposure risk of any personnel position in the city, not only provides an effective tool for urban residents to travel and take relevant protective measures, but also provides valuable data sources for urban planners and decision-makers, and provides important guidance for future urban development and public health policy making.

[0059] The above description is only a summary of the technical solutions of the application, in order to more clearly understand the technical means of the application, and can be implemented according to the content of the specification, the following will be explained in detail with the preferred embodiments of the application and the accompanying drawings. The specific embodiments of the application are given in detail by the following examples and their accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0060] The drawings described herein are used to provide further understanding of the application, and form a part of the application. The schematic embodiments of the application and their descriptions are used to explain the application, and do not constitute an improper limitation on the application. In the drawings:

[0061] Figure 1 The above description is only a summary of the technical solutions of the application, in order to more clearly understand the technical means of the application, and can be implemented according to the content of the specification, the following will be explained in detail with the preferred embodiments of the application and the accompanying drawings. The specific embodiments of the application are given in detail by the following examples and their accompanying drawings.

[0062] Figure 2 The above description is only a summary of the technical solutions of the application, in order to more clearly understand the technical means of the application, and can be implemented according to the content of the specification, the following will be explained in detail with the preferred embodiments of the application and the accompanying drawings. The specific embodiments of the application are given in detail by the following examples and their accompanying drawings.

[0063] Figure 3 The above description is only a summary of the technical solutions of the application, in order to more clearly understand the technical means of the application, and can be implemented according to the content of the specification, the following will be explained in detail with the preferred embodiments of the application and the accompanying drawings. The specific embodiments of the application are given in detail by the following examples and their accompanying drawings.

[0064] Figure 4 The above description is only a summary of the technical solutions of the application, in order to more clearly understand the technical means of the application, and can be implemented according to the content of the specification, the following will be explained in detail with the preferred embodiments of the application and the accompanying drawings. The specific embodiments of the application are given in detail by the following examples and their accompanying drawings.

[0065] Figure 5 The above description is only a summary of the technical solutions of the application, in order to more clearly understand the technical means of the application, and can be implemented according to the content of the specification, the following will be explained in detail with the preferred embodiments of the application and the accompanying drawings. The specific embodiments of the application are given in detail by the following examples and their accompanying drawings.

[0066] Figure 6 The above description is only a summary of the technical solutions of the application, in order to more clearly understand the technical means of the application, and can be implemented according to the content of the specification, the following will be explained in detail with the preferred embodiments of the application and the accompanying drawings. The specific embodiments of the application are given in detail by the following examples and their accompanying drawings.

[0067] Figure 7 The back view of the portable device for real-time early warning of composite pollution exposure risk according to the present application;

[0068] Figure 8 The internal view of the portable device for real-time early warning of composite pollution exposure risk according to the present application. DETAILED DESCRIPTION

[0069] The preferred embodiments of the present application will be described in detail below with reference to the attached drawings, so as to more clearly understand the purpose, features and advantages of the present application. It should be understood that the embodiments shown in the drawings are not a limitation on the scope of the present application, but are only to illustrate the essential spirit of the technical solutions of the present application.

[0070] In the following description, for the purpose of explaining various disclosed embodiments, certain specific details are set forth in order to provide a thorough understanding of various disclosed embodiments. However, one skilled in the relevant arts will recognize that embodiments can be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, structures, and techniques associated with the present application are not shown or described in order to avoid unnecessarily obscuring the description of the embodiments.

[0071] Unless the context clearly requires otherwise, throughout the description and the claims, the words "comprise," "comprising," and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is to say, in the sense of "including, but not limited to." Additionally, the words "herein," "above," and words of similar import, when used in this application, shall not be understood to refer to this application prior to the filing date of this application only, but should be construed to cover the description from the beginning through the present application.

[0072] Reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of the phrase "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics can be combined in any suitable manner in one or more embodiments.

[0073] As used in this specification and the appended claims, the singular forms "a," "an," and "the" include plural referents unless the content clearly dictates otherwise. It should be noted that the term "comprising" as used in this specification and the appended claims is to be construed as meaning "including, but not limited to."

[0074] Furthermore, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as there is no conflict.

[0075] The application provides a city composite pollution exposure evaluation method based on multi-source big data.

[0076] The application first establishes a model for identifying real-time distribution of personnel density based on mobile signaling data and population census data. The model first performs mesh division on the city map of the selected target area based on the mesh division function of ArcGIS, and the minimum mesh unit obtained after mesh division is used as the mesh unit map for personnel density distribution calculation and pollution exposure evaluation, and the size of the minimum mesh unit is 1km*1km. The model then takes the personnel positioning (mobile signaling) data and population census data of the target area as influencing factors, calculates the distance from each mesh unit map to the influencing factors, classifies the distance data according to 1 / 4 standard deviation (determining the number of classifications) and quantile (determining the range of each classification), then according to the importance of different influencing factors (importance ranking: personnel positioning data>population census data), assigns corresponding weights to each distance data after classification, and finally calculates the population density distribution data of each unit mesh map in the target area according to each distance data and the corresponding weight coefficient. The calculation formula is as follows:

[0077]

[0078] In formula (1), P i represents the population density of the i-th city mesh unit, ω j represents the weight of the j-th influencing factor, f(dij) represents the distance function of the i-th mesh unit to the j-th influencing factor, and n represents the total number of factors.

[0079] The application further establishes a traffic capacity, land cover type, blue-green infrastructure area, building density / height extraction algorithm based on land satellite remote sensing high-resolution data. By obtaining the land satellite remote sensing high-resolution data of the target area, the traffic capacity distribution data, land cover type distribution data, blue-green infrastructure area data and building density / height data of each unit mesh map in the target area are calculated.

[0080] 1) The calculation method of the traffic capacity data is:

[0081] According to the characteristics of the vehicle in the image, texture feature extraction is performed on the land satellite remote sensing high-resolution data (satellite image) of the target area, a Local Binary Pattern (LBP) is calculated to obtain a texture feature image, and a support vector machine is used for classification of the vehicle, and traffic capacity data of each unit grid map in the target area is calculated according to different vehicle types;

[0082] 2) The calculation method of the land cover type distribution data is:

[0083] First, GF-1 wide multispectral data, MODIS data, and national forest resource continuous inventory fixed plot data are obtained from the land satellite remote sensing high-resolution data (satellite image) of the target area; then the obtained GF-1 wide multispectral data, MODIS data, and national forest resource continuous inventory fixed plot data are preprocessed, including radiation calibration, geometric correction, and projection conversion; then based on the principle of multi-scale segmentation, the preprocessed GF-1 wide multispectral data, MODIS data, and national forest resource continuous inventory fixed plot data are image segmented, and features including spectrum, texture, and shape are extracted; finally, the random forest algorithm is used for feature selection, and the CART algorithm is used for training and classification, and the land cover type distribution data of each unit grid map in the target area is obtained.

[0084] 3) The calculation method of the blue-green infrastructure area data is:

[0085] According to the spectral curve characteristics and experiments, appropriate judgment thresholds are determined by using the NDVI and MNDWI calculation formulas, and the blue-green infrastructure is extracted based on the land satellite remote sensing high-resolution data (satellite image) of the target area, and the blue-green infrastructure area data of each unit grid map in the target area is calculated.

[0086] The calculation formulas of NDVI and MNDWI are:

[0087]

[0088] In formula (2) and formula (3), NDVI is the normalized vegetation index, MNDWI is the improved normalized difference water body index, NIR is the reflectance value of the near-infrared band, R is the reflectance value of the red light band, MIR is the reflectance value of the middle infrared band, and Green is the reflectance value of the green light band.

[0089] 4) The calculation method of the building density / height data is:

[0090] The building density / height data of each unit grid map in the target area is calculated by using a single high-resolution satellite remote sensing image in the high-resolution satellite remote sensing data of the target area through the imaging geometric model of the building and the shadow.

[0091] The application further provides a composite pollution concentration high-resolution interpolation method combining high-precision satellite images and ground monitoring station data.

[0092] The calculation formula of the shortest path distance between the grid unit map and the ground monitoring station is:

[0093] W i =cos(D i -DM k )×V i -sgn[cos(D i -DM k )] (4);

[0094] In formula (4), W i represents the shortest path distance between the i th grid unit and the ground monitoring station, D i represents the position of the i th grid unit, DM k represents the position of the k th ground monitoring station, and V i represents the pollution concentration of the i th grid unit.

[0095] The calculation formula of the pollution concentration after the interpolation processing is:

[0096]

[0097] In formula (5), Z R represents the R th pollution concentration after the interpolation processing, VM k represents the pollution concentration of the k th ground monitoring station, and a is a distance attenuation parameter.

[0098] Based on the calculated personnel density distribution data, traffic capacity data, land cover type data, blue-green infrastructure area data, building density / height data and composite pollution concentration high-resolution distribution data, the application constructs a multi-source database using a general multi-source relationship data fusion (MSF) framework. First, the attribute data including personnel density distribution data, traffic capacity data, land cover type data, blue-green infrastructure area data, building density / height data and composite pollution concentration high-resolution distribution data are feature extracted to measure the similarity between the attribute data, the similarity distance is solved and a distance matrix is formed, and then the best matching result is found based on the obtained distance matrix, so that the sum of the distances between the matching attributes of all attribute data is minimized, that is, the preliminary screened multi-source database is obtained.

[0099] Next, based on the preliminary screened multi-source database, the multi-source heterogeneous data deep analysis including multi-source data cleaning and dimensionless processing is realized through the data cleaning method based on dynamic configurable rules and the range standardization method, so as to obtain the dimensionless form multi-source database. Among them,

[0100] The specific steps of realizing multi-source data cleaning by using the data cleaning method based on dynamic configurable rules are as follows:

[0101] The missing values are filled, the median of the same type of data is selected as the filling value, the standard deviation of the noise data is detected, the data consistency is further checked, that is, whether the data conforms to the predefined format is checked, and finally the redundant data detection is realized according to the similarity calculation;

[0102] The standard deviation calculation formula is:

[0103]

[0104] In formula (6), sigma is the standard deviation, X is the value of the data, and mu is the mean value. i

[0105] The similarity calculation formula is:

[0106]

[0107] In formula (7), Sim is the similarity of two data records, X and X are the attribute values of two k-type data. ik jk

[0108] The range standardization method is used to realize the dimensionless processing of multi-source data, that is, the original data is mapped to the [0, 1] interval through linear transformation, so that data of different orders of magnitude can be compared and weighted, and the specific steps are as follows:

[0109] ​​​First, find the maximum and minimum value in each category of data, and then according to the following formula for dimensionless processing:

[0110]

[0111] In formula (8), X ik represent the data processed by range method, A k represent the maximum value in each category of data, B k represent the minimum value in each category of data.

[0112] Based on the above data analysis process, the dimensionless processed multi-source database is obtained, including dimensionless personnel density distribution data, dimensionless traffic capacity data, dimensionless land cover type data, dimensionless blue-green infrastructure area data, dimensionless building density / height data, and dimensionless complex pollution concentration high-resolution distribution data.

[0113] On the basis of multi-source heterogeneous data fusion analysis, the application also provides a multi-factor weighted urban complex pollution exposure risk assessment method, which extracts the urban characteristic factors of traffic capacity, land cover type, blue-green infrastructure area and building density / height according to the dimensionless multi-source database, then calculates the weighted personnel density distribution data of each characteristic factor, and then combines the dimensionless complex pollution concentration high-resolution distribution data to calculate the cumulative complex pollution concentration, and finally calculates the complex pollution exposure risk of the target area.

[0114] The assessment method of the complex pollution exposure risk of the target area is:

[0115] First, according to the dimensionless data corresponding to the traffic capacity, land cover type, blue-green infrastructure area, building density / height of each factor in the dimensionless multi-source database, the urban characteristic factors of each factor are extracted by using entropy method, and the calculation formula is as follows:

[0116]

[0117] g j =1-e j (11);

[0118]

[0119] In formula (9)-(13), P ij is the proportion of the i th data in the j th factor, Z ij is the dimensionless data, n is the number of data samples, e j is the entropy value of the j th factor, g j is the difference coefficient of the j th factor, and ω jis the weight of the jth factor, m is the number of factors, and F is the value of the urban feature factor. Based on the above steps, the index weight is determined by calculating the entropy value of each type of factor, thereby extracting the urban feature factor.

[0120] Then, the feature factor corresponding to each type of factor is multiplied by the dimensionless personnel density distribution data as a weight coefficient, thereby obtaining the personnel density distribution data processed by each type of feature factor, and the calculation formula is as follows:

[0121] pop = TR x F (14);

[0122] In formula (14), pop represents the personnel density distribution data processed by the weight, TR is the dimensionless personnel density data, and F is the value of the urban feature factor.

[0123] Next, based on the obtained personnel density distribution data processed by each type of feature factor, the high-resolution distribution data of the dimensionless composite pollution concentration is combined to calculate the cumulative composite pollution concentration, and the calculation formula is as follows:

[0124]

[0125] In formula (15) and formula (16), PWE represents the cumulative composite pollution concentration, PC mn represents the concentration of the mth type of pollutant in the nth grid cell, pop dn represents the weighted personnel density data of the nth grid cell on weekdays, pop wn represents the weighted personnel density data of the nth grid on non-working days, D dm and D wm represent the number of weekdays and non-working days, respectively, when the concentration of the mth type of pollutant is higher than the concentration threshold, pop c represents the average weighted personnel density data, d d and d w represent the number of weekdays and non-working days, respectively, and d represents the total number of days.

[0126] Finally, the relative mortality rate calculation method of epidemiology is used in combination with the cumulative composite pollution concentration to calculate the composite pollution exposure risk of the target area, and the calculation formula is as follows:

[0127] RR = β x PWE (17);

[0128]

[0129] In formula (17) and formula (18), RR represents the relative mortality risk rate, β represents the relative mortality rate corresponding to the composite pollution, and the value is 1.02 x 10 -1 , Mort represents the exposure risk, and y0 represents the baseline mortality rate, which is the all-cause mortality rate, and the value is 6.14 x 10-3 can be used to assess the comprehensive health effects of air pollution on diseases including cardiovascular disease, lung cancer, chronic bronchitis, acute bronchitis and asthma attacks.

[0130] Referring to Figures 6-8 As shown, according to the coding transformation of the urban composite pollution exposure risk assessment method, an executable independent operation program is formed, and the present application further proposes a warning device for urban composite pollution exposure risk. The device includes a map display screen 1, a text display screen 2 and a switch 3 arranged on the front of the shell, a hook 5 arranged on the back of the shell, a wireless data receiver 4 arranged on the side wall of the shell, and an operator 6, a power supply 7 and a storage 8 arranged inside the shell. Among them,

[0131] The wireless data receiver 4 is responsible for sending personnel positioning (mobile phone signaling) data to the background, and is responsible for receiving the composite pollution exposure risk corresponding to the location of the personnel calculated by the background using the above-mentioned urban composite pollution exposure assessment method based on multi-source big data.

[0132] The operator 6 is responsible for combining the urban grid coordinates to perform linear interpolation fitting on the composite pollution exposure risk value corresponding to the location of the personnel received, to obtain a high-resolution composite pollution exposure risk distribution map and output it; and is responsible for comparing the composite pollution exposure risk of the location of the personnel with the set risk threshold based on the high-resolution composite pollution exposure risk distribution map, to obtain a comparison result and output it.

[0133] The map display screen 1 is responsible for displaying the high-resolution composite pollution exposure risk distribution map output by the operator 6.

[0134] The text display screen 2 is responsible for displaying the comparison result of the composite pollution exposure risk of the location of the personnel with the set risk threshold output by the operator 6.

[0135] The storage 8 is responsible for storing the set risk threshold, the obtained personnel positioning (mobile phone signaling) data, the received composite pollution exposure risk value corresponding to the location of the personnel, the fitted high-resolution composite pollution exposure risk distribution map, and the calculated comparison result of the composite pollution exposure risk of the location of the personnel with the set risk threshold.

[0136] The power supply 7 is responsible for powering the operator 6, the wireless data receiver 4, the map display screen 1, the text display screen 2 and the storage 8.

[0137] The switch 3 is responsible for the on-off of the power supply 7.

[0138] The hook 5 is convenient for detachable connection with the personnel's clothes.

[0139] The working method of the early warning device for urban complex pollution exposure risk of the application is as follows:

[0140] According to the personnel positioning (mobile phone signaling) data, the complex pollution exposure risk value corresponding to the position of the personnel is input into the operator, linear interpolation fitting is performed in combination with the urban grid coordinates, a high-resolution complex pollution exposure risk distribution map is obtained, and the map is transmitted to the screen display device for real-time display.

[0141] According to different time periods (morning peak, evening peak, and other time periods) of weekdays and non-weekdays, corresponding complex pollution risk thresholds are set, which are input into the memory.

[0142] Based on the high-resolution complex pollution exposure risk distribution map, the complex pollution exposure risk of the position of the personnel is compared with the set risk threshold in the operator, and the comparison result is saved.

[0143] The comparison result is input into the screen display device, when the complex pollution exposure risk of the position of the personnel is greater than the set risk threshold, "pollution is seriously over-standard" is displayed; when the complex pollution exposure risk of the position of the personnel is equal to the set risk threshold, "pollution has been over-standard" is displayed; when the complex pollution exposure risk of the position of the personnel is less than the set risk threshold, "pollution has not been over-standard" is displayed.

[0144] The following will take the urban complex pollution exposure assessment and early warning based on Nanjing as a specific embodiment to specifically describe the urban complex pollution exposure assessment method and early warning device based on multi-source big data of the application, but the implementation manner of the application is not limited to this.

[0145] The complex pollution species involved in this embodiment include PM2.5, O3, and NO2 (unit: μg / m 3 The pollution exposure risk assessment and dynamic early warning are performed at a frequency of every hour, and the time span is from May 27, 2021 to May 31, 2021, and the specific implementation process is as follows.

[0146] 1. Select the central area of Nanjing and the surrounding areas as the research area, divide the area into grids by using the fishing net division function of ArcGIS, realize the minimum grid unit size of 1 km x 1 km, and take it as the grid unit map for personnel density distribution calculation and pollution exposure assessment.

[0147] 2. The personnel positioning (mobile phone signaling) data and the population census data are used as the influence factors to calculate the distance of each grid unit to the influence factor, the distance data is classified according to 1 / 4 standard deviation and quantile, and then according to the importance of different influence factors (importance ranking: personnel positioning data > population census data), a weight is assigned to each classification, and the population density distribution data is calculated according to the distance data and the weight coefficient.

[0148] 3. Based on high-resolution satellite remote sensing data, traffic capacity distribution data in the study area is obtained by local binary pattern algorithm and support vector machine, land cover type distribution data is extracted by random forest and CART algorithm, area distribution data of blue-green infrastructure is extracted by combining NDVI and MNDWI calculation formula, and building density distribution data is calculated according to the geometric model of building shadow and imaging, as shown in Figure 1 .

[0149] 4. The concentration field of PM2.5, O3 and NO2 in the study area is extracted by satellite remote sensing technology, the diffusion distance of adjacent grid cells in the concentration field is calculated based on the grid map, and the shortest path distance between the grid cells and the ground monitoring station in the study area (as shown in Figure 2 ) is further calculated, combined with the distance data and pollution monitoring data, different types of pollution concentration high-resolution interpolation is realized.

[0150] 5. Based on the above high-resolution data of personnel density distribution, traffic capacity, land cover type, blue-green infrastructure area data, building density, pollutant concentration, etc., a multi-source database is constructed, and multi-source heterogeneous data deep analysis (including data cleaning and dimensionless processing) is realized by dynamic configurable rule data cleaning method and range standardization method, to obtain a dimensionless multi-source database.

[0151] 6. According to the dimensionless multi-source database, the characteristic factors of traffic, land, blue-green infrastructure and building density are extracted by entropy method (0.12, 0.17, 0.55, 0.16 respectively), and the characteristic factors corresponding to each influencing factor are taken as weight coefficients, multiplied by the dimensionless personnel density distribution data, to obtain the weighted personnel density distribution data, as shown in Figure 3 , Figure 3 is the weighted personnel density distribution result (from May 27, 2021 to May 31, 2021, at 10:00 every day).

[0152] 7. Based on the weighted personnel density distribution data, combined with the high-resolution distribution data of dimensionless complex pollution concentration, the cumulative complex pollution concentration is calculated, as shown in Figure 4 .

[0153] 8. According to the relative mortality rate calculation method, combined with the cumulative complex pollution concentration, the complex pollution exposure risk in the study area is obtained, as shown in Figure 5 , Figure 5 is the exposure risk quantitative evaluation result.

[0154] 9. The complex pollution exposure risk evaluation result is input into Figure 6The operation unit of the portable early warning device obtains a high-resolution composite pollution exposure risk map (displayed through a screen display device), and according to the position of the personnel, the corresponding composite pollution exposure risk is matched and compared with the set risk threshold value. When greater than the set risk threshold value, "pollution seriously exceeds the standard" is displayed; when equal to the set risk threshold value, "pollution has exceeded the standard" is displayed; and when less than the set risk threshold value, "pollution has not exceeded the standard" is displayed.

[0155] The application further provides a computer device, comprising a processor, a memory, a communication interface and a communication bus, the processor, the memory and the communication interface complete communication with each other through the communication bus, the memory is used for storing at least one executable instruction, and the executable instruction makes the processor execute the operation corresponding to the urban composite pollution exposure evaluation method based on multi-source big data.

[0156] The application further provides a computer readable storage medium, and the computer storage medium stores at least one executable instruction, and the executable instruction makes the processor execute the operation corresponding to the urban composite pollution exposure evaluation method based on multi-source big data.

[0157] The above only describes the preferred embodiments of the application and is not used to limit the application, and the application can have various changes and variations for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the application shall be included in the protection scope of the application.

Claims

1. A method for urban complex pollution exposure assessment based on multi-source big data, characterized in that, The method comprises the following steps: Step 1) selecting a target area and performing grid division on the urban map of the target area, and taking the minimum grid unit obtained after the grid division as a grid unit map for personnel density distribution calculation and pollution exposure evaluation; Step 2) obtaining personnel positioning data and population census data of the target area, and calculating population density distribution data of each grid unit map in the target area; Step 3) obtaining land satellite remote sensing high-resolution data of the target area, and calculating traffic capacity distribution data, land cover type distribution data, blue-green infrastructure area data and building density / height data of each unit grid map in the target area respectively; Step 4) obtaining ground monitoring station data of the target area, and combining the land satellite remote sensing high-resolution data to calculate composite pollution concentration high-resolution distribution data of each unit grid map in the target area; Step 5) based on the calculated personnel density distribution data, traffic capacity data, land cover type data, blue-green infrastructure area data, building density / height data and composite pollution concentration high-resolution distribution data, a multi-source database is constructed by using a multi-source relationship data fusion framework, and multi-source heterogeneous data is deeply analyzed to obtain a dimensionless form multi-source database; Step 6) according to the dimensionless form multi-source database, urban characteristic factors of various factors such as traffic capacity, land cover type, blue-green infrastructure area and building density / height are extracted, then the personnel density distribution data after weighted processing of various characteristic factors is calculated, and then combined with the dimensionless composite pollution concentration high-resolution distribution data, the cumulative composite pollution concentration is calculated, and finally the composite pollution exposure risk of the target area is calculated. 2.The method of claim 1, wherein, In step 1, the grid division of the urban map of the target area is realized by using the fishing net division technology based on ArcGIS, and the size of the minimum grid unit of the urban map of the target area after the grid division is 1km*1km. 3.The method of claim 1, wherein, In step 2, the calculation method of the population density distribution data of each unit grid map in the target area is as follows: Firstly, taking the personnel positioning data and population census data of the target area as influence factors, the distance of each grid unit map to the influence factor is calculated, and the distance data is classified according to 1 / 4 standard deviation and quantile; Then, according to the importance of different influence factors, each distance data after classification is given a corresponding weight; Finally, according to each distance data and the corresponding weight coefficient, the population density distribution data of each unit grid map in the target area is calculated. 4.The method of claim 1, wherein, In step 3, the calculation methods of the traffic capacity distribution data, the land cover type distribution data, the blue-green infrastructure area data and the building density / height data of each unit grid map in the target area are as follows: 1) the calculation method of the traffic capacity data is as follows: According to the characteristics of vehicles in the image, the texture feature extraction is performed on the land satellite remote sensing high-resolution data of the target area, the local binary pattern is calculated to obtain the texture feature image, and then the support vector machine is used to classify the vehicles, and the traffic capacity data of each unit grid map in the target area is calculated according to different vehicle types; 2) The calculation method of land cover type distribution data is: Firstly, GF-1 wide multispectral data, MODIS data and national forest resource continuous investigation fixed plot data are obtained through satellite remote sensing high resolution data of the target area; then the obtained GF-1 wide multispectral data, MODIS data and national forest resource continuous investigation fixed plot data are preprocessed including radiation calibration, geometric correction and projection conversion; then the preprocessed GF-1 wide multispectral data, MODIS data and national forest resource continuous investigation fixed plot data are segmented based on the principle of multi-scale segmentation, and features including spectrum, texture and shape are extracted; finally, the random forest algorithm is used for feature selection, and the CART algorithm is used for training and classification, and land cover type distribution data of each unit grid map in the target area is obtained; 3) The calculation method of blue-green infrastructure area data is: The blue-green infrastructure is extracted based on satellite remote sensing high resolution data of the target area by using NDVI and MNDWI calculation formula according to the spectral curve characteristics and the experiment, and the blue-green infrastructure area data of each unit grid map in the target area is calculated; 4) The calculation method of building density / height data is: The building density / height data of each unit grid map in the target area is calculated by using the imaging geometric model of building and shadow and single high resolution satellite remote sensing image in the satellite remote sensing high resolution data of the target area. 5.The method of claim 1, wherein, In step 4, the calculation method of composite pollution concentration high resolution distribution data of each unit grid map in the target area is: The PM2.5, O3 and NO2 concentration fields of the target area are extracted by satellite remote sensing technology, the diffusion distance of adjacent grid unit maps in the concentration field is calculated based on the divided grid unit map, the diffusion distance surface is obtained, then the shortest path distance between each grid unit map and the ground monitoring station of the research area is calculated, and the inverse distance weighted interpolation is carried out combined with the pollution monitoring data, so as to realize the high resolution interpolation of different types of pollution concentration, and finally the composite pollution concentration high resolution distribution data is obtained according to the distribution results of different types of pollution concentration. 6.The method of claim 1, wherein, In step 5, the construction method of dimensionless form multi-source database is: Firstly, the attribute data including personnel density distribution data, traffic capacity data, land cover type data, blue-green infrastructure area data, building density / height data and composite pollution concentration high resolution distribution data are extracted to measure the similarity between the attribute data, the similarity distance is solved and the distance matrix is formed, and then the best matching result is found based on the obtained distance matrix, so that the sum of distances between all attribute data matching attributes is minimized, that is, the preliminary screened multi-source database is obtained; Then, based on the preliminary screened multi-source database, the multi-source heterogeneous data deep analysis including multi-source data cleaning and dimensionless processing is realized by using the data cleaning method based on dynamic configurable rules and the range standardization method, so as to obtain the dimensionless form multi-source database; wherein, 1) The specific steps of implementing multi-source data cleaning by using a data cleaning method based on dynamically configurable rules are as follows: The missing values are filled in by selecting the median of similar data as the filling value, the standard deviation of the noise data is detected, the data consistency is further checked, that is, whether the data conforms to the pre-defined format is checked, and finally the redundant data detection is realized according to the similarity calculation; 2) The range standardization method is used to realize the dimensionless processing of multi-source data, that is, the original data is mapped to the [0, 1] interval through linear transformation, so that data of different orders of magnitude can be compared and weighted. Based on the above data analysis process, the dimensionless multi-source database is obtained, including dimensionless personnel density distribution data, dimensionless traffic capacity data, dimensionless land cover type data, dimensionless blue-green infrastructure area data, dimensionless building density / height data, and dimensionless high-resolution distribution data of complex pollution concentration. 7.The method of claim 1, wherein, In step 6, the evaluation method of the complex pollution exposure risk of the target area is as follows: First, according to the dimensionless data corresponding to the traffic capacity, land cover type, blue-green infrastructure area, building density / height and other factors in the dimensionless multi-source database, the urban characteristic factors of each type of factor are extracted by using the entropy method; Then, the characteristic factors corresponding to each type of factor are taken as weight coefficients, and multiplied by the dimensionless personnel density distribution data to obtain the personnel density distribution data processed by each type of characteristic factor weighting; Then, based on the obtained personnel density distribution data processed by each type of characteristic factor weighting, the cumulative complex pollution concentration is calculated by combining the dimensionless high-resolution distribution data of complex pollution concentration; Finally, the relative mortality rate calculation method of epidemiology is used to calculate the complex pollution exposure risk of the target area in combination with the cumulative complex pollution concentration.

8. A device for early warning of urban complex pollution exposure risk, characterized in that, It comprises a map display screen (1) and a text display screen (2) arranged on the front of the shell, a hook (5) arranged on the back of the shell, a wireless data receiver (4) arranged on the side wall of the shell, and an operation device (6), a power supply (7) and a memory (8) arranged inside the shell; wherein, The wireless data receiver (4) is responsible for sending personnel positioning data to the background, and is responsible for receiving the complex pollution exposure risk corresponding to the position of the personnel calculated by the background based on the multi-source big data city complex pollution exposure evaluation method according to any one of claims 1-7; The operation device (6) is responsible for combining the city grid coordinates to perform linear interpolation fitting on the complex pollution exposure risk value corresponding to the position of the personnel received, to obtain a high-resolution complex pollution exposure risk distribution map and output it; and is responsible for comparing the complex pollution exposure risk of the position of the personnel with the set risk threshold based on the high-resolution complex pollution exposure risk distribution map, to obtain a comparison result and output it; The map display screen (1) is responsible for displaying the high-resolution complex pollution exposure risk distribution map output by the operation device (6); The character display screen (2) is responsible for displaying the comparison result of the composite pollution exposure risk of the personnel's location output by the operator (6) and the set risk threshold value; when the composite pollution exposure risk of the personnel's location is greater than the set risk threshold value, the "pollution is seriously over-standard" character is displayed; when the composite pollution exposure risk of the personnel's location is equal to the set risk threshold value, the "pollution has been over-standard" character is displayed; when the composite pollution exposure risk of the personnel's location is less than the set risk threshold value, the "pollution is not over-standard" character is displayed. The memory (8) is responsible for storing the set risk threshold value, the obtained personnel positioning data, the received composite pollution exposure risk value corresponding to the personnel's location, the fitted high-resolution composite pollution exposure risk distribution map, and the calculated comparison result of the composite pollution exposure risk of the personnel's location and the set risk threshold value. The power supply (7) is responsible for powering the operator (6), the wireless data receiver (4), the map display screen (1), the character display screen (2), and the memory (8). The switch (3) is responsible for the on-off of the power supply (7). The hook (5) facilitates detachable connection with the personnel's clothing.

9. A computer apparatus, comprising: It comprises: a processor, a memory, a communication interface, and a communication bus, the processor, the memory, and the communication interface complete communication with each other through the communication bus, the memory is used to store at least one executable instruction, and the executable instruction makes the processor execute the operation corresponding to the urban composite pollution exposure evaluation method based on multi-source big data according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer storage medium stores at least one executable instruction, and the executable instruction makes the processor execute the operation corresponding to the urban composite pollution exposure evaluation method based on multi-source big data according to any one of claims 1-7.

Images