Method, apparatus and storage medium for determining thermal exposure risk time partition

Abstract

The present application provides a kind of thermal exposure risk time partition determination method, device, equipment and storage medium, comprising: obtaining the time series thermal exposure risk spatial distribution layer of target city in target period under predetermined time scale, hierarchical clustering analysis is carried out based on thermal exposure risk spatial pattern similarity, obtain the time partition under predetermined time scale;Based on the time partition under predetermined time scale, the average city thermal exposure risk spatial distribution layer of time partition under target time scale is obtained and paired sample difference test is carried out for the spatio-temporal partition statistics of thermal exposure risk, to determine the reliability of the time partition under predetermined time scale according to test result.The present application considers the spatial pattern of thermal exposure risk, thereby realizing the quantitative division of thermal exposure risk time partition under different predetermined time scales, and the obtained time partition is matched with the travel time of urban residents, which can effectively guide the partition control of urban thermal exposure risk.

Description

Technical Field

[0001] The present invention relates to the field of heat exposure risk technology, and in particular to a method, device, equipment and storage medium for determining time zones for heat exposure risk. Background Art

[0002] Urban heat exposure risk represents the possibility of residents suffering health hazards from contact and exposure to high temperature conditions or adverse thermal environments. It is closely related to the urban living environment and residents' health, and profoundly affects the livability and sustainable management of the city.

[0003] Since both ambient temperature and urban populations are highly spatially heterogeneous and temporally variable, urban heat exposure risk also has a high degree of spatiotemporal variability. At the same time, limited by the availability of real resources, the targeted implementation of adaptation and mitigation measures for urban heat exposure risk needs to be carried out in different regions, which puts forward new requirements for the spatial and temporal zoning and verification methods of heat exposure risk.

[0004] Therefore, how to effectively and reliably determine the time zones of urban heat exposure risks in order to implement targeted zoning control of urban heat exposure risks is an urgent problem that needs to be solved. Summary of the Invention

[0005] The present invention provides a method, device, equipment and storage medium for determining the time zones of heat exposure risks, which are used to address the defects in the existing technology that the time zones of urban heat exposure risks lack relevant scientific basis and the zoning management of risks cannot be effectively guided. In realizing the quantitative division of the time zones of urban heat exposure risks, the spatial pattern of heat exposure risks is taken into account at the same time, thereby effectively guiding the zoning management of urban heat exposure risks.

[0006] The present invention provides a method for determining heat exposure risk time zones, comprising:

[0007] Obtain a time series heat exposure risk spatial distribution layer at a predetermined time scale for the target city during the target period;

[0008] Based on the similarity of the spatial pattern of heat exposure risk, a hierarchical cluster analysis is performed on the time series heat exposure risk spatial distribution layer at the predetermined time scale to obtain the time partition at the predetermined time scale;

[0009] Based on the time partitions at the predetermined time scale, performing spatiotemporal statistics on the heat exposure risk, and obtaining a spatial distribution layer of the average urban heat exposure risk in the time partitions at the target time scale;

[0010] A paired sample difference test is performed on the average urban heat exposure risk spatial distribution layer of the time partition at the target time scale to determine the reliability of the time partition at the predetermined time scale based on the test results.

[0011] According to a method for determining heat exposure risk time zones provided by the present invention, obtaining a time series heat exposure risk spatial distribution layer at a predetermined time scale for a target city within a target period includes:

[0012] For each predetermined time scale, determining a basic time unit of the predetermined time scale based on the predetermined time scale;

[0013] Based on the basic time unit, dividing the target period into multiple time intervals of equal length;

[0014] Determine a basic spatial unit, and divide the target city into multiple spatial areas based on the basic spatial unit;

[0015] The spatial regions on the heat exposure risk layer in each time interval are sorted to obtain a time series heat exposure risk spatial distribution layer in the predetermined time scale.

[0016] According to a method for determining heat exposure risk time zones provided by the present invention, the spatial regions on the heat exposure risk layer in each time interval are sorted to obtain a time series heat exposure risk spatial distribution layer in the predetermined time scale, including:

[0017] The spatial regions on the heat exposure risk layer in each time interval are sorted according to the same spatial region order to obtain the time series heat exposure risk spatial distribution layer in the predetermined time scale.

[0018] According to a method for determining time zones of heat exposure risk provided by the present invention, based on the similarity of the spatial pattern of heat exposure risk, a hierarchical cluster analysis is performed on the time series heat exposure risk spatial distribution layer at the predetermined time scale to obtain the time zones at the predetermined time scale, including:

[0019] Performing a hierarchical clustering analysis on the time series heat exposure risk spatial distribution layer at the predetermined time scale based on the similarity of the heat exposure risk spatial pattern, and obtaining a specific number of multiple clustering results at different clustering levels;

[0020] A target clustering level is determined, and according to the time attribute characteristics of the time interval contained in each clustering result under the target clustering level, the clustering result is defined to obtain a time partition under a predetermined time scale.

[0021] According to a method for determining heat exposure risk by time partition provided by the present invention, the method performs spatiotemporal statistics of heat exposure risk based on the time partitions at the predetermined time scale to obtain an average urban heat exposure risk spatial distribution layer for the time partitions at the target time scale, including:

[0022] Combining the time partitions at different predetermined time scales to obtain the time partitions at the target time scale;

[0023] Calculate the average heat exposure risk value of each spatial area in the time partition at the target time scale to obtain the average urban heat exposure risk spatial distribution layer in the time partition at the target time scale.

[0024] According to a method for determining heat exposure risk time zones provided by the present invention, performing a paired sample difference test on the average urban heat exposure risk spatial distribution layer of the time zones at the target time scale includes:

[0025] The average urban heat exposure risk values ​​of different time zones in the same spatial area at the target time scale are used as paired samples, and a paired sample difference test is performed on the spatial distribution layer of the average urban heat exposure risk of the time zones at the target time scale.

[0026] According to a method for determining time zones for heat exposure risk provided by the present invention, determining the reliability of the time zones at the predetermined time scale based on the test results includes:

[0027] If the significance level test result parameter value is less than a preset significance level test threshold, determining that the time partition under the predetermined time scale is a reliable result under the significance level;

[0028] If the significance level test result parameter value is not less than a preset significance level test threshold, it is determined that the time partition under the predetermined time scale is an unreliable result under the significance level.

[0029] The present invention also provides a device for determining heat exposure risk time zones, comprising:

[0030] An acquisition module is used to obtain a time series heat exposure risk spatial distribution layer at a predetermined time scale for a target city within a target period;

[0031] A clustering module is used to perform a hierarchical clustering analysis on the time series heat exposure risk spatial distribution layer at the predetermined time scale based on the similarity of the heat exposure risk spatial pattern, so as to obtain a time partition at the predetermined time scale;

[0032] A statistical module is used to perform spatiotemporal statistics on heat exposure risks based on the time partitions at the predetermined time scale, and obtain an average urban heat exposure risk spatial distribution layer for the time partitions at the target time scale;

[0033] The test module is used to perform a paired sample difference test on the average urban heat exposure risk spatial distribution layer of the time partition under the target time scale, so as to determine the reliability of the time partition under the predetermined time scale according to the test results.

[0034] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for determining the time partition of heat exposure risk as described above is implemented.

[0035] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described methods for determining time zones for heat exposure risks.

[0036] The method, device, equipment and storage medium for determining time zones of heat exposure risks provided by the present invention perform hierarchical cluster analysis on the time series heat exposure risk spatial distribution layer at a predetermined time scale of the target city within the target period, taking into account the spatial pattern of heat exposure risk, so that the time zones obtained by cluster analysis can match the travel time of urban residents, thereby realizing the quantitative division of time zones at different predetermined time scales, and can effectively guide the zoning management and control of urban heat exposure risks; by performing spatiotemporal zoning statistics on heat exposure risks based on time zones at a predetermined time scale, the average urban heat exposure risk spatial distribution layer of the time zones at the target time scale is obtained, and then a paired sample difference test is performed on the average urban heat exposure risk spatial distribution layer of the time zones at the target time scale, so that the reliability of the time zones at the predetermined time scale obtained by cluster analysis can be further effectively verified through the test results, which is conducive to the final output of reliable and effective time zoning results. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 It is a flow chart of a method for determining time zones for heat exposure risk provided by an embodiment of the present invention.

[0039] Figure 2 3 is a schematic diagram of the spatial distribution of the average heat exposure risk of a target city within 24 hours provided by an embodiment of the present invention.

[0040] Figure 331-day average heat exposure risk spatial distribution diagram of a target city provided by an embodiment of the present invention.

[0041] Figure 4 This is a schematic diagram of the hierarchical clustering pattern of urban heat exposure risk time series at different predetermined time scales in a target city provided by an embodiment of the present invention.

[0042] Figure 5 This is a schematic diagram of the spatial distribution of average urban heat exposure risks in different time zones of a target city provided by an embodiment of the present invention.

[0043] Figure 6 It is a structural diagram of a device for determining time zones for heat exposure risks provided by an embodiment of the present invention.

[0044] Figure 7 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0046] Currently, there is no clear and definitive method for quantitatively defining the temporal zoning of heat exposure risk. At the hourly scale, intraday zoning of heat exposure risk is often simply qualitatively divided into natural daytime and natural nighttime based on sunrise and sunset times. However, on the one hand, this temporal zoning is somewhat mismatched with urban residents' travel times and lacks applicability and significance at the daily scale. On the other hand, it fails to account for the spatial heterogeneity of heat exposure risk, a crucial characteristic of risk. Therefore, there is currently a lack of reliable methods for the temporal zoning of urban heat exposure risk, and effective guidance for zoning-based management of urban heat exposure risk is lacking.

[0047] To address the above issues, the present invention takes into account the spatial pattern of heat exposure risk, thereby achieving a quantitative division of heat exposure risk time zones under different predetermined time scales. The obtained time zones match the travel time of urban residents and can effectively guide the zoning control of urban heat exposure risks.

[0048] Figure 1 FIG. 1 is a flow chart of a method for determining heat exposure risk time zones according to an embodiment of the present invention. Figure 1 The embodiment of the present invention provides a method for determining heat exposure risk time zones, which may include the following steps:

[0049] Step 110: Obtain a time series heat exposure risk spatial distribution layer at a predetermined time scale for a target city within a target period.

[0050] It should be noted that the execution entity of the heat exposure risk time zone determination method provided in the embodiments of the present invention can be an electronic device, a component of an electronic device, an integrated circuit, or a chip. The electronic device can be a mobile electronic device or a non-mobile electronic device. For example, a mobile electronic device can be a mobile phone, tablet computer, laptop computer, PDA, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), while a non-mobile electronic device can be a server, network attached storage (NAS), personal computer (PC), television, ATM, or self-service machine, etc., which are not specifically limited in the embodiments of the present invention.

[0051] Specifically, the target period may refer to a heat exposure risk study period determined according to actual needs. For example, the target period may be a month of a certain year or a day of a certain month.

[0052] Specifically, the target city may refer to a heat exposure risk study city determined according to actual needs. It should be noted that the heat exposure risk time zone determination method provided in the embodiment of the present invention can be applied not only to heat exposure risk study scenarios within a specific city, but also to heat exposure risk study scenarios within other regions, such as heat exposure risk study scenarios within a province, heat exposure risk study scenarios within a district or county, etc., and the present invention does not impose any specific limitations on this.

[0053] Specifically, the predetermined time scale may refer to a single-dimensional time scale determined according to actual needs, such as a monthly scale, a daily scale, an hourly scale, etc. There may be multiple predetermined time scales, and each predetermined time scale may have its own corresponding time series heat exposure risk spatial distribution layer, for example, a monthly series heat exposure risk spatial distribution layer at the monthly scale, a date series heat exposure risk spatial distribution layer at the daily scale, and a time period series heat exposure risk spatial distribution layer at the hourly scale.

[0054] It should be noted that the predetermined time scale can be determined based on the target period and cannot exceed the time range of the target period. For example, if the target period is a month, the predetermined time scale can be determined as a day scale and an hour scale, but not a month scale. If the target period is a year, the predetermined time scale can be determined as two time scales: a month and a day scale, or as three time scales: a month, a day, and an hour scale.

[0055] In an embodiment of the present invention, time series heat exposure risk spatial distribution layers at multiple predetermined time scales of a target city within a target period can be obtained, and hierarchical clustering analysis can be performed to obtain corresponding time partitions.

[0056] The embodiment of the present invention uses the heat exposure risk spatial distribution layer to realize the division of time zones, taking into account the important risk characteristic property of spatial heterogeneity of heat exposure risk, which is conducive to more effectively guiding the zoning control of urban heat exposure risk.

[0057] Step 120 : Based on the similarity of the spatial pattern of heat exposure risk, a hierarchical clustering analysis is performed on the time series heat exposure risk spatial distribution layer at the predetermined time scale to obtain the time partition at the predetermined time scale.

[0058] Specifically, a hierarchical clustering analysis can be performed on the time series heat exposure risk spatial distribution layer at each predetermined time scale based on the similarity of the heat exposure risk spatial pattern to obtain time partitions at each predetermined time scale. There can be at least two time partitions at each predetermined time scale.

[0059] In some embodiments, a hierarchical clustering analysis can be performed on the date series heat exposure risk spatial distribution layer at the daily scale to obtain time partitions at the daily scale; a hierarchical clustering analysis can be performed on the time period series heat exposure risk spatial distribution layer at the hourly scale to obtain time partitions at the hourly scale; and a hierarchical clustering analysis can also be performed on the month series heat exposure risk spatial distribution layer at the monthly scale to obtain time partitions at the monthly scale.

[0060] In some embodiments, the time partitions at the day scale may include two time partitions: "rest days" and "working days", the time partitions at the hour scale may include two time partitions: "daytime" and "nighttime", and the time partitions at the month scale may include two time partitions: "cold season" and "hot season".

[0061] Step 130 , based on the time partitions at the predetermined time scale, performing spatiotemporal statistics on the heat exposure risk, and obtaining a spatial distribution layer of the average urban heat exposure risk of the time partitions at the target time scale.

[0062] Specifically, the target time scale can be a multidimensional time scale composed of multiple different predetermined time scales, and the time partitions at the target time scale can be obtained by combining time partitions at different predetermined time scales. For example, when the predetermined time scales are days and hours, the target time scale is a two-dimensional time scale of days-hours.

[0063] In some embodiments, when the predetermined time scale is a day scale and an hour scale, the time partitions under the target time scale may include “daytime on weekends”, “nighttime on weekends”, “daytime on weekdays” and “nighttime on weekdays”.

[0064] In some embodiments, when the predetermined time scale is a monthly scale, a daily scale, and an hourly scale, the time partitions under the target time scale may include "daytime on holidays in cold seasons", "nighttime on holidays in cold seasons", "daytime on working days in cold seasons", "nighttime on working days in cold seasons", "daytime on holidays in hot seasons", "nighttime on holidays in hot seasons", "daytime on working days in hot seasons", and "nighttime on working days in hot seasons".

[0065] In an embodiment of the present invention, based on the preliminary division of each time partition under the predetermined time scale, the heat exposure risk can be subjected to spatiotemporal statistics with the basic spatial unit as the object, thereby obtaining the average urban heat exposure risk spatial distribution layer of each time partition under the target time scale.

[0066] Step 140 : performing a paired sample difference test on the average urban heat exposure risk spatial distribution layer of the time partitions at the target time scale, so as to determine the reliability of the time partitions at the predetermined time scale according to the test results.

[0067] Specifically, a paired sample difference test can be performed on the average urban heat exposure risk spatial distribution layer of any two time zones under the target time scale. The difference test can be used to compare whether the differences between the samples of the average urban heat exposure risk spatial distribution layer of the two time zones are significant, thereby determining the reliability of each time zone under the predetermined time scale that has been preliminarily divided based on the significance level test results.

[0068] The embodiment of the present invention performs a hierarchical cluster analysis on the time series heat exposure risk spatial distribution layer at a predetermined time scale of the target city within the target period, taking into account the spatial pattern of heat exposure risk, so that the time partitions obtained by the cluster analysis can match the travel time of urban residents, thereby realizing the quantitative division of time partitions at different predetermined time scales, which can effectively guide the zoning control of urban heat exposure risks; by performing spatiotemporal zoning statistics on heat exposure risks based on time partitions at a predetermined time scale, the average urban heat exposure risk spatial distribution layer of the time partitions at the target time scale is obtained, and then a paired sample difference test is performed on the average urban heat exposure risk spatial distribution layer of the time partitions at the target time scale, so that the reliability of the time partitions at the predetermined time scale obtained by the cluster analysis can be further effectively verified through the test results, which is conducive to the final output of reliable and effective time partitioning results.

[0069] In some optional embodiments, obtaining a time series heat exposure risk spatial distribution layer at a predetermined time scale for a target city within a target period may specifically include:

[0070] Step 111 : for each predetermined time scale, determine a basic time unit of the predetermined time scale based on the predetermined time scale.

[0071] Specifically, for each predetermined time scale, a basic time unit of the time series at each predetermined time scale may be determined respectively.

[0072] In some embodiments, for a date sequence on a day scale, days may be used as a basic time unit; for a time period sequence on an hour scale, hours may be used as a basic time unit.

[0073] Step 112: Divide the target period into a plurality of time intervals of equal length based on the basic time unit.

[0074] Specifically, the target period may be divided into a plurality of time intervals of equal length based on the basic time units corresponding to the respective predetermined time scales.

[0075] In some embodiments, assuming that the target period is October 2020, October can be divided into 31 dates based on the basic time unit of the day scale, and October can be divided into 24 hours based on the time period sequence of the hour scale; assuming that the target period is September 2020, September can be divided into 30 dates based on the basic time unit of the day scale, and September can be divided into 24 hours based on the time period sequence of the hour scale.

[0076] Step 113: determine a basic spatial unit, and divide the target city into multiple spatial areas based on the basic spatial unit.

[0077] Specifically, the basic spatial unit may refer to a regular grid set according to actual needs. The regular grid may be a grid with the same length and width, or a grid with different lengths and widths.

[0078] Specifically, the target city can be divided into n spatial regions of the same size (i.e., the same area) based on the basic spatial unit, and the average heat exposure risk value HER of each spatial region in each time interval can be calculated. n , and obtain the heat exposure risk layer of each spatial area in each time interval.

[0079] In some embodiments, the basic spatial unit may be determined as a regular grid of 250 meters by 250 meters, thereby dividing the target city into multiple spatial regions of the same area of ​​250 meters by 250 meters.

[0080] Step 114 , sorting the spatial regions on the heat exposure risk layer in each time interval to obtain a time series heat exposure risk spatial distribution layer in the predetermined time scale.

[0081] In some embodiments, the spatial areas on each day's heat exposure risk layer can be sorted with the spatial area as the horizontal coordinate and the date sequence at the daily scale as the vertical coordinate to obtain a date sequence heat exposure risk spatial distribution layer at the daily scale; the spatial areas on each hour's heat exposure risk layer can be sorted with the spatial area as the horizontal coordinate and the time period sequence at the hourly scale as the vertical coordinate to obtain a time period sequence heat exposure risk spatial distribution layer at the hourly scale.

[0082] Figure 2 This is a schematic diagram of the spatial distribution of the average heat exposure risk of a target city within 24 hours provided by an embodiment of the present invention. Figure 2 The higher the brightness, the higher the average heat exposure risk value; the lower the brightness, the lower the average heat exposure risk value. It can be seen that the brightness from period 8 to period 19 is high, and the average heat exposure risk value is high; the brightness from period 19 to period 8 is low, and the average heat exposure risk value is low.

[0083] Figure 3 This is a schematic diagram of the spatial distribution of the average heat exposure risk of the target city over 31 days provided by the embodiment of the present invention. Figure 3 The higher the brightness, the higher the average heat exposure risk; the lower the brightness, the lower the average heat exposure risk. As can be seen, the brightness on the 1st to 8th, 11th, 24th to 25th, 17th to 18th, and 31st were all high, with high average heat exposure risk; while the brightness on the 9th to 10th, 12th to 16th, 19th to 23rd, and 26th to 30th were all low, with low average heat exposure risk.

[0084] The embodiment of the present invention divides the time intervals and spatial areas and sorts the spatial areas on the heat exposure risk layer in each time interval, which is conducive to ensuring the consistency of the spatial pattern of heat exposure risk layers in different time series, taking into account the spatial pattern of heat exposure risk, and thus effectively guiding the zoning control of urban heat exposure risk.

[0085] In some optional embodiments, the sorting of the spatial regions on the heat exposure risk layer in each time interval to obtain the time series heat exposure risk spatial distribution layer in the predetermined time scale may specifically include: sorting the spatial regions on the heat exposure risk layer in each time interval in the same spatial region order to obtain the time series heat exposure risk spatial distribution layer in the predetermined time scale.

[0086] Specifically, after dividing the target city into multiple spatial regions of equal size, each spatial region can be uniquely numbered, and the spatial regions can be sorted in the order of their numbers. For example, the spatial regions can be sorted in the order of: spatial region 1, spatial region 2, spatial region 3, ..., spatial region n.

[0087] Specifically, for each predetermined time scale, the spatial regions on the heat exposure risk layer for each time interval can be sorted according to the same spatial region sorting order to obtain a time series heat exposure risk layer for the predetermined time scale. The same spatial region has the same relative spatial position in the time series, which helps ensure the consistency of the spatial pattern of the heat exposure risk layers across different time series.

[0088] The embodiment of the present invention sorts the spatial regions on the heat exposure risk layer in each time interval according to the same spatial region order, so that the relative spatial position of the same spatial region in the time series is the same, which is conducive to ensuring the consistency of the spatial pattern of heat exposure risk layers in different time series, thereby effectively guiding the zoning control of urban heat exposure risks.

[0089] In some optional embodiments, based on the similarity of the spatial pattern of heat exposure risk, a hierarchical cluster analysis is performed on the time series heat exposure risk spatial distribution layer at the predetermined time scale to obtain the time partition at the predetermined time scale, which may specifically include:

[0090] Step 121, performing a hierarchical cluster analysis on the time series heat exposure risk spatial distribution layer at the predetermined time scale based on the similarity of the heat exposure risk spatial pattern, to obtain a specific number of clustering results at different clustering levels;

[0091] Step 122 : determining a target clustering level, defining the clustering results according to the time attribute characteristics of the time interval contained in each clustering result under the target clustering level, and obtaining time partitions under a predetermined time scale.

[0092] Specifically, the target clustering level may refer to a clustering level determined according to the number requirement of clustering results.

[0093] Specifically, after performing hierarchical clustering analysis, multiple clustering levels can be obtained, and each clustering level can include a specific number of clustering results. Based on the actual number of clustering results required, a clustering level that meets the number of clustering results can be selected as the target clustering level.

[0094] In some embodiments, after performing a hierarchical cluster analysis, one clustering result can be obtained at the first clustering level (i.e., the time series heat exposure risk spatial distribution layer belongs to a large cluster), two clustering results at the second clustering level, Cluster 1 and Cluster 2, and four clustering results at the third clustering level, Cluster 11, Cluster 12, Cluster 21, and Cluster 22. Cluster 1 includes Cluster 11 and Cluster 12, and Cluster 2 includes Cluster 21 and Cluster 22. If the number of required clustering results is two, the second clustering level can be selected as the target clustering level; if the number of required clustering results is four, the third clustering level can be selected as the target clustering level.

[0095] Specifically, the time attribute characteristics of the time intervals included in different clustering results are also different.

[0096] Specifically, each clustering result under the target clustering level can include the spatial distribution of heat exposure risk under multiple time intervals. The clustering results can be defined according to the time attribute characteristics of the multiple time intervals contained in each clustering result, thereby obtaining the time partition under the predetermined time scale.

[0097] In some embodiments, when the target clustering level is the second clustering level, cluster 1 can be defined based on the time attribute characteristics of multiple time intervals contained in cluster 1, and cluster 2 can be defined based on the time attribute characteristics of multiple time intervals contained in cluster 2.

[0098] Figure 4 This is a schematic diagram of the hierarchical clustering pattern of urban heat exposure risk time series at different predetermined time scales in a target city provided by an embodiment of the present invention.

[0099] Reference Figure 4In some embodiments, a hierarchical cluster analysis is performed on the spatial distribution layer of heat exposure risk in a date series at the daily scale. When the target cluster level is determined to be the second cluster level, two clustering results can be obtained: Cluster 1 (1st to 8th, 11th, 24th to 25th, 17th to 18th, and 31st) and Cluster 2 (9th to 10th, 12th to 16th, 19th to 23rd, and 26th to 30th). Based on the time attribute characteristics of the specific dates included in the two clustering results, Cluster 1 and Cluster 2 can be defined as "rest days" and "work days," respectively.

[0100] In some embodiments, hierarchical cluster analysis of the hourly time series heat exposure risk spatial distribution layer can yield two clustering results: Cluster 3 (time periods 9-19) and Cluster 4 (time periods 1-8 and 20-24). Based on the time attribute characteristics of the specific dates included in these two clustering results, Cluster 3 and Cluster 4 can be defined as "daytime" and "nighttime," respectively.

[0101] The embodiment of the present invention performs hierarchical clustering analysis on the spatial distribution layer of time series heat exposure risk at a predetermined time scale, and defines the clustering results according to the time attribute characteristics of the time series contained in each clustering result, which is conducive to the quantitative division of time zones at different predetermined time scales, thereby effectively guiding the zoning control of urban heat exposure risks.

[0102] In some optional embodiments, performing spatiotemporal statistics of heat exposure risk based on the time partitions at the predetermined time scale to obtain an average urban heat exposure risk spatial distribution layer for the time partitions at the target time scale may specifically include:

[0103] Step 131, combining time partitions at different predetermined time scales to obtain time partitions at a target time scale;

[0104] Step 132 , calculating the average heat exposure risk value of each spatial region in the time partition at the target time scale, and obtaining the average urban heat exposure risk spatial distribution layer in the time partition at the target time scale.

[0105] Specifically, there can be multiple predetermined time scales, and one predetermined time scale can have multiple time partitions. The time partitions under different predetermined time scales can be combined to obtain multiple time partitions under the target time scale, thereby calculating the average heat exposure risk value HER of each spatial area in each time partition under the target time scale. ` n , and obtain the average urban heat exposure risk spatial distribution layer in each time zone at the target time scale.

[0106] In some embodiments, the time partitions "rest day" and "working day" at the day scale and the time partitions "day" and "night" at the hour scale can be combined to obtain the time partitions "rest day", "rest night", "working day" and "working night" at the target time scale.

[0107] Figure 5 This is a schematic diagram of the spatial distribution of average urban heat exposure risks in different time zones of a target city provided by an embodiment of the present invention.

[0108] Reference Figure 5 In some embodiments, based on the preliminary hourly and daily time partitions, temporal and spatial distribution statistics of the target city's heat exposure risk can be performed, yielding the average spatial distribution of the city's heat exposure risk for weekday daytime, weekday nighttime, weekend daytime, and weekend nighttime. It can be seen that weekday daytime and weekend daytime have higher brightness and higher average heat exposure risk values, while weekday nighttime and weekend nighttime have lower brightness and lower average heat exposure risk values.

[0109] The embodiment of the present invention calculates the average heat exposure risk value of each spatial area in the time partition at the target time scale, and obtains the average urban heat exposure risk spatial distribution layer in the time partition at the target time scale. Then, a paired sample difference test can be performed. The test results can further effectively verify the reliability of the time partition at the predetermined time scale obtained by cluster analysis, which is conducive to the final output of reliable and effective time partition results.

[0110] In some optional embodiments, the paired sample difference test is performed on the spatial distribution layer of the average urban heat exposure risk of the time partition at the target time scale, which can specifically include: taking the average urban heat exposure risk values ​​of different time partitions in the same spatial area at the target time scale as paired samples, and performing a paired sample difference test on the spatial distribution layer of the average urban heat exposure risk of the time partition at the target time scale.

[0111] Specifically, any predetermined time scale can be selected as the partition difference test scale, and other time scales outside the partition difference test scale can be used as control variable scales to perform paired sample difference test.

[0112] Specifically, the test results may include significance level test results and differential effect results. The significance level test results can be used to determine whether the time partitions at a predetermined scale obtained by cluster analysis are reliable results, and the differential effect results can be used to determine the level of difference between the time partitions at a predetermined scale obtained by cluster analysis.

[0113] Table 1 shows the significance test results of the time-zone differences in heat exposure risk of the target city provided by the embodiment of the present invention.

[0114]

[0115] Referring to Table 1, in some embodiments, when the hourly scale is selected as the zoning difference test scale and the daily scale is selected as the control variable scale, the average urban heat exposure risk values ​​of the same spatial area during weekday daytime and weekday nighttime can be used as paired samples for difference test, and the significance level is 0.001 and the difference effect is 0.2968; the average urban heat exposure risk values ​​of the same spatial area during weekend daytime and weekend nighttime can be used as paired samples for difference test, and the significance level is 0.001 and the difference effect is 0.3079.

[0116] When the daily scale is selected as the zoning difference test scale and the hourly scale is selected as the control variable scale, the average urban heat exposure risk values ​​in the same spatial area during weekday daytime and weekend daytime can be used as paired samples for difference test, and the significance level is 0.001, and the difference effect is 0.2071; the average urban heat exposure risk values ​​in the same spatial area during weekday nights and weekend nights can be used as paired samples for difference test, and the significance level is 0.001, and the difference effect is 0.2568.

[0117] In the embodiment of the present invention, the average urban heat exposure risk values ​​of different time partitions in the same spatial area at the target time scale are used as paired samples for difference testing. The test results can further effectively verify the reliability of the time partition at the predetermined time scale obtained by cluster analysis, which is conducive to the final output of reliable and effective time partition results.

[0118] In some optional embodiments, determining the reliability of the time partition at the predetermined time scale according to the test result may specifically include:

[0119] Step 141: If the significance level test result parameter value is less than a preset significance level threshold, then determining that the time partition under the predetermined time scale is a reliable result under the significance level;

[0120] Step 142: If the significance level test result parameter value is not less than a preset significance level test threshold, it is determined that the time partition under the predetermined time scale is an unreliable result under the significance level.

[0121] Specifically, the smaller the parameter value (p-value) of the significance level test result is, the more reliable the time partition division result under the predetermined time scale obtained by cluster analysis is.

[0122] In some embodiments, the preset significance level threshold can be set to 0.001. If the significance level test result parameter value p < 0.001, it can be determined that the time partition under the predetermined time scale obtained by the cluster analysis is a reliable result at the 0.001 significance level; if the significance level test result parameter value p ≥ 0.001, it can be determined that the time partition under the predetermined time scale obtained by the cluster analysis is an unreliable result at the 0.001 significance level. It should be noted that the preset significance level threshold is usually 0.1, 0.05 and 0.01, and the embodiment of the present application can more effectively illustrate the reliability of the final output time partition under the predetermined time scale by setting a more stringent preset significance level threshold (0.001) for reliability verification, thereby more effectively guiding the partitioning and control of urban heat exposure risk.

[0123] It can be known from Table 1 that there is a significant difference (p < 0.001) in urban heat exposure risk between the time partition groups of the hour scale and the day scale, which can indicate that the time partition result under the predetermined time scale obtained by clustering is reliable.

[0124] Specifically, the greater the difference effect parameter value (es value), the greater the degree of difference. In some embodiments, if the difference effect result is 0 < es < 0.3, it can be indicated that the degree of difference is small; if the difference effect result is 0.3 ≤ es < 0.7, it can be indicated that the degree of difference is moderate; if the difference effect result is 0.7 ≤ es < 1, it can be indicated that the degree of difference is large.

[0125] It can be known from Table 1 that the difference degree of the average urban heat exposure risk spatial distribution between the daytime on rest days and the nighttime on rest days is moderate, while the difference degree of the average urban heat exposure risk spatial distribution between the daytime on weekdays and the nighttime on weekdays, between the daytime on weekdays and the daytime on rest days, and between the nighttime on weekdays and the nighttime on rest days is small.

[0126] The embodiment of the present application can effectively verify the reliability of the time partition under the predetermined time scale obtained by the cluster analysis through the significance level test result, which is conducive to finally outputting a reliable and effective time partition result.

[0127] In order for those skilled in the art to better understand the embodiments of the present application, the embodiments of the present application will be described below through a specific example.

[0128] (1) For the hour scale period sequence and the day scale date sequence, the target period (October 2020) is divided into 24 periods and 31 dates respectively with hour and day as the basic time unit.

[0129] (2) The basic spatial unit is determined as a regular grid of 250 m × 250 m, and the target city is divided into 25,035 spatial areas of equal area. The average heat exposure risk value of each spatial area is calculated.

[0130] (3) Divide the time series at the two time scales into two time partitions respectively.

[0131] Based on the clustering results, the daily date series can be divided into Cluster 1 (1st-8th, 11th, 24th-25th, 17th-18th, and 31st) and Cluster 2 (9th-10th, 12th-16th, 19th-23rd, and 26th-30th). Based on the attribute characteristics of the specific dates included in these two clusters, Cluster 1 and Cluster 2 can be defined as "rest days" and "work days," respectively. "Rest days" include holidays (National Day and Mid-Autumn Festival, 1st-8th) and regular weekends (11th, 24th-25th, 17th-18th, and 31st). For urban risk management, specific holidays and regular weekends can, to a certain extent, be subject to the same risk management measures and strategies.

[0132] The hourly time series is divided into Cluster 1 (times 9-19) and Cluster 2 (times 1-8 and 20-24). Based on the attributes of the specific time periods contained in these two clusters, Cluster 1 and Cluster 2 can be defined as "clustered daytime" (08:00-19:00) and "clustered nighttime" (19:00-08:00), respectively. These time partitions, "clustered daytime" and "clustered nighttime," derived through the clustering algorithm, better match the daily travel times of urban residents compared to the "natural daytime" (06:00-18:00) and "natural nighttime" (18:00-06:00), which are directly based on the city's sunrise (around 06:00) and sunset (around 17:30-18:00) times in October.

[0133] Combining the time zoning results at the two time scales, it can be seen that the quantitative division of time zones through clustering algorithms has more effective guiding significance for the zoning management of urban heat exposure risks.

[0134] (4) Based on the preliminary hourly and daily scale divisions, the heat exposure risk of the target city can be statistically analyzed in time and space, and the average spatial distribution of urban heat exposure risk during weekdays, weekday nights, weekend days, and weekend nights can be obtained.

[0135] (5) A paired sample difference test was performed on the average heat exposure risk layer of the time-space partitions. The test results showed that there were significant differences in urban heat exposure risks between the time partition groups at the hourly scale and the daily scale (p < 0.001), indicating that the preliminary division results of the time partition obtained in step (3) are reliable and the proposed method for quantitative determination of urban heat exposure risk time partition is effective.

[0136] The heat exposure risk time zone determination device provided by the present invention is described below. The heat exposure risk time zone determination device described below and the heat exposure risk time zone determination method described above can refer to each other.

[0137] Figure 6 Schematic diagram of the structure of the device for determining heat exposure risk time zones provided by an embodiment of the present invention. Figure 6 The embodiment of the present invention provides a device for determining heat exposure risk time zones, which may specifically include the following modules:

[0138] An acquisition module 610 is used to obtain a time series heat exposure risk spatial distribution layer at a predetermined time scale for a target city within a target period;

[0139] A clustering module 620 is configured to perform a hierarchical clustering analysis on the time series heat exposure risk spatial distribution layer at the predetermined time scale based on the similarity of the heat exposure risk spatial pattern, to obtain a time partition at the predetermined time scale;

[0140] A statistics module 630 is configured to perform spatiotemporal statistics on heat exposure risk based on the time partitions at the predetermined time scale, and obtain an average urban heat exposure risk spatial distribution layer of the time partitions at the target time scale;

[0141] The test module 640 is used to perform a paired sample difference test on the average urban heat exposure risk spatial distribution layer of the time partition at the target time scale, so as to determine the reliability of the time partition at the predetermined time scale according to the test result.

[0142] In some optional embodiments, the acquisition module 610 is specifically configured to:

[0143] For each predetermined time scale, determining a basic time unit of the predetermined time scale based on the predetermined time scale;

[0144] Based on the basic time unit, dividing the target period into multiple time intervals of equal length;

[0145] Determine a basic spatial unit, and divide the target city into multiple spatial areas based on the basic spatial unit;

[0146] The spatial regions on the heat exposure risk layer in each time interval are sorted to obtain a time series heat exposure risk spatial distribution layer in the predetermined time scale.

[0147] In some optional embodiments, the acquisition module 610 is specifically configured to:

[0148] The spatial regions on the heat exposure risk layer in each time interval are sorted according to the same spatial region order to obtain the time series heat exposure risk spatial distribution layer in the predetermined time scale.

[0149] In some optional embodiments, the clustering module 620 is configured to:

[0150] Performing a hierarchical clustering analysis on the time series heat exposure risk spatial distribution layer at the predetermined time scale based on the similarity of the heat exposure risk spatial pattern to obtain clustering results at different clustering levels;

[0151] A target clustering level is determined, and according to the time attribute characteristics of the time series contained in each clustering result under the target clustering level, the clustering result is defined to obtain a time partition under a predetermined time scale.

[0152] In some optional embodiments, the statistics module 630 is specifically configured to:

[0153] Combining the time partitions at different predetermined time scales to obtain the time partitions at the target time scale;

[0154] Calculate the average heat exposure risk value of each spatial area in the time partition at the target time scale to obtain the average urban heat exposure risk spatial distribution layer in the time partition at the target time scale.

[0155] In some optional embodiments, the inspection module 640 is configured to:

[0156] The average urban heat exposure risk values ​​of different time zones in the same spatial area at the target time scale are used as paired samples, and a paired sample difference test is performed on the spatial distribution layer of the average urban heat exposure risk of the time zones at the target time scale.

[0157] In some optional embodiments, the inspection module 640 is configured to:

[0158] If the significance level test result parameter value is less than a preset significance level test threshold, determining that the time partition under the predetermined time scale is a reliable result under the significance level;

[0159] If the significance level test result parameter value is not less than a preset significance level test threshold, it is determined that the time partition under the predetermined time scale is an unreliable result under the significance level.

[0160] The embodiment of the present invention performs a hierarchical cluster analysis on the time series heat exposure risk spatial distribution layer at a predetermined time scale of the target city within the target period, taking into account the spatial pattern of heat exposure risk, so that the time partitions obtained by the cluster analysis can match the travel time of urban residents, thereby realizing the quantitative division of time partitions at different predetermined time scales, which can effectively guide the zoning control of urban heat exposure risks; by performing spatiotemporal zoning statistics on heat exposure risks based on time partitions at a predetermined time scale, the average urban heat exposure risk spatial distribution layer of the time partitions at the target time scale is obtained, and then a paired sample difference test is performed on the average urban heat exposure risk spatial distribution layer of the time partitions at the target time scale, so that the reliability of the time partitions at the predetermined time scale obtained by the cluster analysis can be further effectively verified through the test results, which is conducive to the final output of reliable and effective time partitioning results.

[0161] Figure 7 An example of a physical structure diagram of an electronic device is shown below. Figure 7 As shown, the electronic device may include: a processor 710, a communications interface 720, a memory 730, and a communications bus 740. The processor 710, the communications interface 720, and the memory 730 communicate with each other via the communications bus 740. The processor 710 may invoke logic instructions in the memory 730 to execute a method for determining time zones for heat exposure risk. The method includes: obtaining a time series heat exposure risk spatial distribution layer at a predetermined time scale for a target city within a target period; performing a hierarchical clustering analysis on the time series heat exposure risk spatial distribution layer at the predetermined time scale based on the similarity of the heat exposure risk spatial patterns to obtain time zones at the predetermined time scale; performing spatiotemporal statistics on the heat exposure risk based on the time zones at the predetermined time scale to obtain an average city heat exposure risk spatial distribution layer for the time zones at the target time scale; and performing a paired sample difference test on the average city heat exposure risk spatial distribution layer for the time zones at the target time scale to determine the reliability of the time zones at the predetermined time scale based on the test results.

[0162] In addition, the logic instructions in the memory 730 described above can be implemented in the form of software functional units and sold or used as independent products, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0163] In another aspect, the present application also provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the heat exposure risk time partition determination method provided by the above-mentioned method. The method comprises: obtaining a time series heat exposure risk spatial distribution layer of a target city in a target period under a predetermined time scale; based on the similarity of the heat exposure risk spatial pattern, performing hierarchical cluster analysis on the time series heat exposure risk spatial distribution layer under the predetermined time scale to obtain a time partition under the predetermined time scale; based on the time partition under the predetermined time scale, performing spatio-temporal partition statistics on the heat exposure risk to obtain an average city heat exposure risk spatial distribution layer of the time partition under the target time scale; and performing paired sample difference test on the average city heat exposure risk spatial distribution layer of the time partition under the target time scale to determine the reliability of the time partition under the predetermined time scale according to the test result.

[0164] The device embodiments described above are only schematic, wherein the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e. they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment. Those skilled in the art can understand and implement it without creative labor.

[0165] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0166] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for determining heat exposure risk time zones, characterized in that: include: Obtain a time series heat exposure risk spatial distribution layer at a predetermined time scale for the target city during the target period; Based on the similarity of the spatial pattern of heat exposure risk, a hierarchical cluster analysis is performed on the time series heat exposure risk spatial distribution layer at the predetermined time scale to obtain the time partition at the predetermined time scale; Based on the time partitions at the predetermined time scale, performing spatiotemporal statistics on the heat exposure risk, and obtaining a spatial distribution layer of the average urban heat exposure risk in the time partitions at the target time scale; Performing a paired sample difference test on the spatial distribution layer of the average urban heat exposure risk of the time partitions at the target time scale, so as to determine the reliability of the time partitions at the predetermined time scale according to the test results; Wherein, based on the similarity of the spatial pattern of heat exposure risk, a hierarchical cluster analysis is performed on the time series heat exposure risk spatial distribution layer at the predetermined time scale to obtain the time partition at the predetermined time scale, including: Performing a hierarchical clustering analysis on the time series heat exposure risk spatial distribution layer at the predetermined time scale based on the similarity of the heat exposure risk spatial pattern, and obtaining a specific number of multiple clustering results at different clustering levels; Determine a target clustering level, and define the clustering results according to the time attribute characteristics of the time interval contained in each clustering result under the target clustering level to obtain time partitions under a predetermined time scale; The time partitioning under the predetermined time scale is used to perform spatiotemporal statistics on the heat exposure risk, and obtain the average urban heat exposure risk spatial distribution layer of the time partition under the target time scale, including: Combining the time partitions at different predetermined time scales to obtain the time partitions at the target time scale; Calculate the average heat exposure risk value of each spatial area in the time partition at the target time scale to obtain the average urban heat exposure risk spatial distribution layer in the time partition at the target time scale.

2. The method for determining heat exposure risk time zones according to claim 1, characterized in that: The step of obtaining a time series heat exposure risk spatial distribution layer at a predetermined time scale for a target city within a target period includes: For each predetermined time scale, determining a basic time unit of the predetermined time scale based on the predetermined time scale; Based on the basic time unit, dividing the target period into multiple time intervals of equal length; Determine a basic spatial unit, and divide the target city into multiple spatial areas based on the basic spatial unit; The spatial regions on the heat exposure risk layer in each time interval are sorted to obtain a time series heat exposure risk spatial distribution layer in the predetermined time scale.

3. The method for determining heat exposure risk time zones according to claim 2, characterized in that: The process of sorting the spatial regions on the heat exposure risk layer in each time interval to obtain the time series heat exposure risk spatial distribution layer in the predetermined time scale includes: The spatial regions on the heat exposure risk layer in each time interval are sorted according to the same spatial region order to obtain the time series heat exposure risk spatial distribution layer in the predetermined time scale.

4. The method for determining heat exposure risk time zones according to claim 1, wherein: The paired sample difference test on the spatial distribution layer of the average urban heat exposure risk of the time partition under the target time scale includes: The average urban heat exposure risk values ​​of different time zones in the same spatial area at the target time scale are used as paired samples, and a paired sample difference test is performed on the spatial distribution layer of the average urban heat exposure risk of the time zones at the target time scale.

5. The method for determining heat exposure risk time zones according to claim 1, characterized in that: Determining the reliability of the time partition under the predetermined time scale according to the test result includes: If the significance level test result parameter value is less than a preset significance level test threshold, determining that the time partition under the predetermined time scale is a reliable result under the significance level; If the significance level test result parameter value is not less than a preset significance level test threshold, it is determined that the time partition under the predetermined time scale is an unreliable result under the significance level.

6. A device for determining time zones for heat exposure risk, characterized in that: include: An acquisition module is used to obtain a time series heat exposure risk spatial distribution layer at a predetermined time scale for a target city within a target period; A clustering module is used to perform a hierarchical clustering analysis on the time series heat exposure risk spatial distribution layer at the predetermined time scale based on the similarity of the heat exposure risk spatial pattern, so as to obtain a time partition at the predetermined time scale; A statistical module is used to perform spatiotemporal statistics on heat exposure risks based on the time partitions at the predetermined time scale, and obtain an average urban heat exposure risk spatial distribution layer for the time partitions at the target time scale; A testing module is used to perform a paired sample difference test on the average urban heat exposure risk spatial distribution layer of the time partition at the target time scale, so as to determine the reliability of the time partition at the predetermined time scale according to the test result; The clustering module is specifically used to: Performing a hierarchical clustering analysis on the time series heat exposure risk spatial distribution layer at the predetermined time scale based on the similarity of the heat exposure risk spatial pattern to obtain clustering results at different clustering levels; Determine a target clustering level, and define the clustering results according to the time attribute characteristics of the time series contained in each clustering result under the target clustering level to obtain time partitions under a predetermined time scale; The statistics module is specifically used for: Combining the time partitions at different predetermined time scales to obtain the time partitions at the target time scale; Calculate the average heat exposure risk value of each spatial area in the time partition at the target time scale to obtain the average urban heat exposure risk spatial distribution layer in the time partition at the target time scale.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for determining the time zones of heat exposure risks according to any one of claims 1 to 5 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining the time zones of heat exposure risks according to any one of claims 1 to 5 is implemented.

Images