Urban agglomeration surface heat island intensity assessment method, system, medium and terminal equipment
By evaluating the intensity and causes of urban agglomeration heat islands by enhancing regression tree methods, the assessment problem that the existing technology cannot be applied to urban agglomeration areas is solved, and scientific basis is provided to alleviate heat islands and improve livability.
Patent Information
- Application Number
- CN202110921755.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-08-11
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2041-08-11
AI Technical Summary
The existing urban heat island research is mainly evaluated from the perspective of a single city or several cities. It is not applicable to urban agglomeration areas, and it is difficult to fully understand the causes and intensity of urban agglomeration surface heat islands.
The enhanced regression tree method is used to construct a genesis determination model for urban agglomeration heat islands. By obtaining surface temperature data and potential driver factors, the heat island intensity of urban agglomerations is evaluated, and its genesis mechanism is analyzed, providing scientific basis to alleviate regional heat islands and build livable urban agglomerations.
The assessment of urban agglomerations as an overall regional assessment of heat island intensity and causes provides more detailed spatial information and scientific basis, helping to formulate effective mitigation measures and improve the livability of urban agglomerations.
Smart Images

Figure CN113743740B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a method, system, storage medium and terminal device for evaluating the intensity of surface heat islands in urban agglomerations. Background Art
[0002] With the rapid development of society, the population has also surged, resulting in rapid urbanization. However, rapid urbanization and population growth have also caused a series of environmental problems, among which the urban heat island effect is one of the most significant impacts of human beings on the earth's environment. Urban heat island usually refers to the phenomenon that the temperature of a city is higher than that of the surrounding suburbs or rural areas due to human factors. More and more studies have shown that urban heat islands have a great impact on vegetation growth, water and air quality, urban energy consumption, human thermal comfort and health risks, morbidity and mortality, etc. Therefore, there is an urgent need to better understand the spatial pattern of urban heat islands and the causes of their formation, which is of great significance for formulating appropriate mitigation and adaptation strategies and improving urban livability.
[0003] Current research on urban heat islands is mainly divided into two categories: atmospheric urban heat islands and surface urban heat islands. Among them, the atmospheric urban heat island is generally measured by the measured temperature difference between urban and rural meteorological stations, but due to the limited number of meteorological stations, it is difficult to provide large-scale spatial information. The surface urban heat island is usually quantified by the difference in surface temperature between urban and rural areas observed by satellites, which can obtain high-quality consistency and repeatability data at various temporal and spatial scales. Therefore, the intensity of the surface urban heat island is widely used to indicate the spatiotemporal pattern and characteristics of the urban heat island effect, especially for large-scale areas. In addition, existing studies mainly analyze the urban-rural surface temperature difference of a single city or several large cities by identifying the scope of cities and rural areas, and then evaluate the intensity of the heat island.
[0004] However, since the reduction or even disappearance of distances between cities in an urban agglomeration will significantly change the regional thermal environment, the intensity of the surface heat island in an urban agglomeration is no longer suitable for evaluation from the current mainstream perspective of a single city. Summary of the invention
[0005] Based on this, it is necessary to provide a method, system, storage medium and terminal equipment for evaluating the surface heat island intensity of urban agglomerations, which regards the urban agglomeration as a whole region to evaluate the heat island intensity and analyze the relative importance and marginal effects of its causes, in order to provide a scientific basis for alleviating regional heat islands and building livable urban agglomerations.
[0006] An embodiment of the present invention provides a method for evaluating the intensity of urban surface heat island, the method comprising the following steps:
[0007] Determine a target urban cluster, obtain surface temperature data of the target urban cluster within a target time period, and evaluate the urban heat island intensity of the target urban cluster based on the surface temperature data;
[0008] Screen out potential driving factors that affect the urban heat island of the target urban agglomeration based on the urban agglomeration data of the target urban agglomeration within the target time period, and create a data set of causes of the urban heat island of the target urban agglomeration based on the potential driving factors;
[0009] Based on the evaluation results of the urban agglomeration heat island intensity and the urban agglomeration heat island cause dataset, a model for determining the cause of the urban agglomeration heat island is constructed using the enhanced regression tree method;
[0010] The urban agglomeration heat island cause determination model is run to obtain a cause diagnosis result of the urban agglomeration heat island, and the heat island cause mechanism of the urban agglomeration is determined according to the cause diagnosis result.
[0011] Furthermore, the method of determining a target urban cluster, obtaining the surface temperature data of the target urban cluster within a target time period, and evaluating the urban heat island intensity of the target urban cluster based on the surface temperature data specifically includes:
[0012] Determine the target city cluster and target time period;
[0013] Acquire the surface temperature data inverted based on the remote sensing image of the target urban agglomeration within the target time period;
[0014] Acquire the land use data of the target urban agglomeration, and select the average surface temperature of cultivated land as the reference surface temperature;
[0015] The surface temperature data are mosaicked into annual data through a data management tool, and the heat island intensity of the target urban agglomeration is obtained through a heat island intensity assessment model;
[0016] The heat island intensity level is evaluated according to the heat island intensity of the urban agglomeration.
[0017] Furthermore, the heat island intensity assessment model is:
[0018] UAHII i =LST i -LST ref
[0019] Among them, UAHII i is the heat island intensity of urban cluster pixel i, LST i is the surface temperature of pixel i, LST ref is the reference surface temperature.
[0020] Furthermore, the potential driving factors include climate factors, vegetation factors, socio-economic factors, landscape pattern factors and other factors.
[0021] Furthermore, the climate factor is obtained by selecting the temperature variable and the precipitation variable according to the background climate; the vegetation factor is obtained by the vegetation coverage rate and the vegetation index; the socioeconomic factor is obtained by the population density, GDP, the night light index, the built-up area intensity and the anthropogenic heat emission; the landscape pattern factor is obtained by the indicators related to the landscape composition and the landscape configuration; the other factors include the terrain factors and the surface characteristic factors selected according to the terrain characteristics and the surface characteristics.
[0022] Furthermore, based on the evaluation results of the urban agglomeration heat island intensity and the urban agglomeration heat island cause dataset, a method for constructing a cause determination model of the urban agglomeration heat island using a boosted regression tree method includes:
[0023] Based on the enhanced regression tree method, the evaluation results of the urban heat island intensity and the urban heat island cause data set were input into the gbm.step function in the R language dismo package for N-fold cross-validation, and after M rounds of training, the relative importance of each cause of urban heat island was obtained;
[0024] The partial dependence relationship diagram between the various causes of urban heat island and the preset percentage confidence interval of heat island intensity was drawn by R language ggBRT package to analyze the marginal effects of various causes affecting urban heat island.
[0025] Furthermore, the method for determining the heat island formation mechanism of the urban agglomeration according to the urban agglomeration heat island formation diagnosis result includes:
[0026] According to the diagnosis results of the causes of urban heat island in the urban agglomeration, the relative importance of each cause is obtained, and the dominant factor of urban heat island is obtained;
[0027] Based on the partial dependence relationship diagram between the dominant factors of urban heat island and the intensity of urban heat island, the marginal effect of the dominant factors of urban heat island is obtained, and the threshold value of each factor in the dominant factors of urban heat island affecting the intensity of urban heat island is determined.
[0028] Another embodiment of the present invention proposes a system for evaluating the intensity of surface heat islands in urban agglomerations, which can evaluate the intensity of heat islands in urban agglomerations as a whole region and analyze the relative importance and marginal effects of their causes, providing a scientific basis for alleviating regional heat islands and building livable urban agglomerations.
[0029] The urban agglomeration surface heat island intensity assessment system according to an embodiment of the present invention includes:
[0030] A heat island assessment module is used to determine a target urban cluster, obtain surface temperature data of the target urban cluster within a target time period, and assess the heat island intensity of the target urban cluster based on the surface temperature data;
[0031] A factor screening module is used to screen out potential driving factors that affect the urban heat island of the target urban agglomeration according to the urban agglomeration data of the target urban agglomeration within the target time period, and to create a cause data set of the urban heat island according to the potential driving factors;
[0032] A model building module is used to build a cause determination model of the urban agglomeration heat island by using an enhanced regression tree method based on the evaluation results of the urban agglomeration heat island intensity and the urban agglomeration heat dynamic cause data set;
[0033] The cause diagnosis module is used to run the urban agglomeration heat island cause determination model to obtain the cause diagnosis result of the urban agglomeration heat island, and determine the heat island cause mechanism of the urban agglomeration according to the cause diagnosis result.
[0034] Another embodiment of the present invention further proposes a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the above-mentioned urban agglomeration surface heat island intensity assessment method.
[0035] Another embodiment of the present invention further proposes a terminal device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the above-mentioned method for assessing the surface heat island intensity of an urban agglomeration when executing the computer program.
[0036] The above-mentioned urban agglomeration surface heat island intensity assessment method first determines the target urban agglomeration, obtains the surface temperature data of the target urban agglomeration within the target time period, and assesses the heat island intensity of the target urban agglomeration based on the surface temperature data; screens out the potential driving factors affecting the urban agglomeration heat island based on the urban agglomeration data of the target urban agglomeration within the target time period, and creates the cause data set of the urban agglomeration heat island based on the potential driving factors; based on the assessment results of the urban agglomeration heat island intensity and the urban agglomeration heat island cause data set, uses the enhanced regression tree method to construct the cause determination model of the urban agglomeration heat island; runs the urban agglomeration heat island cause determination model to obtain the cause diagnosis result of the urban agglomeration heat island, and determines the heat island cause mechanism of the urban agglomeration based on the cause diagnosis result. Compared with the prior art, the present invention regards the urban agglomeration as a whole region to assess the heat island intensity and analyzes the relative importance and marginal effect of its causes, which can provide a scientific basis for alleviating regional heat islands and building livable urban agglomerations, and meets the actual application needs. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 A schematic diagram of a flow chart of a method for evaluating the intensity of urban surface heat islands provided by an embodiment of the present invention;
[0038] Figure 2 for Figure 1 Specific flow diagram of step S11;
[0039] Figure 3 An effect diagram for the urban heat island intensity classification;
[0040] Figure 4 This is the result of the analysis of the relative importance of various causes of urban heat islands;
[0041] Figure 5 This is the partial dependence relationship diagram of the causes of urban heat island and the intensity of heat island;
[0042] Figure 6 A structural block diagram of a system for evaluating the intensity of urban surface heat islands provided by an embodiment of the present invention;
[0043] Figure 7 A structural diagram of a terminal device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this technical field without creative work are within the scope of protection of the present invention.
[0045] It should be noted that the step numbers in the text are only for the convenience of explaining the specific embodiment and do not limit the order of execution of the steps. The method provided in this embodiment can be executed by a related server, and the following description will be given by taking the server as the execution subject as an example.
[0046] like Figures 1 to 5 As shown, the method for evaluating the intensity of urban surface heat island provided by the embodiment of the present invention includes steps S11 to S14:
[0047] Step S11, determining a target urban cluster, obtaining surface temperature data of the target urban cluster within a target time period, and evaluating the urban heat island intensity of the target urban cluster based on the surface temperature data.
[0048] As described above, according to actual needs, the surface temperature data of the target urban agglomeration within the target time period is obtained, so as to obtain the heat island intensity of the target urban agglomeration according to the surface temperature data, and to evaluate the heat island intensity level according to the heat island intensity of the urban agglomeration.
[0049] See also Figures 2 to 3 , determining a target urban cluster, obtaining surface temperature data of the target urban cluster within a target time period, and evaluating the heat island intensity of the target urban cluster based on the surface temperature data, specifically comprising:
[0050] Step S111, determining the target city cluster and target time period.
[0051] Specifically, the target city cluster and target time period are determined according to actual needs. In this embodiment, the Guangdong-Hong Kong-Macao Greater Bay Area, one of the three major city clusters in China, is selected as the target city cluster, and the target time period is set to 15 years from 2003 to 2017. This period is the stage of rapid development of the Guangdong-Hong Kong-Macao Greater Bay Area, and its urban heat island effect has attracted widespread attention.
[0052] Step S112, obtaining the surface temperature data inverted based on the remote sensing image of the target urban cluster within the target time period.
[0053] Specifically, since the Aqua satellite of MODIS passes at 13:30 and 1:30 local time, the observed surface temperature data has day and night differences, which can be used to compare the differences between daytime and nighttime heat islands and their causes. Therefore, this embodiment collects surface temperature data through MODIS surface temperature inversion data MYD11A1. However, the present invention is not limited to this, and in other embodiments, it can also be replaced with other image data according to actual application requirements, such as using remote sensing images such as ASTER or Landsat to invert surface temperature.
[0054] Step S113, obtaining the land use data of the target urban agglomeration, and selecting the average surface temperature of cultivated land as the reference surface temperature.
[0055] Specifically, the land use data of the target urban agglomeration is obtained through the regional information of the target urban agglomeration, and the average surface temperature of cultivated land is selected as the reference surface temperature. It is understandable that since the distance between cities in the urban agglomeration is disappearing, and the large number of urban villages around cities in the urbanization process blurs the urban-rural boundary, if the traditional rural or suburban surface temperature is used as the reference temperature to analyze the urban agglomeration heat island, the intensity of the heat island may be underestimated. Cultivated land is generally distributed on the edge of urban and rural areas or in traditional villages, so the surface temperature of cultivated land is more likely to represent the surface temperature of rural areas.
[0056] Step S114: mosaicking the surface temperature data into annual data through a data management tool, and obtaining the heat island intensity of the target urban agglomeration through a heat island intensity assessment model.
[0057] Specifically, the daily surface temperature data of MYD11A1 are mosaicked into annual data through the mosaic function of ArcGISc, and then the target urban agglomeration is regarded as a whole area, and the UAHII is calculated according to the formula i =LST i -LST ref The annual heat island intensity of the urban agglomeration from 2003 to 2017 was calculated, where UAHII i represents the heat island intensity of urban agglomeration pixel i, LST i represents the surface temperature of pixel i, LST ref The reference surface temperature is represented, and finally the heat island intensity calculation results of 15 years are averaged over many years to represent the heat island intensity status of the urban agglomeration. However, the present invention is not limited to this, and the heat island intensity of urban agglomerations at different time scales (such as months, seasons, etc.) can also be calculated according to actual application requirements.
[0058] Step S115, evaluating the heat island intensity level according to the heat island intensity of the urban agglomeration.
[0059] Specifically, the calculation results of the urban heat island intensity are classified into grades, such as: UAHII i ≤ -5℃ is a strong cold island; -5℃ <UAHII i ≤ -3℃ is the second strongest cold island; -3℃ < UAHII i ≤ -1℃ is a weak cold island; -1℃ <UAHII i ≤ 1℃ means no heat island; 1℃ < UAHII i ≤ 3℃ is a weak heat island; 3℃< UAHII i ≤ 5℃ is a secondary heat island; UAHII i > 5℃ is a strong heat island.
[0060] The classification results are as follows Figure 3 As shown, it can be seen that there is no obvious boundary between the cities in the urban agglomeration. Compared with evaluating the heat island intensity from the perspective of a single city, the urban agglomeration heat island intensity assessment method regards the urban agglomeration as a whole and can reveal more spatial details.
[0061] Step S12, screening out potential driving factors that affect the urban heat island of the target urban agglomeration according to the urban agglomeration data of the target urban agglomeration within the target time period, and creating a data set of causes of the urban heat island of the target urban agglomeration according to the potential driving factors.
[0062] Specifically, the data of urban agglomerations are obtained based on the existing research and actual conditions of the target urban agglomerations, and potential driving factors affecting the intensity of urban heat islands are screened out, including climate factors, vegetation factors, socio-economic factors, landscape pattern factors and other factors.
[0063] Furthermore, the meteorological station data of the target urban agglomeration are spatially interpolated by the thin disk spline function of the ANUSPLIN software to obtain the temperature variable and the precipitation variable, and the climate factor is obtained based on the temperature variable and the precipitation variable. The forest coverage rate and vegetation index of the target urban agglomeration are obtained through the MODIS MOD44B and MOD13A3 data, and the vegetation factor is obtained based on the forest coverage rate and the vegetation index. The socioeconomic factor is obtained based on the population density, GDP, night light index, built-up area intensity and anthropogenic heat emissions of the target urban agglomeration; and the socioeconomic factor mainly selects the night light index and built-up area intensity, among which the night light data comes from the National Center for Environmental Information of the United States, and the built-up area intensity is obtained by calculating the proportion of construction land in the land use type by the moving window method. Indicators related to landscape composition and landscape configuration are screened as landscape pattern factors. Since topography and surface features are also related to the formation of heat islands, elevation and surface albedo are selected as topographic factors and surface feature factors, respectively, to obtain the other factors; and elevation and surface albedo are obtained through ASTER's GDEM data and MODIS's MCD43A3 data, respectively. By obtaining the specific data of the above factors and calculating the multi-year average values from 2003 to 2017, the cause data set of the urban agglomeration heat island is established. The above potential causes are only selected for this embodiment, and the factors can be enriched or simplified according to the actual situation of the region.
[0064] Step S13, based on the evaluation result of the urban agglomeration heat island intensity and the urban agglomeration heat island cause dataset, a boosted regression tree method is used to construct a cause determination model for the urban agglomeration heat island.
[0065] Specifically, based on the enhanced regression tree method, the evaluation results of the urban agglomeration heat island intensity and the urban agglomeration heat island cause data set are input into the gbm.step function in the R language dismo package for N-fold cross-validation, and after M rounds of training, the relative importance of each cause of the urban agglomeration heat island is obtained; the partial dependence relationship diagram of each cause of the urban agglomeration heat island and the preset percentage confidence interval of the heat island intensity is drawn through the R language ggBRT package to analyze the marginal effect of each cause of the urban agglomeration heat island.
[0066] For example, see Figures 4 to 5Based on the boosted regression tree method, the “gbm.step” function in the “dismo” package of R language was used to analyze the relative importance of the various causes of the urban heat island in the above mentioned city cluster. The model parameters tree complexity, learning rate and bagging fraction were set to 5, 0.005 and 0.5 respectively, and a 10-fold cross validation was performed. The model was run 100 times and then averaged to eliminate the possible errors caused by random sampling. The results of the relative importance analysis of the various causes of the urban heat island in the above mentioned city cluster are shown in Figure 4 The abbreviations of the causes in the figure are as follows: TEM-temperature, PRE-precipitation, VCF-forest cover, EVI-enhanced vegetation index, NL-night light index, BI-built-up area intensity, DEM-elevation, WSA-surface albedo.
[0067] Furthermore, the “ggBRT” package of R language was used to draw a partial dependence relationship diagram of the various causes of urban heat island and the 95% confidence interval of heat island intensity, and analyze the marginal effect of each cause. The partial dependence relationship diagram can show the relationship between a certain independent variable and the dependent variable when other independent variables take the mean or remain unchanged, so it can be used to analyze the marginal effect of each cause affecting the heat island intensity of the urban agglomeration. The partial dependence relationship diagram of the various causes of urban heat island and heat island intensity is shown in the figure below: Figure 5 As shown in the figure, the abbreviations of the causes are as follows: TEM-temperature, PRE-precipitation, VCF-forest coverage, EVI-enhanced vegetation index, NL-night light index, BI-built-up area intensity, DEM-elevation, WSA-surface albedo. If the forest coverage (VCF) is greater than the threshold of 70%, the intensity of the heat island will no longer decrease, which may be due to the fact that excessive forest coverage will affect ventilation, which has a very important guiding significance for the construction of urban green spaces.
[0068] Step S14, running the urban agglomeration heat island cause determination model to obtain the cause diagnosis result of the urban agglomeration heat island, and determining the heat island cause mechanism of the urban agglomeration according to the cause diagnosis result.
[0069] Specifically, the urban agglomeration heat island cause determination model is run to obtain the cause diagnosis result of the urban agglomeration heat island, and the urban agglomeration heat island dominant factor is obtained according to the cause diagnosis result of the urban agglomeration and the relative importance of each cause; based on the partial dependence relationship diagram between the urban agglomeration heat island dominant factor and the heat island intensity, the marginal effect of the urban agglomeration heat island dominant factor is obtained, and the threshold value of each factor in the urban agglomeration heat island dominant factor affecting the heat island intensity is determined.
[0070] For example, according to the relative importance analysis results of the various causes of urban heat island, three causes, including forest coverage rate (VCF), elevation (DEM) and surface albedo (WSA), which have the greatest impact on the intensity of urban heat island during the day, and three causes, including temperature (TEM), enhanced vegetation index (EVI) and night light index (NL), which have the greatest impact on the intensity of urban heat island at night, are selected as the dominant factors of urban heat island. Based on the partial dependence relationship diagram of the dominant factors of urban heat island and heat island intensity, the marginal effects of these factors are analyzed, the threshold of each factor affecting the intensity of heat island is determined, and the mechanism of heat island formation is revealed.
[0071] It can be understood that the present invention fully considers that the reduction and disappearance of the distance between cities in the urban agglomeration will significantly change the regional thermal environment, regards the urban agglomeration as a whole area, and evaluates the intensity of the surface heat island in the urban agglomeration with the average surface temperature of cultivated land as a reference, and uses the enhanced regression tree model to analyze the relative importance and marginal effects of various causes of urban heat islands in urban agglomerations, thereby solving the existing problem that evaluating urban heat islands from the perspective of a single city is not suitable for urban agglomeration areas, and the current lack of research on the causes and mechanisms of urban heat island formation, in order to provide methodological support for the accurate evaluation of urban heat island effects in urban agglomerations, and at the same time provide scientific guidance for formulating heat island mitigation measures and improving the livability of urban agglomerations.
[0072] The above-mentioned urban agglomeration surface heat island intensity assessment method determines the target urban agglomeration, obtains the surface temperature data of the target urban agglomeration within the target time period, and assesses the heat island intensity of the target urban agglomeration based on the surface temperature data; screens out the potential driving factors affecting the urban agglomeration heat island based on the urban agglomeration data of the target urban agglomeration within the target time period, and creates the cause data set of the urban agglomeration heat island based on the potential driving factors; based on the assessment results of the urban agglomeration heat island intensity and the urban agglomeration heat island cause data set, uses the enhanced regression tree method to construct the cause determination model of the urban agglomeration heat island; runs the urban agglomeration heat island cause determination model to obtain the cause diagnosis result of the urban agglomeration heat island, and determines the heat island cause mechanism of the urban agglomeration based on the cause diagnosis result. Compared with the prior art, the present invention regards the urban agglomeration as a whole region to assess the heat island intensity and analyzes the relative importance and marginal effect of its causes, which can provide a scientific basis for alleviating regional heat islands and building livable urban agglomerations, and meets the actual application needs.
[0073] It should be understood that, although the various steps in the above-mentioned flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above-mentioned flow chart may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.
[0074] like Figure 6 FIG. 1 is a block diagram of a system for evaluating the intensity of urban surface heat island provided by the present invention, wherein the system comprises:
[0075] The heat island assessment module 21 is used to determine a target urban cluster, obtain the surface temperature data of the target urban cluster within a target time period, and assess the heat island intensity of the target urban cluster based on the surface temperature data.
[0076] Furthermore, the heat island assessment module 21 is specifically used to:
[0077] Determine the target city cluster and target time period;
[0078] Acquire the surface temperature data inverted based on the remote sensing image of the target urban agglomeration within the target time period;
[0079] Acquire the land use data of the target urban agglomeration, and select the average surface temperature of cultivated land as the reference surface temperature;
[0080] The surface temperature data are mosaicked into annual data through a data management tool, and the heat island intensity of the target urban agglomeration is obtained through a heat island intensity assessment model;
[0081] The heat island intensity level is evaluated according to the heat island intensity of the urban agglomeration.
[0082] The heat island intensity assessment model is:
[0083] UAHII i =LST i -LST ref
[0084] Among them, UAHII i is the heat island intensity of urban cluster pixel i, LST i is the surface temperature of pixel i, LST ref is the reference surface temperature.
[0085] The factor screening module 22 is used to screen out potential driving factors that affect the urban heat island of the target urban agglomeration according to the urban agglomeration data of the target urban agglomeration within the target time period, and create a cause data set of the urban heat island according to the potential driving factors.
[0086] Among them, the potential driving factors include climate factors, vegetation factors, socio-economic factors, landscape pattern factors and other factors.
[0087] Furthermore, the climate factor is obtained by filtering out temperature variables and precipitation variables based on the background climate; the vegetation factor is obtained by filtering out forest coverage and vegetation index; the socioeconomic factor is obtained by filtering out population density, GDP, night light index, built-up area intensity and anthropogenic heat emissions; the landscape pattern factor is obtained by filtering out indicators related to landscape composition and landscape configuration; and the other factors include terrain factors and surface characteristic factors based on terrain characteristics and surface characteristics.
[0088] The model building module 23 is used to build a model for determining the causes of urban heat islands by using a boosted regression tree method based on the evaluation results of the urban heat island intensity and the urban heat island causes dataset.
[0089] Furthermore, the model building module 23 is specifically used to:
[0090] Based on the enhanced regression tree method, the evaluation results of the urban heat island intensity and the urban heat island cause data set were input into the gbm.step function in the R language dismo package for N-fold cross-validation, and after M rounds of training, the relative importance of each cause of urban heat island was obtained;
[0091] The partial dependence relationship diagram between the various causes of urban heat island and the preset percentage confidence interval of heat island intensity was drawn by R language ggBRT package to analyze the marginal effects of various factors affecting urban heat island.
[0092] The cause diagnosis module 24 is used to obtain the cause diagnosis result of the urban agglomeration according to the urban agglomeration heat island cause determination model, and determine the heat island cause mechanism of the urban agglomeration according to the cause diagnosis result.
[0093] Furthermore, the cause diagnosis module 24 is specifically used to:
[0094] According to the diagnosis results of the causes of the urban agglomeration, the dominant factors of urban heat islands are obtained according to the relative importance of each cause;
[0095] Based on the partial dependence relationship diagram between the dominant factors of urban heat island and the intensity of urban heat island, the marginal effect of the dominant factors of urban heat island is obtained, and the threshold value of each factor in the dominant factors of urban heat island affecting the intensity of urban heat island is determined.
[0096] The urban agglomeration surface heat island intensity assessment system provided by the embodiment of the present invention determines the target urban agglomeration, obtains the surface temperature data of the target urban agglomeration within the target time period, and assesses the heat island intensity of the target urban agglomeration based on the surface temperature data; screens out the potential driving factors affecting the urban agglomeration heat island based on the urban agglomeration data of the target urban agglomeration within the target time period, and creates the cause data set of the urban agglomeration heat island based on the potential driving factors; based on the assessment results of the urban agglomeration heat island intensity and the urban agglomeration heat island cause data set, uses the enhanced regression tree method to construct the cause determination model of the urban agglomeration heat island; runs the urban agglomeration heat island cause determination model to obtain the cause diagnosis result of the urban agglomeration heat island, and determines the heat island cause mechanism of the urban agglomeration based on the cause diagnosis result. Compared with the prior art, the present invention regards the urban agglomeration as a whole region to assess the heat island intensity and analyzes the relative importance and marginal effect of its causes, which can provide a scientific basis for alleviating regional heat islands and building livable urban agglomerations, and meets the actual application needs.
[0097] An embodiment of the present invention further provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located controls the execution of the above-mentioned urban agglomeration surface heat island intensity assessment method.
[0098] The embodiment of the present invention also provides a terminal device, see Figure 7 As shown, it is a structural block diagram of a preferred embodiment of a terminal device provided by the present invention, wherein the terminal device comprises a processor 10, a memory 20, and a computer program stored in the memory 20 and configured to be executed by the processor 10, and the processor 10 implements the above-mentioned urban agglomeration surface heat island intensity assessment method when executing the computer program.
[0099] Preferably, the computer program may be divided into one or more modules / units (such as computer program 1, computer program 2, ...), and the one or more modules / units are stored in the memory 20 and executed by the processor 10 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.
[0100] The processor 10 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor 10 may be any conventional processor. The processor 10 is the control center of the terminal device, and various parts of the terminal device are connected using various interfaces and lines.
[0101] The memory 20 mainly includes a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function, etc., and the data storage area can store related data, etc. In addition, the memory 20 can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, and a flash card (Flash Card), etc., or the memory 20 can also be other volatile solid-state storage devices.
[0102] It should be noted that the above terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 7 The structural block diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the figure, or a combination of certain components, or different components.
[0103] In summary, the method, system, storage medium and terminal device for evaluating the intensity of surface heat island in urban agglomerations provided by the embodiments of the present invention determine the target urban agglomeration, obtain the surface temperature data of the target urban agglomeration within the target time period, and evaluate the intensity of heat island in the target urban agglomeration according to the surface temperature data; screen out the potential driving factors affecting the heat island in the urban agglomeration according to the urban agglomeration data of the target urban agglomeration within the target time period, and create the cause data set of the heat island in the urban agglomeration according to the potential driving factors; based on the evaluation results of the heat island intensity of the urban agglomeration and the cause data set of the heat island in the urban agglomeration, use the enhanced regression tree method to construct the cause determination model of the heat island in the urban agglomeration; run the cause determination model of the heat island in the urban agglomeration to obtain the cause diagnosis result of the heat island in the urban agglomeration, and determine the cause mechanism of the heat island in the urban agglomeration according to the cause diagnosis result. Compared with the prior art, the present invention regards the urban agglomeration as a whole region to evaluate the intensity of the heat island and analyze the relative importance and marginal effect of its causes, which can provide a scientific basis for alleviating regional heat islands and building livable urban agglomerations, and meet the actual application needs.
[0104] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A method for assessing the intensity of urban surface heat island, characterized in that: The method comprises the following steps: Determine a target urban cluster, obtain surface temperature data of the target urban cluster within a target time period, and evaluate the urban heat island intensity of the target urban cluster based on the surface temperature data; specifically include: Determine the target city cluster and target time period; Acquire the surface temperature data inverted based on the remote sensing image of the target urban agglomeration within the target time period; Acquiring the land use data of the target urban agglomeration, and selecting the average surface temperature of the cultivated land as the reference surface temperature; specifically comprising: obtaining the land use data of the target urban agglomeration through regional information of the target urban agglomeration, and selecting the average surface temperature of the cultivated land as the reference surface temperature; The surface temperature data are mosaicked into annual data through a data management tool, the target urban agglomeration is regarded as a whole area, and the urban agglomeration heat island intensity of the target urban agglomeration is obtained through a heat island intensity assessment model; the heat island intensity level is assessed according to the urban agglomeration heat island intensity; Screen out potential driving factors that affect the urban heat island of the target urban agglomeration based on the urban agglomeration data of the target urban agglomeration within the target time period, and create a data set of causes of the urban heat island of the target urban agglomeration based on the potential driving factors; Based on the evaluation results of the urban agglomeration heat island intensity and the urban agglomeration heat island cause dataset, a model for determining the cause of the urban agglomeration heat island is constructed using the enhanced regression tree method; The urban cluster heat island cause determination model is run to obtain a cause diagnosis result of the urban cluster heat island, and the heat island cause mechanism of the urban cluster is determined according to the cause diagnosis result.
2. The method for evaluating the intensity of urban surface heat island according to claim 1, characterized in that: The heat island intensity assessment model is: UAHII i =LST i -LST ref Among them, UAHII i is the heat island intensity of urban cluster pixel i, LST i is the surface temperature of pixel i, LST ref is the reference surface temperature.
3. The method for evaluating the intensity of urban surface heat island according to claim 2, characterized in that: The potential driving factors include climate factors, vegetation factors, socioeconomic factors, landscape pattern factors and other factors.
4. The method for evaluating the intensity of urban surface heat island according to claim 3 is characterized in that: The climate factor is obtained by selecting the temperature variable and precipitation variable according to the background climate; the vegetation factor is obtained by the vegetation coverage rate and the vegetation index; the socioeconomic factor is obtained by the population density, GDP, night light index, built-up area intensity and anthropogenic heat emission; the landscape pattern factor is obtained by indicators related to landscape composition and landscape configuration; the other factors include terrain factors and surface characteristic factors selected according to terrain characteristics and surface characteristics.
5. The method for evaluating the intensity of urban surface heat island according to claim 4, characterized in that: Based on the evaluation results of the urban agglomeration heat island intensity and the urban agglomeration heat island cause data set, a method for constructing a cause determination model of the urban agglomeration heat island using the enhanced regression tree method includes: Based on the enhanced regression tree method, the evaluation results of the urban heat island intensity and the urban heat island cause data set were input into the gbm.step function in the R language dismo package for N-fold cross-validation, and after M rounds of training, the relative importance of each cause of urban heat island was obtained; The partial dependence relationship diagram between the various causes of urban heat island and the preset percentage confidence interval of heat island intensity was drawn by R language ggBRT package to analyze the marginal effects of various causes affecting urban heat island.
6. The method for evaluating the intensity of urban surface heat island according to claim 5, characterized in that: The method for determining the heat island formation mechanism of the urban agglomeration according to the diagnosis result of the heat island formation of the urban agglomeration comprises: According to the diagnosis results of the causes of urban heat island in the urban agglomeration, the relative importance of each cause is obtained, and the dominant factor of urban heat island is obtained; Based on the partial dependence relationship diagram between the dominant factors of urban heat island and the intensity of urban heat island, the marginal effect of the dominant factors of urban heat island is obtained, and the threshold value of each factor in the dominant factors of urban heat island affecting the intensity of urban heat island is determined.
7. A system for assessing the intensity of urban surface heat islands, characterized in that: The system comprises: The heat island assessment module is used to determine the target urban cluster, obtain the surface temperature data of the target urban cluster within the target time period, and assess the heat island intensity of the target urban cluster based on the surface temperature data; specifically includes: Determine the target city cluster and target time period; Acquire the surface temperature data inverted based on the remote sensing image of the target urban agglomeration within the target time period; Acquiring the land use data of the target urban agglomeration, and selecting the average surface temperature of the cultivated land as the reference surface temperature; specifically comprising: obtaining the land use data of the target urban agglomeration through regional information of the target urban agglomeration, and selecting the average surface temperature of the cultivated land as the reference surface temperature; The surface temperature data are mosaicked into annual data through a data management tool, the target urban agglomeration is regarded as a whole area, and the heat island intensity of the target urban agglomeration is obtained through a heat island intensity assessment model; the heat island intensity level is assessed according to the heat island intensity of the urban agglomeration; A factor screening module is used to screen out potential driving factors that affect the urban heat island of the target urban agglomeration according to the urban agglomeration data of the target urban agglomeration within the target time period, and to create a cause data set of the urban heat island according to the potential driving factors; A model building module, for building a cause determination model of the urban agglomeration heat island by using a boosted regression tree method based on the evaluation results of the urban agglomeration heat island intensity and the urban agglomeration heat island cause dataset; The cause diagnosis module is used to run the urban agglomeration heat island cause determination model to obtain the cause diagnosis result of the urban agglomeration heat island, and determine the heat island cause mechanism of the urban agglomeration according to the cause diagnosis result.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program; wherein, when the computer program is run, it controls the device where the computer-readable storage medium is located to execute the urban agglomeration surface heat island intensity assessment method according to any one of claims 1 to 6.
9. A terminal device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method for assessing the intensity of surface heat island in urban agglomerations as claimed in any one of claims 1 to 6 when executing the computer program.
