Urban climate risk monitoring system based on multi-source data fusion and early warning application thereof

Abstract

The invention relates to the technical field of smart cities, in particular to an urban climate risk monitoring system based on multi-source data fusion and early warning application thereof, and the urban climate risk monitoring system comprises a data reconstruction module, a precursor identification module, a trend chain extraction module, a grade assignment module and a risk diffusion module. According to the method, the reliability of multi-source meteorological data is effectively enhanced, the precision of data fusion and the reliability of spatial positioning are improved by carrying out credibility level evaluation on a plurality of data sources, and the sensitivity of risk precursor events and the accuracy of factor propagation prediction are enhanced by utilizing deep identification of trend consistency and response delay relation; according to the method, the regional spatial continuity factors are combined, the stability and spatial continuity of risk grade division are optimized, spatial impedance characteristics are brought into diffusion path prediction, accurate deduction of urban climate risk spatial diffusion paths and dynamic marking of risk regions are realized, and the accuracy and dynamic of urban climate risk monitoring and prevention and control decisions are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of smart cities, and particularly to an urban climate risk monitoring system based on multi-source data fusion and its early warning application. Background Art

[0002] The technical field of smart cities includes various technical means such as the Internet of Things, cloud computing, big data, geographic information systems, remote sensing, and artificial intelligence. By real-time sensing of various types of urban data and fusion analysis of multi-source information, it realizes the monitoring of urban operation status, precise identification of risks, and support for management decision-making. Smart cities take urban information digitization, management decision-making intelligence, and urban governance refinement as the core content, systematically integrating sensing devices from different sources, spatial data acquisition systems, and artificial intelligence analysis platforms, and comprehensively realizing refined urban operation monitoring and risk management.

[0003] Among them, the urban climate risk monitoring system based on multi-source data fusion refers to using satellite remote sensing data, ground meteorological observation data, unmanned aerial vehicle remote sensing data, Internet of Things sensing device data, and social and economic statistical data, and through data fusion analysis methods, precisely identifying and dynamically monitoring urban rainstorm waterlogging, high temperature heat waves, air pollution, and various specific climate risk factors. The system realizes the precise identification and dynamic monitoring of urban climate risks through various methods such as satellite image interpretation, remote sensing image data processing, Internet of Things sensor data acquisition, spatial analysis of geographic information data, and machine learning model training.

[0004] In the actual application process of traditional urban climate risk monitoring technologies, the fusion of multi-source data is limited to simple spatial data overlay analysis, without deeply examining the observation density and credibility of the data sources themselves. The data fusion accuracy is insufficient, and there are biases in the fusion results caused by differences in data credibility. Most of the identifications of urban climate risks focus on single indicators, lacking a detailed analysis of the response relationships between multiple factors, and unable to finely reveal the formation process and triggering paths of urban disasters, reducing the accuracy of disaster identification. The regional risk level assignment depends on the intensity distribution of a single factor, ignoring the spatial continuity and mutual influence relationships between the risk levels of adjacent regions, and the spatial distribution of the risk grading results is unreasonable. When predicting the risk diffusion path, spatial impedance factors such as surface characteristics, building distribution, and terrain differences are rarely comprehensively considered, resulting in the deviation of risk propagation prediction from the actual situation, causing the urban risk management decision-making to be inaccurate, the risk early warning response ability to be insufficient, and increasing the urban management cost and the difficulty of disaster prevention and control. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, the embodiments of the present invention provide an urban climate risk monitoring system based on multi-source data fusion and its early warning application. The technical solutions are as follows:

[0006] On the one hand, a city climate risk monitoring system based on multi-source data fusion is provided. The system includes:

[0007] The data reconstruction module obtains multi-source meteorological monitoring data, extracts the observation density, interval value, and deviation value of multiple data sources, analyzes the credibility levels of multiple data sources, and combines location information to perform data fusion on the multi-source monitoring data to generate a spatially reconstructed data set;

[0008] The precursor identification module calls the spatially reconstructed data set, obtains time series data of various climate factors, marks risk-concerned areas by analyzing the consistency characteristics of the change trends of each type of data in multiple regions, and generates a precursor perturbation trend interval;

[0009] The trend chain extraction module calls the precursor perturbation trend interval, extracts the meteorological factor monitoring sequence data of risk-concerned areas, identifies the response delay relationship between various climate factors by analyzing the change order of each climate factor, identifies the risk propagation trigger order, and generates a risk trend excitation path;

[0010] The level assignment module calls the risk trend excitation path, calculates and adjusts the risk levels of multiple regions according to the change frequency and fluctuation amplitude of the data, by analyzing the change intensity of climate data in multiple regions and combining the spatial continuity between the risk levels of adjacent regions, and generates a risk level spatial distribution value.

[0011] As a further solution of the present invention, the spatially reconstructed data set includes grid position units, fused observation values, and credibility level coefficients. The precursor perturbation trend interval includes a perturbation time period, a perturbation factor type, and a risk-concerned area number. The risk trend excitation path includes a factor trigger order, a response delay time difference, and a trend path number. The risk level spatial distribution value is specifically a level numerical unit, a level change amplitude, and a level continuity index.

[0012] As a further solution of the present invention, the data reconstruction module includes:

[0013] The difference analysis sub-module obtains multi-source meteorological monitoring data, calculates the density value of the observation points of multiple data sources according to the number and spatial distribution of the observation points of multiple data sources, analyzes the observation interval difference of the data sources, and calculates the data value deviation of each data source to generate a data difference coefficient;

[0014] The data source rating sub-module calls the data difference coefficient, and grades and evaluates the credibility of each data source according to the data difference coefficient to identify the credibility level value of each data source;

[0015] The data fusion sub-module calls the trust level values of each data source, calculates the weight coefficients of multiple data sources according to the trust level values, combines the position information corresponding to the meteorological monitoring data, performs data fusion on the multi-source meteorological monitoring data, and establishes a spatially reconstructed data set.

[0016] As a further solution of the present invention, the specific formula for performing data fusion on the multi-source meteorological monitoring data is:

[0017]

[0018] Calculate the fused data value;

[0019] where, V s′ is the fused data value at the spatial position s′, V i′,s′ is the original monitoring value of the i′-th data source at the position s′, C i′ is the trust level value of the i′-th data source, D i′,s′ is the spatial distance value from the monitoring point of the i′-th data source to the spatial position s′, C j′ is the trust level value of the j′-th data source, D j′,s′ is the spatial distance value from the monitoring point of the j′-th data source to the spatial position s′, n′ is the total number of data sources participating in the spatial data fusion, i′ is the index number of each data source in the weighted calculation, j′ is the index number of each data source in the weight normalization calculation, and s′ is the number of the position point to be calculated in the spatial fusion area.

[0020] As a further solution of the present invention, the precursor identification module includes:

[0021] The trend extraction sub-module calls the spatially reconstructed data set, obtains the time series data of each climate factor in multiple regions of the city, and establishes a data change trend curve;

[0022] The consistency analysis sub-module calls the data change trend curve, extracts the fluctuation direction and fluctuation duration of each climate factor trend curve, and analyzes the consistency degree of the fluctuation directions and durations of multiple data trend curves to generate a trend consistency coefficient;

[0023] The region marking sub-module calls the trend consistency coefficient, marks the risk attention regions according to the consistency of the change trends of each meteorological monitoring data, and establishes a precursor disturbance trend interval.

[0024] As a further solution of the present invention, the trend chain extraction module includes:

[0025] The sequence extraction sub-module calls the aforementioned precursor perturbation trend interval, extracts the real-time monitoring sequence values of various climate factors in the area according to the coordinates of the risk concern area, including temperature and humidity, precipitation, and wind speed, arranges the data according to the time stamp, and establishes the factor monitoring sequence data;

[0026] The delay determination sub-module calls the factor monitoring sequence data, calculates the correlation between the numerical changes of each climate factor according to the numerical changes of each data sequence, analyzes the response relationship of various climate factors, and obtains the response delay coefficient;

[0027] The trigger sorting sub-module calls the response delay coefficient, analyzes the trigger order of various climate factors in the risk propagation, and establishes the risk trend excitation path.

[0028] As a further solution of the present invention, the grade assignment module includes:

[0029] The intensity calculation sub-module calls the risk trend excitation path, analyzes the change frequency and fluctuation amplitude of the numerical value according to the numerical change of the climate data in each area, calculates the change intensity value, and obtains the data change intensity information;

[0030] The continuity analysis sub-module calls the data change intensity information, detects the boundary relationship between adjacent areas, analyzes the spatial relationship of the regional risk level by comparing the change intensity between adjacent areas, and obtains the spatial continuity coefficient;

[0031] The grade adjustment sub-module calls the spatial continuity coefficient, calculates the risk level reference value of multiple areas according to the change intensity value, and adjusts the risk level in combination with the spatial relationship of the regional risk level to establish the spatial distribution value of the risk level.

[0032] As a further solution of the present invention, the system further includes:

[0033] The risk diffusion module calls the spatial distribution value of the risk level, obtains the surface material type, building density, and terrain elevation difference of each area, analyzes the spatial impedance characteristics between areas, calculates the spatial diffusion direction and path of the urban climate risk, marks the diffusion risk area, and generates the climate risk prediction result;

[0034] The climate risk prediction result specifically refers to the diffusion direction path, risk impact boundary, and spatial propagation intensity.

[0035] As a further solution of the present invention, the risk diffusion module includes:

[0036] The impedance calculation sub-module calls the spatial distribution value of the risk level, obtains the surface material type, building density, and terrain elevation difference of each region, and calculates the spatial impedance value and establishes a spatial impedance coefficient based on the surface material friction coefficient, building density barrier value, and terrain elevation drop value.

[0037] The specific formula for calculating the spatial impedance value is as follows:

[0038]

[0039] Calculate the comprehensive spatial impedance value;

[0040] Among them, Z t′ represents the comprehensive spatial impedance value of region t′, f t′ represents the average friction coefficient of the surface material in region t′, B t′ represents the building density barrier value in region t′, H max,t′ represents the highest terrain elevation in region t′, H min,t′ represents the lowest terrain elevation in region t′, H avg represents the average value of the elevation differences of all regions, W f represents the weight of the surface material friction coefficient, W b represents the weight of the building density barrier value, W h represents the weight of the terrain elevation drop value, and t′ is the index of the region;

[0041] The direction analysis sub-module calls the spatial impedance coefficient, analyzes the spatial diffusion direction of the climate risk, identifies the diffusion path, and generates a risk diffusion prediction result according to the obstruction intensity of the diffusion risk propagation between multiple regions;

[0042] The path marking sub-module calls the risk diffusion prediction result, marks the diffusion risk area by predicting the spatial diffusion trajectory of the urban climate risk, and establishes a climate risk prediction result.

[0043] On the other hand, a urban climate risk monitoring and early warning application based on multi-source data fusion is provided, and the application is used to carry a urban climate risk monitoring system based on multi-source data fusion.

[0044] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0045] By evaluating the trust levels of multiple data sources, the reliability of multi-source meteorological data is effectively enhanced, the accuracy of data fusion and the reliability of spatial positioning are improved. Through in-depth identification of the relationship between trend consistency and response delay, the sensitivity of risk precursor events and the accuracy of factor propagation prediction are enhanced. Considering regional spatial continuity factors, the stability and spatial continuity of risk level division are optimized. Incorporating spatial impedance characteristics into the prediction of diffusion paths enables precise deduction of the spatial diffusion paths of urban climate risks and dynamic marking of risk areas, enhancing the precision and dynamism of urban climate risk monitoring and prevention and control decisions. Brief Description of the Drawings

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0047] Figure 1 It is the system flowchart of the present invention;

[0048] Figure 2 It is the schematic diagram of the system framework of the present invention. Detailed Embodiments

[0049] The following describes the technical solutions in the present invention with reference to the drawings.

[0050] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to give examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0051] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when not emphasizing their differences, their intended meanings are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when not emphasizing their differences, their intended meanings are the same.

[0052] In the embodiments of the present invention, sometimes subscripts such as W1 may be written in non-subscript form such as W1. When not emphasizing their differences, their intended meanings are the same.

[0053] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0054] An embodiment of the present invention provides an urban climate risk monitoring system based on multi-source data fusion. Please refer to Figures 1 to 2 , the present invention provides a technical solution. The urban climate risk monitoring system based on multi-source data fusion includes:

[0055] The data reconstruction module obtains multi-source meteorological monitoring data, extracts the observation density, interval value, and deviation value of multiple data sources, analyzes the credibility levels of multiple data sources, and combines location information to perform data fusion on the multi-source monitoring data to generate a spatially reconstructed data set.

[0056] The precursor identification module calls the spatially reconstructed data set, obtains the time series data of various climate factors, marks the risk-concerned areas by analyzing the consistency characteristics of the change trends of each type of data in multiple regions, and generates a precursor perturbation trend interval.

[0057] The trend chain extraction module calls the precursor perturbation trend interval, extracts the meteorological factor monitoring sequence data of the risk-concerned areas, identifies the response delay relationship between various climate factors by analyzing the change order of each climate factor, identifies the risk propagation trigger order, and generates a risk trend excitation path.

[0058] The level assignment module calls the risk trend excitation path, calculates and adjusts the risk levels of multiple regions according to the change frequency and fluctuation amplitude of the data, by analyzing the change intensity of the climate data in multiple regions and combining the spatial continuity between the risk levels of adjacent regions, to generate a risk level spatial distribution value.

[0059] The risk diffusion module calls the risk level spatial distribution value, obtains the surface material type, building density, and terrain elevation difference of each region, analyzes the spatial impedance characteristics between regions, calculates the spatial diffusion direction and path of urban climate risk, marks the diffusion risk areas, and generates a climate risk prediction result.

[0060] The spatially reconstructed data set includes grid position units, fused observation values, and credibility level coefficients. The precursor perturbation trend interval includes a perturbation time period, a perturbation factor type, and a risk-concerned area number. The risk trend excitation path includes a factor trigger order, a response delay time difference, and a trend path number. The risk level spatial distribution value specifically refers to level numerical units, a level change amplitude, and a level continuity index. The climate risk prediction result specifically refers to a diffusion direction path, a risk impact boundary, and a spatial propagation intensity.

[0061] The data reconstruction module includes:

[0062] The difference analysis sub-module obtains multi-source meteorological monitoring data, calculates the density values of the observation points of multiple data sources according to the number and spatial distribution of the observation points of multiple data sources, analyzes the observation interval differences of the data sources, and calculates the data value deviations of each data source to generate a data difference coefficient.

[0063] The difference analysis sub-module obtains multi-source meteorological monitoring data, obtains the number and spatial positions of the observation points of each data source in the observation area, divides the observation area into 100 grid cells of equal area, sets the area of each cell to 1 square kilometer, extracts the number of observation points of each data source in each cell, calculates the observation density value, and performs normalization processing in combination with the maximum and minimum observation point densities. Collect the observation time interval values of each data source. For example, data source A is 10 minutes, data source B is 15 minutes, and data source C is 20 minutes. Perform pairwise absolute value difference operations to obtain the time interval difference, and normalize it as the time consistency index. Extract the meteorological observation values of different data sources at the same location and the same time. For example, A is 25.0 °C, B is 26.0 °C, and C is 24.5 °C. First, calculate the average value, and then calculate the deviation of each observation value to obtain the data consistency index. Taking the three indicators as inputs, set the weighting coefficients to the observation density weight of 0.4, the observation time interval weight of 0.3, and the numerical deviation weight of 0.3, and perform weighted synthesis on them to form a data difference coefficient. The calculation formula is as follows:

[0064] D s = 0.4·M s + 0.3·T s + 0.3·P s ;

[0065] Among them, D s is the data difference coefficient of data source s, M s is the normalized observation density index of data source s, T s is the normalized observation interval index of data source s, P s is the normalized numerical deviation index of data source s.

[0066] Set M A = 0.6, T A = 0.2, P A = 0.1, then:

[0067] D A = 0.4·0.6 + 0.3·0.2 + 0.3·0.1 = 0.24 + 0.06 + 0.03 = 0.33;

[0068] Generate a data difference coefficient.

[0069] The data source rating sub-module calls the data difference coefficient, and based on the data difference coefficient, grades the credibility of each data source's data and identifies the credibility level value of each data source;

[0070] The data source rating sub-module calls the data difference coefficient, sets the credibility level interval as a four-level segmentation, and the interval is delimited as: [0, 0.25) is level 1, [0.25, 0.5) is level 2, [0.5, 0.75) is level 3, [0.75, 1.0] is level 4. It reads the difference coefficient of each data source and determines the interval range it falls into, and assigns the corresponding credibility level value. The calculation formula is as follows:

[0071]

[0072] Among them, L s is the credibility level value of data source s, and D s is the data difference coefficient of data source s.

[0073] Set D B = 0.72, then it satisfies 0.5 ≤ D B < 0.75, and the corresponding credibility level is:

[0074] L B = 3;

[0075] Identify the credibility level value of each data source.

[0076] The data fusion sub-module calls the credibility level value of each data source, calculates the weight coefficient of multiple data sources according to the credibility level value, and combines the position information corresponding to the meteorological monitoring data to perform data fusion on the multi-source meteorological monitoring data and establish a spatial reconstruction data set;

[0077] The specific formula for performing data fusion on the multi-source meteorological monitoring data is:

[0078]

[0079] Calculate the fused data value;

[0080] Among them, V s′ is the fused data value at spatial position s′, V i′,s′ is the original monitoring value of the i′-th data source at position s′, C i′ is the credibility level value of the i′-th data source, D i′,s′ is the spatial distance value from the monitoring point of the i′-th data source to spatial position s′, C j′ is the credibility level value of the j′-th data source, D j′,s′The spatial distance value from the monitoring point of the j'-th data source to the spatial position s', n' is the total number of data sources participating in the spatial data fusion, i' is the index number of each data source in the weighted calculation, j' is the index number of each data source in the weight normalization calculation, and s' is the number of the position point to be calculated in the spatial fusion area.

[0081] Formula:

[0082]

[0083] Detailed explanation of the formula and the derivation process of the formula calculation:

[0084] The formula is used to calculate the fused value of multi-source meteorological monitoring data at the spatial position point s', and the result is used to establish the temperature fusion output value at the corresponding position in the spatial reconstruction dataset;

[0085] Meaning and setting values of parameters:

[0086] V s′ Is the fused meteorological value at the position point s';

[0087] C i′ Is the credibility level value of the i'-th data source. Set C1 = 0.9, C2 = 0.6, C3 = 0.3, which reflects the sampling stability and temporal integrity of the data source;

[0088] D i′,s′ Is the distance from the sensor of the i'-th data source to the position point s', in meters. Set D 1,s′ = 120, D 2,s′ = 100, D 3,s′ = 80, which reflects the inhibitory effect of spatial distribution on data weights;

[0089] V i′,s′ Is the original temperature value collected by the i'-th data source near the position point s'. Set as V 1,s′ = 32.0 °C, V 2,s′ = 30.5 °C, V 3,s′ = 31.0 °C;

[0090] n' is the number of data sources participating in the fusion, set to 3;

[0091] i' represents the weight index and normalization index number participating in the calculation;

[0092] s' represents the number of the current position point to be fused;

[0093] Substitute the parameters into the formula for calculation:

[0094]

[0095] 0.0075 + 0.0060 + 0.00375 = 0.01725;

[0096]

[0097] V s′ ≈0.4348×32.0 + 0.3478×30.5 + 0.2174×31.0 = 13.91 + 10.61 +

[0098] 6.74 = 31.26°C;

[0099] The result 31.26 indicates that the representative temperature value after fusing multi-source meteorological monitoring data at the current spatial position point is 31.26°C, and this value is the fusion output value of this point in the spatially reconstructed dataset.

[0100] The precursor identification module includes:

[0101] The trend extraction sub-module calls the spatially reconstructed dataset to obtain the time series data of each climate factor in multiple regions of the city, and establishes a data change trend curve;

[0102] The trend extraction sub-module calls the spatially reconstructed dataset to obtain the time series data of each climate factor in multiple regions of the city, calls the observed values of meteorological factors such as air temperature, wind speed, precipitation, and surface heat flux in a certain urban area in the spatially reconstructed dataset, extracts the observed values of each factor at each hour in chronological order to form multiple groups of factor time series. The extraction process is based on each meteorological factor, and the sampling time span is set to 72 hours to form continuous observed values at 72 time nodes. Combining the time series of each factor, calculate the first-order difference value at each time node to obtain the variable change amplitude. Call the positive and negative changes of the difference value as the fluctuation direction flag, and combine the maximum continuous length of the same fluctuation direction in the continuous time series to construct a trend segment. If a certain meteorological factor continuously shows an upward state within 12 hours, the trend segment direction is upward and the duration is 12 hours. Merge the trend segments of the same type of meteorological factors in all regions to obtain the trend curve of each climate factor in each region. The trend curve is stored according to the region number, with time as the abscissa and the numerical change amplitude as the ordinate to form a continuous change trajectory. Let the value of each node in the trend curve be the meteorological factor value Y of a certain region at time t r,t , then the difference calculation formula for two adjacent moments is:

[0103] ΔY r,t = Y r,t - Y r,t-1 ;

[0104] Among them, ΔY r,t is the change amplitude of region r at time t, Y r,tis the observed value at the current moment, Y r,t-1 is the observed value at the previous moment.

[0105] Set Y r,10 = 25.6, Y r,9 = 24.9, then:

[0106] ΔY r,10 = 25.6 - 24.9 = 0.7;

[0107] It shows that this factor is on an upward trend at this time point. This operation is performed for each factor, each region, and each time point to establish a data change trend curve.

[0108] The consistency analysis sub-module calls the data change trend curve, extracts the fluctuation direction and duration of the trend curve of each climate factor, and analyzes the consistency degree of the fluctuation directions and durations of multiple data trend curves to generate a trend consistency coefficient;

[0109] The consistency analysis sub-module calls the data change trend curve, extracts the fluctuation direction and duration of the trend curve of each climate factor, structurally extracts the trend segments of each climate factor by region, defines the trend segment direction as continuous upward or downward, and the duration as the time length of this trend segment. The extraction method is from the continuous positive difference or negative difference segment in the trend curve, records the start time, end time, and direction type. After obtaining the trend segment combination, according to the trend direction consistency and duration overlap degree of different climate factors in the same time period, calculate the trend consistency coefficient. The trend consistency coefficient is based on the premise of consistent direction and the duration overlap ratio as the weight basis. The formula is as follows:

[0110]

[0111] Among them, C r is the trend consistency coefficient of region r, N is the total number of climate factors, δ f is whether factor f is in the same direction as the main factor in this time period (taking values of 0 or 1), is the overlapping duration of the trend segment of factor f and the trend segment of the main factor, is the total duration of this factor's trend segment.

[0112] Set in region r, among the three factors, the wind speed and air temperature are in the same direction and the overlapping time is 6 hours, the total trend segment is 8 hours, and the precipitation is in the opposite direction, then:

[0113]

[0114] Obtain the trend consistency coefficient.

[0115] The area marking sub-module calls the trend consistency coefficient, marks the risk attention areas according to the consistency of the change trends of each meteorological monitoring data, and establishes the precursor disturbance trend intervals.

[0116] The area marking sub-module calls the trend consistency coefficient, marks the risk areas according to the trend consistency of the climate factors in each area, sets the threshold interval of the consistency coefficient as: less than 0.4 is the area without risk attention, 0.4 to 0.7 is the area with mild attention, and higher than 0.7 is the area with strong attention. Extract the trend consistency coefficient of each area, compare it with the above interval for determination, and map the marking results to the map coordinate system in combination with the spatial position to generate the precursor disturbance trend intervals, forming the area-level spatial distribution data. The judgment criterion uses the following formula:

[0117]

[0118] where, R r is the attention level mark of area r, and C r is the trend consistency coefficient of area r.

[0119] Suppose the trend consistency coefficient of area A is 0.73, then:

[0120] R A = 2;

[0121] It is determined that this area is a strongly concerned area, and the precursor disturbance trend interval is established.

[0122] The trend chain extraction module includes:

[0123] The sequence extraction sub-module calls the precursor disturbance trend interval, extracts the real-time monitoring sequence values of various climate factors in the area according to the coordinates of the risk attention area, including temperature and humidity, precipitation, and wind speed, and arranges the data according to the time stamp to establish the factor monitoring sequence data.

[0124] The sequence extraction sub-module calls the above-mentioned precursor perturbation trend interval, extracts the real-time monitoring values of temperature, humidity, precipitation, and wind speed within the area according to the coordinates of the risk concern area, obtains the temperature, humidity, precipitation, and wind speed data of area A from the start time of risk concern 00:00 to 24:00 the next day, synchronously samples the temperature, humidity, precipitation, and wind speed data at 1-hour time intervals to form continuous observation data. Assume that the temperature in area A at 00:00 is 24.5 °C, the humidity is 80%, the precipitation is 2 mm / h, and the wind speed is 1.5 m / s. Then extract hour by hour until 24 hours, store them separately, call the time stamps corresponding to each of the above meteorological data, and arrange all factor data indexed by time. Assume that in area A, the temperature data at the 5th hour is 25.7 °C, the humidity is 78%, the precipitation is 1.5 mm / h, and the wind speed is 1.2 m / s. Align the data record at the 5th hour with the data in the previous and subsequent time periods for indexing, and execute the above process in sequence until the arrangement of all 24-hour data is completed. During this period, use the extracted temperature, humidity, precipitation, and wind speed data to form a sequence set at continuous time nodes. The data at the t-th moment in each meteorological factor sequence is denoted as X i,t , where i represents the specific climate factor, t represents the time index, and the adjacent point difference of the observed data can be confirmed by the following formula:

[0125] ΔX i,t =X i,t -X i,t-1 ;

[0126] Among them, ΔX i,t is the change amount of the i-th meteorological factor between the t-th moment and the (t - 1)-th moment, X i,t is the observed data at the t-th moment, and X i,t-1 is the observed data at the (t - 1)-th moment. Assume that the temperature at the 5th hour in area A is 25.7 °C and the temperature at the 4th hour is 25.2 °C, then the temperature change is:

[0127] ΔX 温度,5 =25.7 - 25.2=0.5 °C;

[0128] Establish factor monitoring sequence data.

[0129] The delay determination sub-module calls the above-mentioned factor monitoring sequence data, calculates the correlation of the numerical changes between each climate factor according to the numerical changes of each data sequence, analyzes the response relationship of multiple climate factors, and obtains the response delay coefficient;

[0130] The delay determination sub-module calls the factor monitoring sequence data, performs numerical difference calculation on each climate factor sequence respectively according to the numerical value changes of each climate factor in the sequence, extracts the data differences at adjacent moments of each sequence, calls the difference data of temperature, humidity, precipitation, and wind speed within the same time range, calculates the correlation coefficient of the difference values of any two climate factors respectively, and uses the Pearson correlation coefficient calculation formula:

[0131]

[0132] where, R xy is the correlation coefficient of the difference values of meteorological factors x and y, X x,t and X y,t are the difference values of factor x and y at time t respectively, and are the means of the corresponding difference sequences, T is the total time period length. The difference value sequences of temperature and wind speed in region A are the observed difference data for 5 consecutive hours respectively. Among them, the temperature difference value sequences are: 0.4°C, 0.3°C, 0.5°C, 0.2°C, 0.1°C, and the wind speed difference value sequences are: 0.25 m / s, 0.2 m / s, 0.3 m / s, 0.15 m / s, 0.1 m / s. Calculate the mean of the temperature difference sequence

[0133] Calculate the mean of the wind speed difference sequence

[0134]

[0135] Calculate the correlation coefficient R between temperature and wind speed xy :

[0136]

[0137] (0.1)(0.05)+(0)(0)+(0.2)(0.1)+(-0.1)(-0.05)+(-0.2)(-0.1) = 0.005 + 0 + 0.02 + 0.005 + 0.02 = 0.05;

[0138]

[0139] Therefore, the calculated correlation coefficient between temperature and wind speed in area A is 1, which is determined to be strongly correlated. After the correlation calculation, for the two climate factor sequences that reach strong correlation, the numerical difference data of the two climate factors are called and compared hour by hour. Starting from the starting moment, the time point when the first climate factor shows an obvious change (the numerical difference is greater than the set change threshold, for example, the temperature difference value exceeds 0.3°C) is used as the starting reference point. Continuously check the numerical change of the difference value of the other climate factor hour by hour, and record the time point when this factor shows an obvious change (the wind speed difference value exceeds the set change threshold, for example, exceeds 0.2 m / s). Subsequently, call the two time points for comparison of numerical magnitudes, and subtract the time of the factor with the earlier obvious change from the time of the factor with the later obvious change to obtain the time difference between the two factors, which is the response delay coefficient. For example, set the obvious change threshold temperature to 0.3°C and the wind speed to 0.2 m / s. In area A, the temperature difference value at the 3rd hour is 0.5°C, exceeding the temperature threshold of 0.3°C, so it is determined that the temperature factor shows an obvious change first. And at the 4th hour, the wind speed difference value exceeds the threshold for the first time and reaches 0.25 m / s. At this time, the obvious change in wind speed is 1 hour later than the obvious change in temperature. Therefore, the response delay coefficient between temperature and wind speed is determined to be 1 hour.

[0140] The trigger sorting sub-module calls the response delay coefficient to analyze the trigger order of various climate factors in risk propagation and establish a risk trend excitation path;

[0141] The trigger sorting sub-module calls the response delay coefficient, calls the response delay coefficients between temperature and humidity, precipitation, and wind speed, and performs a comparison of the numerical magnitudes of the response delay coefficients between climate factors. The one with the smaller value is judged to respond earlier, and the one with the larger value is judged to be relatively lagged, thereby clarifying the trigger sorting relationship between factors. Assume that the temperature-wind speed delay coefficient in area A is 0.5 h, the precipitation-wind speed delay coefficient is 2 h, and the temperature-precipitation delay coefficient is 1 h. Then, arrange the trigger order in ascending order of delay time. First, determine that the shortest delay time is temperature-wind speed, which is triggered first at 0.5 hours, followed by temperature-precipitation with a 1-hour delay, and finally precipitation-wind speed with a 2-hour delay. Call the trigger sorting relationship corresponding to each climate factor, structure the propagation order of climate risks in this area according to the trigger order, form a continuous trigger link between risk factors, record the evolution path relationship of risk factors in the area according to the sorting order of the trigger link, and store it in the form of a data chain of trigger sequence, thereby establishing a risk trend excitation path.

[0142] The level assignment module includes:

[0143] The intensity calculation sub-module calls the risk trend excitation path, analyzes the change frequency and fluctuation amplitude of the numerical values according to the change situation of the climate data numerical values in each region, calculates the change intensity value, and obtains the data change intensity information;

[0144] The intensity calculation sub-module calls the risk trend excitation path. According to the temperature, humidity, precipitation, and wind speed monitoring data in Region A, it calls the hourly monitoring values within 24 hours, calculates the difference magnitude of each item of data within each hour, accumulates the absolute value of the difference and divides it by the number of data within the time period to obtain the fluctuation amplitude. Suppose the temperature data in Region A is 24.5°C at the 1st hour, 25.0°C at the 2nd hour, and 25.7°C at the 3rd hour, and the differences are 0.5°C and 0.7°C respectively. Then the temperature fluctuation amplitude is (0.5 + 0.7) / 2 = 0.6°C. It calls the number of data changes within the same time period, and takes the number of times the numerical difference exceeds the corresponding threshold within the unit time as the change frequency. Suppose the temperature change threshold is 0.3°C. Then both differences in Region A exceed the threshold, and the change frequency is 2 times. Multiply the fluctuation amplitude by the change frequency to obtain the change intensity value. The calculation formula is:

[0145] I = F × A;

[0146] Among them, I is the change intensity value, F is the change frequency, and A is the fluctuation amplitude. Taking the above temperature data as an example, the change frequency F = 2, and the fluctuation amplitude A = 0.6°C. Substitute into the formula:

[0147] I = 2 × 0.6 = 1.2;

[0148] After performing the same calculation process for temperature, humidity, precipitation, and wind speed respectively and then summarizing, the data change intensity information is obtained.

[0149] The continuity analysis sub-module calls the data change intensity information, detects the boundary relationship between adjacent regions, analyzes the spatial relationship of the regional risk levels by comparing the change intensities between adjacent regions, and obtains the spatial continuity coefficient;

[0150] The continuity analysis sub-module calls the data change intensity information. According to the boundary coordinates of Region A, it obtains the boundary coordinates of the adjacent Region B, performs position matching on the boundary coordinates to confirm the boundary relationship between the regions, calls the change intensity values corresponding to Region A and Region B. Suppose the change intensity of Region A is 1.2 and the change intensity of Region B is 0.8. Perform a comparison of the magnitudes of the change intensity values of the two regions, calculate the absolute value of the difference in the change intensities of the two regions and divide it by the mean value of the change intensity values of the two regions to obtain the spatial continuity coefficient. The specific formula is:

[0151]

[0152] Among them, C is the spatial continuity coefficient, I A is the change intensity of Region A, IB Let \(I\) be the change intensity of region B, and substitute the above assumed data:

[0153]

[0154] The value of this spatial continuity coefficient is between 0 and 1. It is set that when the coefficient is between 0 and 0.3, the spatial continuity is strong; when it is between 0.3 and 0.7, the continuity is medium; when it is above 0.7, the continuity is weak. Therefore, the spatial continuity between region A and region B is medium, and the spatial continuity coefficient is obtained.

[0155] The level adjustment sub-module calls the spatial continuity coefficient, calculates the risk level benchmark values of multiple regions according to the change intensity values, and adjusts the risk levels in combination with the spatial relationship of the regional risk levels to establish the spatial distribution value of the risk levels;

[0156] The level adjustment sub-module calls the spatial continuity coefficient. It is set that the benchmark value of the regional risk level is obtained by calculating the change intensity value. First, call the change intensity values of three factors: temperature, precipitation, and wind speed. Weighted sum the change intensity values of the three factors according to the preset weight coefficients. The weight coefficients are set as 0.4 for temperature, 0.3 for precipitation, and 0.3 for wind speed. For example, the temperature change intensity value of region A is \(0.5^{\circ}C\), the precipitation change intensity value is \(1.2mm / h\), and the wind speed change intensity value is \(0.8m / s\). The calculation formula for the risk level benchmark value is:

[0157] \(L = 0.4\times T+0.3\times R + 0.3\times W\);

[0158] Where \(L\) is the risk level benchmark value, and \(T\), \(R\), and \(W\) are the change intensity values of temperature, precipitation, and wind speed respectively. After substituting the data, we get:

[0159] \(L = 0.4\times0.5 + 0.3\times1.2+0.3\times0.8 = 0.2 + 0.36+0.24 = 0.8\);

[0160] Then call the spatial relationship of the risk levels of adjacent regions. Through the numerical comparison of the regional spatial continuity coefficient and the regional risk level benchmark value, for pairs of regions where the continuity coefficient is greater than or equal to 2.5, if the difference in the regional risk level benchmark values exceeds 0.3, then increase the risk level benchmark value of the region with the lower benchmark value by 0.1 until the difference is less than or equal to 0.3. For example, the spatial continuity coefficient of region A and region B is 2.7, the risk level benchmark value of A is 0.8, and the risk level benchmark value of B is 1.2. Then the risk level benchmark value of region A is adjusted to 0.9. After completing the adjustment of all adjacent region risk level benchmark values, the spatial distribution value of the risk levels is formed.

[0161] The risk diffusion module includes:

[0162] The impedance calculation sub-module calls the risk level spatial distribution value, obtains the surface material type, building density, and terrain elevation difference of each area, and calculates the spatial impedance value based on the surface material friction coefficient, building density barrier value, and terrain elevation drop value, and establishes a spatial impedance coefficient.

[0163] The specific formula for calculating the spatial impedance value is as follows:

[0164]

[0165] Calculate the spatial comprehensive impedance value;

[0166] Among them, Z t′ represents the spatial comprehensive impedance value of area t′, f t′ represents the average friction coefficient of the surface material in area t′, B t′ represents the building density barrier value in area t′, H max,t′ represents the highest terrain elevation of area t′, H min,t′ represents the lowest terrain elevation of area t′, H avg represents the average value of the elevation differences of all areas, W f represents the weight of the surface material friction coefficient, W b represents the weight of the building density barrier value, W h represents the weight of the terrain elevation drop value, and t′ is the index of the area.

[0167] Formula:

[0168]

[0169] Detailed explanation of the formula and the derivation process of the formula calculation:

[0170] The formula is used to calculate the spatial comprehensive impedance value of each area in the city, and the result is used to measure the degree of obstruction during the spread of climate risk in this area.

[0171] Parameter meaning and setting value:

[0172] f t′ is the surface material friction coefficient of the area, set to 0.65;

[0173] W f is the weight of the surface material friction coefficient, set to 0.3;

[0174] B t′ is the building density barrier value of the area, set to 0.42;

[0175] W b is the weight of the building density barrier value, set to 0.4;

[0176] H max,t′is the highest elevation of this area, set at 82 meters;

[0177] H min,t′ is the lowest elevation of this area, set at 56 meters;

[0178] H avg is the average value of the elevation difference within the overall urban area, set at 24 meters;

[0179] W h is the weight of the terrain elevation drop value, set at 0.3;

[0180] Substitute the parameters into the formula for calculation:

[0181]

[0182] The result 0.688 indicates that the spatial impedance value of this area is in the medium to high range. The spatial impedance value can be used for sorting or classification marking, as the boundary judgment criterion in the process of identifying the risk propagation trend path. Subsequently, in the direction analysis, it can be compared with the impedance values of surrounding areas to determine the priority propagation path.

[0183] The direction analysis sub-module calls the spatial impedance coefficient, analyzes the hindrance intensity of the diffusion risk propagation among multiple regions, analyzes the spatial diffusion direction of the climate risk, identifies the diffusion path, and generates a risk diffusion prediction result;

[0184] The direction analysis sub-module calls the spatial impedance coefficient, analyzes the hindrance intensity of the diffusion risk propagation among multiple regions, and gradually determines the diffusion path:

[0185] Call the spatial impedance coefficients of any two adjacent regions, and calculate the absolute difference between the impedance coefficients of the two regions:

[0186] R = |Z1 - Z2|;

[0187] Among them, R is the impedance difference between regions, and Z1 and Z2 are the spatial impedance coefficients of two adjacent regions respectively.

[0188] Taking region C and region D as examples, assuming the impedance coefficient of region C is 21.115 and that of region D is 18.275, the calculation is as follows:

[0189] R = |21.115 - 18.275| = 2.84;

[0190] Judge the diffusion hindrance intensity according to the impedance difference. When the impedance difference is in the range of 0 - 1, it is defined as low hindrance; when it is in the range of 1 - 3, it is medium hindrance; when it is greater than 3, it is high hindrance. In the example, the impedance difference between region C and region D is 2.84, belonging to medium hindrance intensity.

[0191] Further call the spatial distribution value of the risk level. Assume that the risk level of area C is 4 and the risk level of area D is 2. When the difference in risk levels is more than 1 and the obstruction intensity is at a low or medium level, it is determined that the risk can spread from the high-level area to the low-level area. Therefore, it is determined that the risk spreads from area C to area D, and the diffusion path is identified and the risk diffusion prediction result is generated.

[0192] The path marking sub-module calls the risk diffusion prediction result, marks the diffusion risk area by predicting the spatial diffusion trajectory of the urban climate risk, and establishes the climate risk prediction result.

[0193] The path marking sub-module calls the risk diffusion prediction result and gradually determines the diffusion trajectory of the risk area:

[0194] Call the central coordinates of the diffusion starting point area and the diffusion direction area. Assume that the central coordinates of the starting area are (x s , y s ) = (30, 40), and the central coordinates of the direction area are (x d , y d ) = (42, 55), and calculate the length of the diffusion trajectory:

[0195]

[0196] where L is the length of the diffusion trajectory, (x s , y s ) is the central point coordinates of the starting area, and (x d , y d ) is the central point coordinates of the diffusion direction area.

[0197] Substitute the above data:

[0198]

[0199] Call the diffusion trajectory line and overlay the urban spatial grid. According to the grids passed by the diffusion trajectory line, determine the corresponding urban grid numbers, and further call these grid numbers for area marking. Mark the area covered by the trajectory as the diffusion risk area, and finally establish the climate risk prediction result.

[0200] The urban climate risk monitoring and early warning application based on multi-source data fusion is used to carry the urban climate risk monitoring system based on multi-source data fusion.

[0201] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0202] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be understood specifically by referring to the context before and after.

[0203] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0204] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0205] Those of ordinary skill in the art will realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0206] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0207] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0208] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0209] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0210] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0211] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An urban climate risk monitoring system based on multi-source data fusion, characterized in that, The system includes: The data reconstruction module obtains multi-source meteorological monitoring data, extracts the observation density, interval value, and deviation value of multiple data sources, analyzes the credibility levels of multiple data sources, and combines location information to perform data fusion on the multi-source monitoring data to generate a spatially reconstructed data set; The precursor identification module calls the spatially reconstructed data set, obtains the time series data of various climate factors, marks the risk-concerned areas by analyzing the consistency characteristics of the change trends of each type of data in multiple regions, and generates a precursor perturbation trend interval; The trend chain extraction module calls the precursor perturbation trend interval, extracts the meteorological factor monitoring sequence data of the risk-concerned areas, identifies the response delay relationships between various climate factors by analyzing the change order of each climate factor, identifies the risk propagation trigger order, and generates a risk trend excitation path; The level assignment module calls the risk trend excitation path, calculates and adjusts the risk levels of multiple regions according to the change frequency and fluctuation amplitude of the data, by analyzing the change intensity of the climate data in multiple regions and combining the spatial continuity between the risk levels of adjacent regions, and generates a spatial distribution value of the risk level.

2. The urban climate risk monitoring system based on multi-source data fusion according to claim 1, characterized in that, The spatially reconstructed data set includes grid position units, fused observation values, and credibility level coefficients. The precursor perturbation trend interval includes a perturbation time period, a perturbation factor type, and a risk-concerned area number. The risk trend excitation path includes a factor trigger order, a response delay time difference, and a trend path number. The spatial distribution value of the risk level is specifically a level numerical unit, a level change amplitude, and a level continuity index.

3. The urban climate risk monitoring system based on multi-source data fusion according to claim 1, characterized in that, The data reconstruction module includes: The difference analysis sub-module obtains multi-source meteorological monitoring data, calculates the density values of the observation points of multiple data sources according to the number and spatial distribution of the observation points of multiple data sources, analyzes the observation interval differences of the data sources, and calculates the data value deviations of each data source to generate a data difference coefficient; The data source rating sub-module calls the data difference coefficient, and grades and evaluates the credibility of each data source's data according to the data difference coefficient to identify the credibility level value of each data source; The data fusion sub-module calls the credibility level value of each data source, calculates the weight coefficients of multiple data sources according to the credibility level value, and combines the location information corresponding to the meteorological monitoring data to perform data fusion on the multi-source meteorological monitoring data to establish a spatially reconstructed data set.

4. The urban climate risk monitoring system based on multi-source data fusion according to claim 3, characterized in that, The specific formula for performing data fusion on the multi-source meteorological monitoring data is: Calculate the fused data value; Among them, V s′ is the fused data value at the spatial position s′, V i′,s′ is the original monitoring value of the i′-th data source at the position s′, C i′ is the trust level value of the i′-th data source, D i′,s′ is the spatial distance value from the monitoring point of the i′-th data source to the spatial position s′, C j′ is the trust level value of the j′-th data source, D j′,s′ is the spatial distance value from the monitoring point of the j′-th data source to the spatial position s′, n′ is the total number of data sources participating in the spatial data fusion, i′ is the index number of each data source in the weighted calculation, j′ is the index number of each data source in the weight normalization calculation, and s′ is the number of the position point to be calculated in the spatial fusion area.

5. The urban climate risk monitoring system based on multi-source data fusion according to claim 1, characterized in that, The precursor identification module includes: The trend extraction sub-module calls the spatially reconstructed data set, obtains the time series data of each climate factor in multiple regions of the city, and establishes a data change trend curve; The consistency analysis sub-module calls the data change trend curve, extracts the fluctuation direction and fluctuation duration of each climate factor trend curve, and analyzes the degree of consistency of the fluctuation directions and durations of multiple data trend curves to generate a trend consistency coefficient; The area marking sub-module calls the trend consistency coefficient, marks the risk-concerned areas according to the consistency of the change trends of each meteorological monitoring data, and establishes a precursor perturbation trend interval.

6. The urban climate risk monitoring system based on multi-source data fusion according to claim 1, characterized in that, The trend chain extraction module includes: The sequence extraction sub-module calls the above-mentioned precursor disturbance trend interval, extracts the real-time monitoring sequence values of various climate factors in the region according to the coordinates of the risk attention area, including temperature and humidity, precipitation, and wind speed, arranges the data according to the time stamp, and establishes the factor monitoring sequence data; The delay determination sub-module calls the above-mentioned factor monitoring sequence data, calculates the correlation of the numerical changes between each climate factor according to the numerical changes of each data sequence, analyzes the response relationship of various climate factors, and obtains the response delay coefficient; The trigger sorting sub-module calls the above-mentioned response delay coefficient, analyzes the trigger order of various climate factors in the risk propagation, and establishes the risk trend excitation path.

7. The urban climate risk monitoring system based on multi-source data fusion according to claim 1, characterized in that, The above-mentioned level assignment module includes: The intensity calculation sub-module calls the above-mentioned risk trend excitation path, analyzes the change frequency and fluctuation range of the numerical values according to the numerical changes of the climate data in each region, calculates the change intensity value, and obtains the data change intensity information; The continuity analysis sub-module calls the above-mentioned data change intensity information, detects the boundary relationship between adjacent regions, analyzes the spatial relationship of the regional risk levels by comparing the change intensities between adjacent regions, and obtains the spatial continuity coefficient; The level adjustment sub-module calls the above-mentioned spatial continuity coefficient, calculates the risk level reference values of multiple regions according to the change intensity values, combines the spatial relationship of the regional risk levels to adjust the risk levels, and establishes the spatial distribution value of the risk levels.

8. The urban climate risk monitoring system based on multi-source data fusion according to claim 1, characterized in that The above-mentioned system further includes: The risk diffusion module calls the above-mentioned spatial distribution value of the risk levels, obtains the surface material type, building density, and terrain elevation difference of each region, analyzes the spatial impedance characteristics between regions, calculates the spatial diffusion direction and path of the urban climate risk, marks the diffusion risk regions, and generates the climate risk prediction result; The above-mentioned climate risk prediction result specifically refers to the diffusion direction path, risk impact boundary, and spatial propagation intensity.

9. The urban climate risk monitoring system based on multi-source data fusion according to claim 1, characterized in that, The above-mentioned risk diffusion module includes: The impedance calculation sub-module calls the above-mentioned spatial distribution value of the risk levels, obtains the surface material type, building density, and terrain elevation difference of each region, and calculates the spatial impedance value based on the surface material friction coefficient, building density barrier value, and terrain elevation drop value, and establishes the spatial impedance coefficient; The specific formula for calculating the above-mentioned spatial impedance value is: Calculate the comprehensive spatial impedance value; Among them, Z t′ represents the spatial comprehensive impedance value of area t′, f t′ represents the average friction coefficient of the surface material in area t′, B t′ represents the building density barrier value in area t′, H max,t′ represents the highest terrain elevation of area t′, H min,t′ represents the lowest terrain elevation of area t′, H avg represents the average value of the elevation differences of all areas, W f represents the weight of the friction coefficient of the surface material, W b represents the weight of the building density barrier value, W h represents the weight of the terrain elevation drop value, and t′ is the index of the area; The direction analysis sub-module calls the above-mentioned spatial impedance coefficient, analyzes the spatial diffusion direction of the climate risk according to the obstacle intensity of the diffusion risk propagation between multiple regions, identifies the diffusion path, and generates the risk diffusion prediction result; The path marking sub-module calls the above-mentioned risk diffusion prediction result, marks the diffusion risk regions by predicting the spatial diffusion trajectory of the urban climate risk, and establishes the climate risk prediction result.

10. Urban climate risk monitoring and early warning application based on multi-source data fusion, characterized in that, The above-mentioned application is used to carry the urban climate risk monitoring system based on multi-source data fusion according to any one of the above 1-9.

Images