A smart city environment management method and system based on digital twinning

Abstract

The present application belongs to the technical field of smart city, and particularly relates to a smart city environment management method and system based on digital twinning. The method not only realizes high-precision collection of species distribution, vegetation coverage, ground temperature and wind speed data in the urban area, but also successfully simulates the dynamic changes of ground thermal radiation absorption and release caused by the increase and decrease of different species by constructing a dynamic spatial model containing species-environment interaction. Further, by calculating the hourly influence coefficient and iteratively deriving the microclimate evolution trend in a ten-year period, a priority ranking scheme for species protection or regulation is finally generated. This method greatly improves the understanding depth and response speed of urban managers on ecological environment changes, makes real-time calibration based on the latest monitoring data possible, and ensures the scientificity and foresight of urban management decisions.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of smart city, and particularly relates to a smart city environment management method and system based on digital twinning. BACKGROUND

[0002] In the current practice of smart city management, environmental monitoring and biodiversity protection mainly rely on traditional ground sensor networks and periodic manual surveys. Although these methods can provide basic data support, they have significant shortcomings in terms of real-time and comprehensiveness. Specifically, traditional methods are difficult to dynamically capture the complex changes of species distribution and their impact on microclimate in urban ecosystems, especially in terms of changes in ground heat radiation absorption and release caused by species increase and decrease, and lack effective quantitative means.

[0003] The general scheme of the prior art is as follows:

[0004] Data collection: Collect basic meteorological parameters such as ground temperature and wind speed through fixed-position sensor networks, and obtain species distribution and vegetation coverage information through manual field investigation. Data analysis: Use statistical methods to analyze the collected data to try to establish a simple correlation model between species distribution and local climate change. Application limitations: Due to low data update frequency and limited spatial resolution, existing methods are difficult to accurately simulate the specific impact of different species increase and decrease on urban microclimate, which in turn limits the ability to develop scientific and reasonable species protection or regulation strategies.

[0005] How to efficiently and accurately simulate the impact of species change in urban areas on ground heat radiation absorption and release, and predict long-term microclimate evolution trends, so as to provide scientific basis for urban planners to optimize biodiversity and microclimate management strategies is a problem to be solved at present. SUMMARY

[0006] The purpose of the present application is to provide a smart city environment management method and system based on digital twinning, which can more effectively cope with the microclimate fluctuations caused by species change and promote the sustainable development of the city, to solve the problems raised in the background art.

[0007] To achieve the above purpose, the present application adopts the following technical scheme: A smart city environment management method based on digital twinning, comprising the following steps:

[0008] Collecting data of species distribution, vegetation coverage, ground temperature and wind speed in urban areas, constructing a dynamic spatial model containing species-environment interaction relationship based on the collected data; simulating the dynamic changes of ground heat radiation absorption and release caused by the increase and decrease of different species according to the dynamic spatial model, calculating the hourly influence coefficient of the dynamic changes on microclimate parameters in the region; iteratively deriving the ten-year evolution trend of the average annual temperature, humidity and wind environment of the region caused by the change of species through the hourly influence coefficient, generating a priority ranking scheme for species protection or regulation according to the evolution trend; matching and calibrating the priority ranking scheme with real-time monitored species migration and environmental data, outputting the calibrated biodiversity-microclimate collaborative optimization strategy and updating the parameters of the dynamic spatial model.

[0009] Preferably, the collecting data of species distribution, vegetation coverage, ground temperature and wind speed in urban areas comprises:

[0010] Setting up multiple monitoring points in the selected area of the city, and installing sensors at each monitoring point to measure ground temperature and wind speed;

[0011] For each monitoring point, taking pictures by a drone, and identifying vegetation coverage by image analysis, the method of calculating vegetation coverage is based on the proportion of the number of green vegetation pixels to the total number of pixels in the entire image;

[0012] Based on the images, using a machine learning classifier to identify the distribution of different species in the images, and determining the frequency of occurrence of each known species;

[0013] Integrating the data of ground temperature, wind speed, vegetation coverage and species distribution frequency of the monitoring points into a database.

[0014] Preferably, the constructing a dynamic spatial model containing species-environment interaction relationship based on the collected data comprises:

[0015] According to the data of ground temperature, wind speed, vegetation coverage and species distribution frequency, calculating the environmental comprehensive index of each monitoring point;

[0016] Using the environmental comprehensive index, combined with the species distribution frequency, establishing a relationship expression associated with environmental factors for each species;

[0017] Based on the relationship expression, integrating the data of all monitoring points to form an overall urban environment interaction network, where the nodes represent the monitoring points, and the weight of the edges is determined by the difference in relationship value between the two adjacent points;

[0018] Mapping the data in the urban environment interaction network to a geographic information system to generate a visual dynamic spatial display map.

[0019] Preferably, the dynamic spatial model simulates the dynamic changes of ground heat radiation absorption and release caused by the increase or decrease of different species, including:

[0020] Based on the urban environment interaction network, the current distribution density of species at each monitoring point is determined, and the ground heat radiation absorption rate of each species at the monitoring point is calculated;

[0021] For the case of species increase or decrease, the distribution density at the monitoring point is updated, and the new distribution density is adjusted when the number of species increases or decreases;

[0022] According to the new distribution density, the ground heat radiation release rate is recalculated.

[0023] Preferably, the hourly impact coefficient of the dynamic changes on the microclimate parameters in the region is calculated, including:

[0024] Based on the ground heat radiation absorption rate and release rate, the basic microclimate parameter set of each monitoring point is first determined, including temperature, humidity and wind speed;

[0025] According to the basic microclimate parameter set and the new distribution density caused by the increase or decrease of species, the hourly microclimate adjustment amount is calculated to reflect the hourly impact of ground heat radiation absorption and release on microclimate;

[0026] Introducing the time variable, for any given time point, the microclimate parameter set is updated to quantify the impact over time;

[0027] The hourly impact coefficient is calculated to evaluate the long-term impact of species increase or decrease by comparing the changes of microclimate parameters at different time points.

[0028] Preferably, the ten-year evolution trend of the annual average temperature, humidity and wind environment in the region caused by the change of species is iteratively derived through the hourly impact coefficient, including:

[0029] Based on the hourly impact coefficient, the daily average impact coefficient is first calculated to obtain the basic data of the diurnal microclimate parameter change;

[0030] Using the daily average impact coefficient, the annual average impact coefficient is calculated to quantify the microclimate parameter variation caused by species change within a year;

[0031] For a ten-year period, the change amount of microclimate parameters in the region is updated year by year to evaluate the long-term impact;

[0032] The change amount of microclimate parameters in each year is accumulated to obtain the total change amount of microclimate parameters during the ten-year period, which is used to determine the ten-year evolution trend of the annual average temperature, humidity and wind environment in the region caused by the change of species.

[0033] Preferably, the priority ranking scheme of species protection or regulation is generated according to the evolution trend, including:

[0034] Based on the total microclimate parameter change amount of the ten-year period, first determine the importance score of each species on the microclimate impact;

[0035] Combined with the importance score and the distribution density, calculate the comprehensive impact value of each species to evaluate the overall influence of the species in the region and its specific contribution to the microclimate;

[0036] According to the comprehensive impact value, all species are ranked from high to low according to their values to form a preliminary priority list;

[0037] An adjustment factor is introduced to consider the ecological value of the species, and the adjusted priority is calculated to generate the final species protection or regulation priority ranking scheme.

[0038] Preferably, the priority ranking scheme is matched and calibrated with real-time monitoring of species migration and environmental data, including:

[0039] Based on the final priority ranking scheme, first obtain real-time monitoring data including species migration rate and current environmental parameters, and calculate the actual impact change rate of each species according to the real-time monitoring data;

[0040] An adjustment factor is introduced to reflect the influence of the actual impact change rate on the priority ranking scheme, and the updated priority is calculated to dynamically adjust the priority ranking scheme;

[0041] The updated priority is combined with real-time map data in the geographic information system to generate a map view containing the latest species distribution, migration trend and environmental conditions.

[0042] Preferably, the calibrated biodiversity-microclimate collaborative optimization strategy is output and the parameters of the dynamic spatial model are updated, including:

[0043] Based on the updated priority and real-time map data, first calculate the optimization adjustment amount of each species to quantify the adjustment amplitude of each species under the new strategy;

[0044] According to the optimization adjustment amount, determine the specific protection or regulation measures for each species to ensure that the effective allocation of resources matches the needs of the key protected species;

[0045] Integrate the specific protection or regulation measures into a comprehensive strategy document containing adjustment information of all species and corresponding measures;

[0046] The comprehensive strategy document is used to update parameters in the dynamic space model, and the updated parameters are re-input into the geographic information system to continuously improve the dynamic space model.

[0047] In another aspect, the present application provides a smart city environment management system based on digital twinning, comprising:

[0048] A data acquisition and preliminary analysis module is configured to acquire species distribution, vegetation coverage, land surface temperature and wind speed data in a city area, and construct a dynamic space model containing species-environment interaction based on the acquired data.

[0049] A microclimate impact assessment module is configured to simulate the dynamic changes of land surface thermal radiation absorption and release caused by different species changes based on the dynamic space model, and calculate the hourly impact coefficient of the dynamic changes on the microclimate parameters in the area.

[0050] A priority ranking module is configured to iteratively derive the ten-year evolution trend of the average annual temperature, humidity and wind environment in the area caused by species changes based on the hourly impact coefficient, and generate a priority ranking scheme for species protection or regulation based on the evolution trend.

[0051] A strategy output module is configured to match and calibrate the priority ranking scheme with real-time monitored species migration and environmental data, output the calibrated biodiversity-microclimate co-optimization strategy and update the parameters of the dynamic space model.

[0052] The technical effects and advantages of the present application are as follows:

[0053] The present application provides a smart city environment management method and system based on digital twinning, which has the following advantages compared with the prior art: BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 The flowchart of the present application based on digital twinning smart city environment management method;

[0055] Figure 2 A block diagram of a smart city environment management system based on digital twinning. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The specific embodiments described herein are only used to explain the present application, and are not used to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0057] The present application provides a smart city environment management method based on digital twinning as shown in Figure 1 The method greatly improves the understanding depth and response speed of city managers to ecological environment changes, makes real-time calibration based on the latest monitoring data possible, and ensures the scientificity and foresight of city management decisions, as follows:

[0058] In the present embodiment, a smart city environment management method based on digital twinning comprises the following steps:

[0059] Step 1: Collecting species distribution, vegetation coverage, surface temperature and wind speed data in the urban area; specifically comprising the following steps:

[0060] A plurality of monitoring points are set in the selected area of the city, and a sensor is installed at each monitoring point to measure the surface temperature T (in Celsius) and wind speed V (in meters / second) in the area; these basic meteorological parameters are important basis for understanding the urban microclimate, and are helpful for subsequent analysis of the interaction between species and environment.

[0061] For each monitoring point, an image is taken by a drone, and the vegetation coverage G (percentage) in the image is identified using image analysis, and the calculation formula is where the number of green pixels represents the number of pixels of green vegetation, and the total number of pixels represents the total number of pixels of the entire image; the formula is based on image processing technology, and estimates the vegetation coverage by distinguishing the ratio of the number of green vegetation pixels to the total number of pixels in the image.

[0062] Based on the image, a machine learning classifier is used to identify the distribution of different species S in the image. In this step, for each known species The frequency F is given by This formula is used to quantify the frequency of a particular species appearing in the image, and the distribution density is determined by counting the proportion of each species in all species.

[0063] The data on surface temperature T, wind speed V, vegetation coverage G, and species distribution frequency F at the monitoring points are integrated into a database so that the data can be used for comprehensive analysis in subsequent steps.

[0064] Step 2: Construct a dynamic spatial model containing species-environment interactions based on the collected data; specifically including the following steps:

[0065] Based on data of surface temperature T, wind speed V, vegetation cover G, and species distribution frequency F, the comprehensive environmental index E (dimensionless) for each monitoring point is calculated using the following formula: ,in Representing a specific species, this formula calculates an index that comprehensively reflects environmental conditions by weighted averaging of surface temperature and wind speed, combined with vegetation cover and species distribution frequency. Here, T, V, and G can be considered relative scores on their respective dimensions, rather than absolute physical quantities.

[0066] When calculating the comprehensive environmental index E, surface temperature T and wind speed V should first be converted or standardized so that they can be compared on the same scale. Common methods include using z-score standardization or min-max normalization techniques to make T and V dimensionless, which will not be elaborated here.

[0067] Using the comprehensive environmental index E, combined with the species distribution frequency For each species, establish an expression R relating it to environmental factors, which is: This is used to describe the interaction between different species and their environment; R represents the strength of the relationship between a species and its environment. This formula combines the comprehensive environmental index with the species distribution frequency in a product form to quantify the strength of the relationship between each species and its environment.

[0068] Based on expression R, data from all monitoring points are integrated to form a unified urban environment interaction network N, where nodes represent monitoring points, and the weight W of an edge is determined by the distance between adjacent points. The difference in value determines, that is Here, i and j represent different monitoring points; the formula determines the weight of edges in the network by calculating the difference in the strength of species-environment relationship between adjacent monitoring points, thereby constructing an urban environment interaction network.

[0069] Finally, the data in the urban environment interaction network N is mapped onto the geographic information system (GIS) to generate a visualized dynamic spatial display map. The dynamic spatial display map generated by the GIS platform can be used to monitor and analyze changes in the city's ecological environment in real time.

[0070] Step 3: Simulate the dynamic changes in the absorption and release of surface thermal radiation caused by the increase or decrease of different species based on the dynamic spatial model; specifically including the following steps:

[0071] Based on the urban environmental interaction network N, the species at each monitoring point are determined. The current distribution density D (number of individuals per unit area), where A represents the coverage area of ​​the monitoring point; this formula is derived by measuring the distribution frequency of a specific species at the monitoring point. Divide by the coverage area A of the monitoring point to calculate the distribution density D.

[0072] Calculate the surface thermal radiation absorptivity of each species at the monitoring points. The formula is Here R is an expression The simplified form of the formula represents the reflectance between a species and its environment; the formula calculates the surface thermal radiation absorption rate by multiplying by (1-R) ​​to account for the influence of the reflectance between the species and its environment. The higher the value, the stronger the species' ability to absorb surface heat radiation in that area.

[0073] For information on species increase or decrease, update the distribution density D' at the monitoring points. When the number of species increases or decreases, the new density... , where ΔD represents the density change caused by the increase or decrease in the number of species; the formula directly updates the distribution density by adding the change caused by the increase or decrease in the number of species to the original distribution density.

[0074] According to the new distribution density Recalculate the surface heat radiation emission rate Using formula ,in It is the surface temperature of the species. The average temperature of the surrounding air is used to calculate the surface heat radiation release rate by multiplying the difference between the species surface temperature and the average temperature of the surrounding air by the new distribution density.

[0075] Step 4: Calculate the hourly impact coefficient of the dynamic changes on the microclimate parameters within the region; specifically including the following steps:

[0076] Based on surface thermal radiation absorptivity and release rate First, determine the set of basic microclimate parameters for each monitoring point. It includes temperature T, humidity H, and wind speed V, and the formula is: This formula defines a set of basic microclimate parameters, including three key meteorological elements: temperature T (degrees Celsius), humidity H (percentage), and wind speed V (meters per second). The base microclimate parameter set represents the initial environmental conditions at each monitoring point.

[0077] According to the base microclimate parameter set And the new distribution density caused by species increase or decrease The hourly microclimate adjustment amount ΔM is calculated, and the formula is To reflect the hourly impact of surface thermal radiation absorption and release on microclimate; this formula calculates the difference between the surface thermal radiation absorption rate A_r and the release rate , and multiplies it by the new distribution density , and then divides it by 24 hours to quantify the hourly microclimate adjustment amount.

[0078] Introducing the time variable t, for any given time point t, update the microclimate parameter set The formula is , Represent the microclimate parameter value at time t, thereby quantifying the impact over time; this formula calculates the microclimate parameter set at a specific time point t by adding the base microclimate parameter set To the hourly microclimate adjustment amount ΔM multiplied by the time variable t.

[0079] Calculate the hourly impact coefficient I by comparing the changes in microclimate parameters at different time points to assess the long-term impact of species increase or decrease, using the formula To measure the percentage change in microclimate parameters relative to the initial state; I represents the hourly impact coefficient; this formula calculates the difference between the microclimate parameter set at a specific time point t And the initial microclimate parameter set , then divide by And multiply by 100% to quantify the percentage change in microclimate parameters.

[0080] Step five: derive the ten-year evolution trend of the regional average temperature, humidity, and wind environment caused by species changes through the hourly impact coefficient; specifically including the following steps:

[0081] Based on the hourly impact coefficient I, first calculate the daily average impact coefficient The formula is Where t represents hours, to obtain the basic data of daily microclimate parameter changes; this formula calculates the daily average impact coefficient by averaging the hourly impact coefficient I at each hour of the day.

[0082] Using the daily average impact coefficient Calculate the annual average impact coefficient The formula is where d represents the number of days, quantifying the annual microclimate parameter variation due to species change; d is a time variable from 1 to 365 days. This formula is used to evaluate the annual microclimate parameter variation due to species change.

[0083] For a ten-year period, the annual average impact coefficient is updated annually, and the microclimate parameter variation in the area is calculated as where is the base microclimate parameter set, used to evaluate the long-term impact; represents the annual microclimate parameter variation; this formula calculates the annual microclimate parameter variation by multiplying the base microclimate parameter set by , reflecting the cumulative impact of species change on the microclimate parameter.

[0084] Finally, the microclimate parameter variation of each year is accumulated to obtain the total microclimate parameter variation over a ten-year period, calculated as where y represents the year, used to determine the ten-year trend of species change on the annual temperature, humidity, and wind environment in the area; y is a year variable from 1 to 10 years. This formula is used to summarize the overall impact of species change on the microclimate parameter over ten years.

[0085] Step six: generating a priority ranking scheme for species protection or regulation based on the trend; specifically including the following steps:

[0086] Based on the total microclimate parameter variation over a ten-year period, the importance score of each species on the microclimate is first determined, calculated as where i represents a specific species, quantifying its importance by comparing the microclimate variation caused by each species; this formula calculates the importance score by taking the ratio of the annual microclimate parameter variation to the total microclimate parameter variation over a ten-year period, and accumulating these ratios to evaluate the impact of each species on the microclimate.

[0087] Combining the importance score and the distribution density D, the comprehensive impact value C of each species is calculated as to evaluate the overall impact of the species in the area and its specific contribution to the microclimate; this formula calculates the comprehensive impact value C by multiplying the importance score of the species by its distribution density D, reflecting the importance and impact of the species in the area.

[0088] According to the comprehensive impact value C, all species are ranked by their values from high to low to form a preliminary priority list L, where The species with the highest comprehensive impact value are represented, and so on, to ensure that resource allocation and management measures can focus on the most influential species;

[0089] Finally, an adjustment factor is introduced to consider the ecological value of the species (such as rarity, irreplaceability, etc.), and the adjusted priority is calculated by the formula , so as to generate the final species protection or regulation priority ranking scheme; the formula calculates the adjusted priority by adding the comprehensive impact value C to the adjustment factor multiplied by the ecological value to more comprehensively consider the multiple attributes of the species.

[0090] Step seven: match and calibrate the priority ranking scheme with real-time monitoring of species migration and environmental data; specifically including the following steps:

[0091] Based on the final priority ranking scheme , first obtain real-time monitoring data Z, including species migration rate and current environmental parameters (temperature T, humidity H, wind speed V), the formula is ; this formula defines the real-time monitoring data set Z, which contains the species migration rate and the current environmental parameters such as temperature T, humidity H and wind speed V.

[0092] According to the real-time monitoring data Z, calculate the actual impact change rate of each species , the formula is , where is the adjusted priority value, is the corresponding comprehensive impact value; this formula calculates the actual impact change rate by multiplying the species migration rate by the adjusted priority value and dividing by the comprehensive impact value .

[0093] An adjustment factor is introduced to reflect the impact of the actual impact change rate on the priority ranking scheme, and the updated priority is calculated by the formula , where is calculated according to the species migration rate is determined after comparison with the preset threshold Th, if , then = 1, otherwise = 0.5, to dynamically adjust the priority ranking scheme; the formula adjusts the priority ranking scheme by introducing a calibration factor , which is determined according to the species migration rate in relation to the preset threshold Th. If the migration rate exceeds the threshold, a larger calibration factor is used, and vice versa.

[0094] Finally, the updated priority is combined with real-time map data in the GIS system to generate a map view containing the latest species distribution, migration trend, and environmental conditions, to facilitate city managers to make decisions based on the latest biodiversity-microclimate co-optimization strategy, and continuously track the effects of species protection or regulation measures;

[0095] Step eight: output the calibrated biodiversity-microclimate co-optimization strategy and update the parameters of the dynamic spatial model, including the following steps:

[0096] Based on the updated priority and real-time map data, first calculate the optimization adjustment amount of each species , the formula is , where is the adjusted priority value, to quantify the adjustment magnitude of each species under the new strategy; the formula calculates the optimization adjustment amount by comparing the difference between the updated priority and the adjusted priority and converting it to a percentage form.

[0097] According to the optimization adjustment amount , determine the specific protection or regulation measures for each species, the measure strength L is determined by the formula , where is an adjustment factor considering ecological value, to ensure that the allocation of resources matches the needs of the key protected species; the formula calculates the measure strength L by multiplying the optimization adjustment amount by the adjustment factor considering ecological value , to ensure effective allocation of resources.

[0098] Integrate the specific protection or regulation measures into a comprehensive strategy document D, containing adjustment information for all species and their corresponding measures, expressed as where n represents the total number of species in the region; the formula is used to calculate the protection or regulation measures for all species The cumulative strategy document D is generated by adding up all the information about the species in the region.

[0099] Finally, the parameters in the dynamic spatial model are updated using the comprehensive strategy document D, and the updated value U is calculated by the formula where N is the urban environment interaction network; the updated parameters are re-input into the GIS system to continuously improve the dynamic spatial model and support future decision-making processes. The formula averages the comprehensive strategy document D and the urban environment interaction network N to generate a new parameter update value U, which is used to update the dynamic spatial model.

[0100] In another aspect, the present application proposes a smart city environment management system based on digital twinning, as shown in Figure 2 The system includes:

[0101] A data collection and preliminary analysis module is used to collect data on species distribution, vegetation coverage, surface temperature, and wind speed in the urban area, and to build a dynamic spatial model containing species-environment interaction relationships based on the collected data.

[0102] A microclimate impact assessment module is used to simulate the dynamic changes in ground heat radiation absorption and release caused by changes in different species based on the dynamic spatial model, and to calculate the hourly impact coefficient of the dynamic changes on the microclimate parameters in the region.

[0103] A priority ranking module is used to iteratively derive the ten-year evolution trend of the average temperature, humidity, and wind environment in the region caused by changes in species based on the hourly impact coefficient, and to generate a priority ranking scheme for species protection or regulation based on the evolution trend.

[0104] A strategy output module is used to match and calibrate the priority ranking scheme with real-time monitored species migration and environmental data, output the calibrated biodiversity-microclimate co-optimization strategy, and update the parameters of the dynamic spatial model.

[0105] In addition, each of the above modules is also used to implement other steps of the above-mentioned smart city environment management method based on digital twinning, as follows:

[0106] Step 1: Data collection

[0107] Three monitoring points A, B, and C are set up in a city park, and sensors are installed to measure the surface temperature and wind speed. At the same time, images of the park are taken using a drone, and the vegetation coverage and species distribution are identified through image analysis.

[0108] Monitoring Point A: Surface Temperature = 25, Wind Speed = 3, Vegetation Coverage = 60, Species S1 Frequency = 25.

[0109] Monitoring Point B: Surface Temperature = 28, Wind Speed = 2, Vegetation Coverage = 60, Species S1 Frequency = 28.

[0110] Monitoring Point C: Surface Temperature = 24, Wind Speed = 4, Vegetation Coverage = 55.56, Species S1 Frequency = 27.27%.

[0111] These data are integrated into a database, preparing for subsequent steps. The above-mentioned temperature, wind speed, and vegetation coverage are considered as relative scores in their respective dimensions, rather than absolute physical quantities.

[0112] Step Two: Building Dynamic Spatial Models

[0113] Based on the data from the first step, the Environmental Comprehensive Index E for each monitoring point is calculated, and an expression R between the species and the environment is established. For example:

[0114] For Monitoring Point A, ;

[0115] Expression ;

[0116] Next, based on the data from all monitoring points, a city environment interaction network N is formed and mapped onto the GIS system to generate a visual dynamic spatial display chart.

[0117] Step Three: Simulating the Impact of Species Increase / Decrease on Heat Radiation

[0118] Suppose the number of species S1 at Monitoring Point A decreases by 5 units, the distribution density is updated and the surface heat radiation absorption and release rates are recalculated. For example, if the original distribution density is 50 per square meter, the new distribution density = 45 per square meter. Based on this, the new surface heat radiation absorption and release rates are calculated.

[0119] Step Four: Calculating Hourly Impact Coefficients

[0120] Based on the new distribution density and heat radiation absorption and release rates, a set of basic microclimate parameters is determined , and then the hourly microclimate adjustment amount ΔM is calculated. For example, at Monitoring Point A, if the initial temperature is 25, the humidity is 60, and the wind speed is 3, the hourly microclimate adjustment amount can be calculated, and further the hourly impact coefficient I can be obtained.

[0121] Step Five: Predicting Ten-Year Evolution Trends

[0122] Based on the hourly influence coefficient, the daily and annual average influence coefficient is calculated, and the microclimate parameter change in ten years is evaluated. For example, the annual microclimate parameter change amount is calculated , and the total microclimate parameter change amount in ten years is accumulated .

[0123] Step six: generate priority ranking scheme

[0124] Based on the microclimate parameter change amount in ten years, the importance score of each species is determined , and the comprehensive influence value C is calculated combined with the distribution density. For example, the importance score of species S1 is 1 (hypothetical), and the distribution density is 50 / m2, so the comprehensive influence value C=50. According to the comprehensive influence value, the species are ranked, and the adjustment factor is introduced to consider the ecological value, and finally the priority ranking scheme is generated.

[0125] Step seven: real-time calibration

[0126] Get real-time monitoring data, including species migration rate and current environmental parameters, calculate the actual influence change rate , and adjust the priority ranking scheme accordingly. For example, if the migration rate of species S1 is 0.6, the adjusted priority P'' will be adjusted accordingly.

[0127] Step eight: output optimization strategy

[0128] Finally, based on the updated priority, calculate the optimization adjustment amount , and develop specific protection or control measures. For example, for species S1, if the optimization adjustment amount is 1.20%, then the corresponding protection measure intensity L=1.20%*adjustment factor. Integrate all measures into the comprehensive strategy document, and update the dynamic space model parameters.

[0129] In this way, city managers can more scientifically understand the changes in the ecological environment of the park, take timely and effective protection and control measures, and promote the sustainable development of the city.

[0130] Finally, it should be pointed out that: the above only for the preferred embodiments of the present application, and not for the limitation of the present application, although the present application is described in detail with reference to the foregoing embodiments, for those skilled in the art, it still can modify the technical scheme recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features, any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application, should be included in the protection scope of the present application.

Claims

1. A digital-twin-based smart city environment management method, characterized by, The method comprises the following steps: Collecting data on species distribution, vegetation coverage, ground temperature and wind speed in urban areas, and constructing a dynamic spatial model containing species-environment interaction based on the collected data; Simulating the dynamic changes of ground thermal radiation absorption and release caused by the increase or decrease of different species based on the dynamic spatial model, and calculating the hourly influence coefficient of the dynamic changes on the microclimate parameters in the region, including: Based on the surface heat radiation absorption rate and release rate , first determine the basic microclimate parameter set of each monitoring point , including temperature T, humidity H and wind speed V, formula ; According to the base microclimate parameter set And the new distribution density caused by the increase and decrease of species , Calculate the microclimate adjustment amount per hour , The formula is To reflect the hourly impact of ground thermal radiation absorption and release on microclimate; Introducing the time variable t, for any given point in time t, the microclimate parameter set is updated , with the formula , representing the microclimate parameter value at time t; The hourly impact coefficient I was calculated to assess the long-term impact of the species addition and removal by comparing the changes in microclimate parameters at different time points using the formula , where I represents the hourly impact coefficient, and the percentage change in the microclimate parameters relative to the initial state was measured. Deriving the ten-year evolution trend of the region's average temperature, humidity and wind environment caused by species changes through the hourly influence coefficient, including: Based on the hourly influence coefficient I, the daily average influence coefficient is calculated first , the formula is where t represents the hour, thus obtaining the basic data of the daily microclimate parameter change; The daily average impact coefficient is calculated using the formula The annual average impact coefficient is calculated using the formula The formula is d is the number of days, thereby quantifying the microclimate parameter variation due to species change over a year; For a ten-year period, the annual average impact factor is used to update the amount of change in the microclimate parameters within the region year by year, according to the formula where is the base set of microclimate parameters, with which the long-term impact is assessed; The annual microclimate parameter change amount is added up to obtain the total microclimate parameter change amount during ten years , the formula is to determine the ten-year evolution trend of the annual average temperature, humidity and wind environment of the region; y is the year variable from 1 to 10; Generating a priority ranking scheme for species protection or regulation based on the evolution trend; Matching and calibrating the priority ranking scheme with real-time monitored species migration and environmental data, outputting the calibrated biodiversity-microclimate co-optimization strategy and updating the parameters of the dynamic spatial model.

2. The digital-twin-based smart city environment management method of claim 1, wherein, The collection of data on species distribution, vegetation coverage, ground temperature and wind speed in urban areas includes: Setting up multiple monitoring points in selected urban areas, each equipped with sensors to measure ground temperature and wind speed; For each monitoring point, taking pictures with a drone and using image analysis to identify vegetation coverage, the method of calculating vegetation coverage is based on the proportion of the number of green vegetation pixels to the total number of pixels in the entire image; Based on the image, use a machine learning classifier to identify the distribution of different species in the image and determine the frequency of occurrence of each known species; Integrate the data on ground temperature, wind speed, vegetation coverage and species distribution frequency of the monitoring points into a database.

3. The method according to claim 2, wherein, The construction of a dynamic spatial model containing species-environment interaction based on the collected data includes: Based on the data of ground temperature, wind speed, vegetation coverage and species distribution frequency, calculate the environmental comprehensive index of each monitoring point; Using the environmental comprehensive index, combined with the species distribution frequency, establish a relationship expression between each species and environmental factors for each species; Based on the relationship expression, integrate the data of all monitoring points to form a whole urban environment interaction network, where the nodes represent the monitoring points and the weights of the edges are determined by the difference in relationship values between adjacent two points; Map the data in the urban environment interaction network to the geographic information system to generate a visual dynamic spatial display map.

4. The method according to claim 3, wherein, Simulating the dynamic changes of ground thermal radiation absorption and release caused by the increase or decrease of different species based on the dynamic spatial model includes: Based on the urban environment interaction network, determine the current distribution density of species on each monitoring point and calculate the ground thermal radiation absorption rate of each species on the monitoring point; For the increase or decrease of species, update the distribution density on the monitoring point, and adjust the new distribution density when the number of species increases or decreases; Recalculate the ground thermal radiation release rate based on the new distribution density.

5. The digital-twin-based smart city environment management method of claim 4, wherein, Generating a priority ranking scheme for species protection or regulation based on the evolution trend includes: Based on the total microclimate parameter change amount in the ten-year period, first determine the importance score of each species on the microclimate; In combination with the importance score and the distribution density, a comprehensive impact value of each species is calculated to evaluate the overall influence of the species in the region and its specific contribution to the microclimate; According to the comprehensive impact value, all species are ranked in order of their values from high to low to form a preliminary priority list; An adjustment factor is introduced to consider the ecological value of the species, and the adjusted priority is calculated to generate a final species protection or regulation priority ranking scheme.

6. The digital-twin-based smart city environment management method of claim 5, wherein, The priority ranking scheme is matched and calibrated with real-time monitored species migration and environmental data, including: Based on the final priority ranking scheme, real-time monitoring data, including species migration rate and current environmental parameters, are first obtained, and the actual impact change rate of each species is calculated based on the real-time monitoring data; An adjustment factor is introduced to reflect the influence of the actual impact change rate on the priority ranking scheme, and the updated priority is calculated to dynamically adjust the priority ranking scheme; The updated priority is combined with real-time map data in the geographic information system to generate a map view containing the latest species distribution, migration trend and environmental conditions.

7. The digital-twin-based smart city environment management method of claim 6, wherein, The calibrated biodiversity-microclimate collaborative optimization strategy is output and the parameters of the dynamic spatial model are updated, including: Based on the updated priority and real-time map data, the optimization adjustment amount of each species is first calculated to quantify the adjustment amplitude of each species under the new strategy; According to the optimization adjustment amount, specific protection or regulation measures for each species are determined to ensure that the effective allocation of resources matches the needs of the priority protected species; The specific protection or regulation measures are integrated into a comprehensive strategy document containing the adjustment information of all species and their corresponding measures; The comprehensive strategy document is used to update the parameters in the dynamic spatial model, and the updated parameters are re-input into the geographic information system to realize continuous improvement of the dynamic spatial model.

8. A digital-twin-based smart city environment management system for implementing the method according to any one of claims 1-7, characterized by, including: Data collection and preliminary analysis module for collecting species distribution, vegetation coverage, land surface temperature and wind speed data in urban areas, and constructing a dynamic spatial model containing species-environment interaction based on the collected data; Microclimate impact evaluation module for simulating the dynamic changes of land surface heat radiation absorption and release caused by the increase or decrease of different species based on the dynamic spatial model, and calculating the hourly impact coefficient of the dynamic changes on the microclimate parameters in the region; Priority ranking module for iteratively deriving the ten-year evolution trend of the annual mean temperature, humidity and wind environment of the region caused by the change of species based on the hourly impact coefficient, and generating a priority ranking scheme for species protection or regulation according to the evolution trend; Strategy output module for matching and calibrating the priority ranking scheme with real-time monitored species migration and environmental data, outputting the calibrated biodiversity-microclimate collaborative optimization strategy and updating the parameters of the dynamic spatial model.

Images