Urban ecological environment design method and system based on digital twinning

Abstract

The invention discloses an urban ecological environment design method and system based on digital twinning, and relates to the technical field of urban ecological environment design, and the method specifically comprises the following steps: determining a water body management target and environmental conditions of an urban central park, and building a digital twinning model for simulating the pollutant diffusion and accumulation effect during seasonal rainfall; pollutant accumulation information of the urban central park during seasonal rainfall is collected in real time, and the collected pollutant accumulation information is transmitted to the digital twinborn model through the data interface; analyzing the pollutant accumulation information input into the digital twinborn model, and evaluating the pollutant accumulation risk level of the urban central park during seasonal rainfall; and according to an evaluation result, determining potential influence of pollutant accumulation on water quality, and starting corresponding water quality management measures. According to the invention, the problem of water quality deterioration caused by pollutant accumulation during seasonal rainfall is solved, and real-time monitoring and dynamic management of water quality are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of urban ecological environment design, and in particular to an urban ecological environment design method and system based on digital twins. Background Art

[0002] Urban ecological environment design refers to the systematic consideration of ecological environment factors in the process of urban planning and construction, and the optimization of the natural environment and human living space of the city through scientific methods and technical means to achieve the goal of sustainable development. The necessity of designing the urban ecological environment lies in that with the acceleration of urbanization, reasonable ecological environment design can alleviate the environmental pressure brought by urbanization, improve key ecological elements such as air quality, water resource management, and green space distribution, and improve the quality of life of residents. Urban ecological environment design based on digital twins refers to the use of digital twin technology to construct a virtual simulation model of the urban ecological environment through real-time collection and integration of multi-source ecological data, so as to accurately evaluate the ecological impact of different design schemes and realize dynamic monitoring and adjustment during construction and operation. The advantage of this method is that it can achieve more refined and intelligent ecological management, help optimize urban environmental design, and ensure the sustainable development and ecological balance of the city.

[0003] The existing urban ecological environment design technology based on digital twins designs the urban ecological environment in a refined manner through multiple steps. First, various ecological data in the city, such as air quality, water quality, soil moisture, vegetation coverage and meteorological data, are collected comprehensively and in real time using sensor networks, remote sensing technology, drones and IoT devices. After strict data cleaning, integration and fusion, these data are used to construct a high-precision digital twin model that truly reflects the current status of the urban ecological environment. Next, designers and planners use this digital twin model to simulate and analyze different areas and design schemes in the city to evaluate the impact of each design scheme on the ecological environment, including the improvement effect of air quality, water resource management efficiency, changes in vegetation coverage, and mitigation of the heat island effect. Based on these simulation results, designers can optimize the scheme, balance the relationship between urban development and ecological protection through multi-objective optimization algorithms, and finally select the optimal scheme. In addition, during the urban construction and operation stages, the digital twin model continues to play a role, monitoring the changes in the ecological environment in real time, comparing the actual data with the model prediction results, and promptly discovering and correcting potential problems. In this way, digital twin technology not only provides a scientific basis for urban ecological environment design, but also ensures the sustainability and flexibility of the design scheme, making the entire urban planning process more precise, dynamic and intelligent, and ultimately achieving an organic combination of ecology and urban development.

[0004] The prior art has the following deficiencies:

[0005] During seasonal rainfall, the water bodies in the city's central park are severely affected by the continuous accumulation of pollutants brought by surface runoff. Pollutants such as silt, fertilizers, and garbage carried by surface runoff are gradually deposited in the water body, and the cumulative effect of pollutants causes the water quality to gradually deteriorate. However, the existing urban ecological environment design technology based on digital twins cannot effectively evaluate the long-term accumulation effect of pollutants because it is difficult to accurately predict the accumulation path and speed of these pollutants in the water body in real time, resulting in the inability to effectively adjust and optimize the water quality management plan in the early stage of pollutant accumulation, which in turn causes the concentration of pollutants in the water body to continue to rise and the dissolved oxygen level to gradually decrease. With the continuous accumulation of pollutants, the water quality gradually deteriorates, the aquatic ecosystem faces a serious risk of long-term damage, and the living environment of fish and aquatic plants is threatened. This not only destroys the ecological balance of the water body, but also increases the difficulty of subsequent governance and increases the maintenance cost of urban management departments.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide an urban ecological environment design method and system based on digital twins to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: an urban ecological environment design method based on digital twins, specifically comprising the following steps:

[0009] Determine water management objectives and environmental conditions in the city’s central park and build a digital twin model to simulate the dispersion and accumulation effects of pollutants during seasonal rainfall;

[0010] Collect pollutant accumulation information in the city’s central park during seasonal rainfall in real time, and transmit the collected pollutant accumulation information to the digital twin model through a data interface;

[0011] Analyze the pollutant accumulation information input into the digital twin model to assess the risk level of pollutant accumulation in the city’s central park during seasonal rainfall;

[0012] Based on the assessment results, determine the potential impact of pollutant accumulation on water quality and initiate appropriate water quality management measures;

[0013] Continuously monitor the effectiveness of water quality management measures, dynamically adjust water quality management strategies based on real-time feedback information, optimize management measures, and maintain the balance of the water ecosystem in the city’s central park.

[0014] Preferably, the pollutant accumulation information input into the digital twin model is analyzed to assess the pollutant accumulation risk level of the city central park during seasonal rainfall, specifically comprising the following steps:

[0015] Extract pollutant accumulation information input into the digital twin model and perform preprocessing after extraction;

[0016] Extracting pollution diffusion dynamic information and water quality impact assessment information from the pre-processed pollutant accumulation information, and analyzing them after extraction to generate pollutant diffusion coefficients and water quality change indices, respectively;

[0017] A pollution accumulation assessment model is constructed for the generated pollutant diffusion coefficient and water quality change index to generate a pollution accumulation coefficient. The generated pollution accumulation coefficient is compared with the pre-set pollution accumulation coefficient threshold range. Based on the comparison results, the pollutant accumulation risk level of the city's central park during seasonal rainfall is evaluated.

[0018] Preferably, the acquisition logic of the pollutant diffusion coefficient is as follows:

[0019] The pollution diffusion dynamic information is extracted from the pre-processed pollutant accumulation information, including the average surface runoff, average rainfall intensity, average water flow velocity, average water area and initial concentration of pollutants in the city central park at different times during a period of seasonal rainfall, and calibrated as and C0, represents the average surface runoff volume at time m in the city's central park during seasonal rainfall. represents the average rainfall intensity at time m in the city's central park during seasonal rainfall. represents the average water flow velocity at time m in the city's central park during seasonal rainfall. represents the average water area of ​​the city central park at time m during a period of seasonal rainfall, C0 represents the initial concentration of pollutants in the city central park during the seasonal rainfall, m = 1, 2, 3, ..., k, k is a positive integer;

[0020] Calculate the pollutant diffusion coefficient. The specific calculation formula is as follows:

[0021]

[0022] Where PDC is the pollutant diffusion coefficient.

[0023] Preferably, the acquisition logic of the water quality change index is as follows:

[0024] The water quality impact assessment information was extracted from the pre-processed pollutant accumulation information, including the average concentration of pollutants, average nitrogen content, average phosphorus content, average dissolved oxygen level and average water temperature at different times during a period of seasonal rainfall in the city's central park, and calibrated as and represents the average concentration of pollutants in the city's central park at time n during a period of seasonal rainfall, represents the average nitrogen content of the city's central park at time n during a period of seasonal rainfall, represents the average phosphorus content in the city's central park at time n during a period of seasonal rainfall, represents the average dissolved oxygen level in the city's central park at time n during seasonal rainfall. represents the average water temperature of the city's central park at time n during a period of seasonal rainfall, n = 1, 2, 3, ..., h, h is a positive integer;

[0025] Calculate the water quality change index. The specific calculation formula is as follows:

[0026]

[0027] Where WQI is the water quality change index.

[0028] Preferably, a pollution accumulation assessment model is constructed based on the generated pollutant diffusion coefficient and water quality change index to generate a pollution accumulation coefficient, which specifically includes the following steps:

[0029] Collect several pollutant diffusion coefficients, several water quality change indices and corresponding pollution accumulation coefficients generated in the past period of time, and calibrate them as PDC x , WQI x and PAC x , x represents the serial numbers of several pollutant diffusion coefficients, several water quality change indexes and corresponding pollution accumulation coefficients generated in the past period of time, x = 3, 4, 5, ..., g, g is a positive integer, and the data collected in the past period of time are formed into a historical data set;

[0030] The multivariate regression model is selected as the pollution accumulation assessment model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula:

[0031] PAC x =β0+β1*PDC x +β2*WQI x

[0032] Where β0, β1 and β2 are regression coefficients;

[0033] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined;

[0034] The final regression coefficient is used to construct the pollution accumulation assessment model, and the pollutant diffusion coefficient PDC and water quality change index WQI generated in real time are input to generate the pollution accumulation coefficient PAC in real time.

[0035] Preferably, the generated pollution accumulation coefficient PAC is compared with a preset pollution accumulation coefficient threshold interval [PAC min , PAC max ] and compared them. The pollutant accumulation risk level of the city’s central park during seasonal rainfall was evaluated based on the comparison results. The specific comparison analysis is as follows:

[0036] If PAC <PAC min , the pollutant accumulation risk level of the city's central park during seasonal rainfall is low risk level;

[0037] If PAC min ≤PAC≤PAC max , the pollutant accumulation risk level of the city's central park during seasonal rainfall is medium risk level;

[0038] If PAC>PAC max , the pollutant accumulation risk level in the city’s central park during seasonal rainfall is high.

[0039] Preferably, based on the assessment results, determine the potential impact of pollutant accumulation on water quality and initiate appropriate water quality management measures, including:

[0040] If the assessment result shows that the risk level of pollutant accumulation in the city's central park during seasonal rainfall is low, the potential impact of pollutant accumulation on water quality is low, and the management measures to be taken are to continue water quality monitoring without adding new intervention measures;

[0041] If the assessment result shows that the risk level of pollutant accumulation in the city's central park during seasonal rainfall is medium, the potential impact of pollutant accumulation on water quality is medium, and the management measures to be taken are to increase water mobility and filtration treatment to control pollutant accumulation;

[0042] If the assessment result is that the risk level of pollutant accumulation in the city's central park during seasonal rainfall is high, the potential impact of pollutant accumulation on water quality is high, and the management measures taken are to reduce the concentration of pollutants in the water body through physical, chemical or mechanical means, increase pollutant treatment and water purification.

[0043] Preferably, the urban ecological environment design system based on digital twins includes a water management target setting and environmental analysis module, a pollutant accumulation information collection and transmission module, a pollution accumulation risk assessment and analysis module, a water quality impact assessment and management measure initiation module, and a water quality management dynamic monitoring and strategy adjustment module;

[0044] The water management goal setting and environmental analysis module determines the water management goals and environmental conditions of the city’s central park and builds a digital twin model to simulate the diffusion and accumulation effects of pollutants during seasonal rainfall;

[0045] The pollutant accumulation information collection and transmission module collects pollutant accumulation information in the city’s central park during seasonal rainfall in real time, and transmits the collected pollutant accumulation information to the digital twin model through a data interface;

[0046] The pollution accumulation risk assessment and analysis module analyzes the pollutant accumulation information input into the digital twin model and assesses the pollutant accumulation risk level of the city’s central park during seasonal rainfall;

[0047] The water quality impact assessment and management measures initiation module determines the potential impact of pollutant accumulation on water quality based on the assessment results and initiates corresponding water quality management measures;

[0048] The water quality management dynamic monitoring and strategy adjustment module continuously monitors the effectiveness of water quality management measures, dynamically adjusts water quality management strategies based on real-time feedback information, optimizes management measures, and maintains the balance of the water ecosystem in the city’s central park.

[0049] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0050] 1. The present invention realizes accurate monitoring and dynamic management of the water body in the city's central park by constructing a digital twin model and monitoring pollutant accumulation information in real time. The real-time collection and transmission of pollutant accumulation data ensures that the system can quickly respond to changes in water quality during seasonal rainfall. This real-time data collection and transmission mechanism greatly improves the efficiency of water pollutant monitoring, allowing managers to obtain information and take timely action when pollutants just begin to accumulate. This effectively avoids the deterioration of water quality caused by hysteresis in traditional methods and significantly improves the management effect of water bodies.

[0051] 2. The multivariate regression model in the present invention establishes an accurate pollutant accumulation assessment model through the analysis of historical data, so that the system can more effectively predict and evaluate the long-term impact of pollutant accumulation on water quality. By generating pollutant diffusion coefficients and water quality change indexes, the system can dynamically evaluate the diffusion rate and cumulative risk level of pollutants during rainfall, and automatically initiate corresponding water quality management measures based on the evaluation results. This model based on complex data analysis avoids the shortcomings of traditional empirical judgments, makes water quality management plans more scientific and quantifiable, and optimizes the effectiveness of pollutant management strategies.

[0052] 3. The present invention adopts a modular structure, and each module has a clear division of labor and can independently complete its own tasks. Such a design makes the system highly flexible under different environmental conditions and easy to expand or modify. For example, the water quality management strategy module can dynamically adjust the strategy and optimize the management measures according to the monitoring feedback. This modular design ensures the high operability of the system, while having strong scalability, which is convenient for subsequent expansion or upgrading of functions according to actual conditions. Through the collaborative work of various modules, the system can effectively respond to the various challenges brought about by the accumulation of pollutants and maintain the balance of the water ecosystem of the city's central park. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0054] Figure 1 It is a flow chart of the urban ecological environment design method and system based on digital twins of the present invention.

[0055] Figure 2 It is a module schematic diagram of the urban ecological environment design method and system based on digital twins of the present invention. DETAILED DESCRIPTION

[0056] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0057] The present invention provides Figure 1 The urban ecological environment design method based on digital twins shown in the figure specifically includes the following steps:

[0058] Determine water management objectives and environmental conditions in the city’s central park and build a digital twin model to simulate the dispersion and accumulation effects of pollutants during seasonal rainfall;

[0059] Determining the water management objectives and environmental conditions of a city's central park can be done in a variety of ways. First, by analyzing urban planning, environmental policies, and the ecological protection needs of the park, the main functional objectives of the water body can be determined, such as maintaining water quality balance, preventing pollutant accumulation, and protecting aquatic biodiversity. Then, reasonable management objectives can be set based on meteorological data of seasonal rainfall, historical pollutant accumulation, and park usage. For example, specific thresholds can be set for dissolved oxygen, pollutant concentrations, and nutrient levels in the water body according to the park's ecological and environmental requirements and rainfall intensity to ensure that the water quality achieves ecological balance under different conditions. In addition, the determination of environmental conditions can be further clarified by combining hydrogeological data such as on-site surveys, water body depth measurements, and soil permeability analysis.

[0060] The way to establish a digital twin model can be achieved by integrating multi-source data. First, the spatial geographic information, hydrological environment data, historical pollution data, etc. of the city’s central park need to be digitized through three-dimensional modeling technology. Use real-time data acquisition systems, including equipment such as meteorological stations, flow meters, and water quality sensors, to integrate the monitored rainfall, surface runoff, and water quality data (such as suspended matter concentration, dissolved oxygen level, etc.) into the model. The establishment of a digital twin model also relies on simulation software. The collected data is simulated and calculated through software algorithms to create a virtual model that can dynamically reflect the diffusion and accumulation paths of pollutants during seasonal rainfall. The model can be combined with real-time monitoring data to simulate the behavior of pollutants in future rainfall events and predict how pollutants will spread and accumulate.

[0061] This step explains in detail how to build a digital twin model through software technology. First, the management objectives and environmental conditions of the park are determined through data analysis and modeling, and then three-dimensional modeling and real-time monitoring of water quality changes are carried out through the collection and integration of multi-source data. The model can not only dynamically simulate the spread of pollution in water bodies during rainfall, but also predict the impact of future pollution events based on historical data, providing real-time and accurate decision support for water management plans.

[0062] Collect pollutant accumulation information in the city’s central park during seasonal rainfall in real time, and transmit the collected pollutant accumulation information to the digital twin model through a data interface;

[0063] In order to collect real-time information on pollutant accumulation in the city's central park during seasonal rainfall, a series of sensor networks and monitoring equipment must first be deployed. These sensors can include water quality monitors (for detecting suspended matter, sediment, and pollutant concentrations in water bodies), flow meters (for monitoring surface runoff), and meteorological stations (recording rainfall, wind speed, etc.). Each device regularly collects relevant data, which is sent to the central server in real time via wireless transmission protocols (such as LoRa, ZigBee, or LTE-M). The central server runs data interface management software to organize the collected pollutant accumulation information into a standardized format and transmit it to the digital twin model through an API or database interface. The digital twin model automatically receives this data and dynamically updates the scenarios and calculation parameters in the model based on real-time data to ensure that the model can reflect the current pollution situation and changing trends of the water body.

[0064] Real-time collection and transmission of pollutant accumulation information in the above manner ensures that the system always keeps track of the dynamics of pollutant diffusion when facing the complex environment of the city's central park. Since the diffusion and accumulation of pollutants during seasonal rainfall is rapid and difficult to predict, these changes must be captured through real-time monitoring methods in order to make timely decisions and adjust water quality management measures. Real-time data collection and transmission of sensor networks enable digital twin models to perform dynamic simulation and evaluation based on accurate and up-to-date data information. This not only helps to improve the accuracy of water management decisions, but also prevents water quality management plans from responding in a timely manner due to delayed or inaccurate data, thereby avoiding water quality deterioration and ensuring the stability of aquatic ecosystems.

[0065] Analyze the pollutant accumulation information input into the digital twin model to assess the risk level of pollutant accumulation in the city’s central park during seasonal rainfall;

[0066] In this embodiment, the pollutant accumulation information input into the digital twin model is analyzed to evaluate the pollutant accumulation risk level of the city central park during seasonal rainfall, specifically including the following steps:

[0067] Extract pollutant accumulation information input into the digital twin model and perform preprocessing after extraction;

[0068] Extracting pollutant accumulation information input into the digital twin model can be done through the system interface and data flow management module. Specifically, the digital twin model is connected to real-time monitoring equipment and sensor networks, which transmit data to the central database through wireless or wired networks. The extraction method can obtain pollutant accumulation information from the database on demand through the API (application programming interface). Pollutant accumulation information includes data such as surface runoff, pollutant concentration, dissolved oxygen level, nitrogen and phosphorus content, water temperature, and rainfall intensity. This information is generated and uploaded in real time through specific monitoring equipment (such as water quality monitors, weather stations, flow meters, etc.). Each type of data has a clear timestamp and location mark to ensure the real-time and spatial accuracy of the data.

[0069] The main purpose of preprocessing is to ensure the consistency, accuracy and completeness of the data to improve the accuracy of subsequent analysis. Since the pollutant accumulation information may have noise, missing values ​​or outliers during the collection process, the preprocessing steps include data cleaning, interpolation to fill missing data, removal of abnormal data, and normalization to eliminate differences between different data units. First, the software automatically detects abnormal points in the data (such as abnormal peaks in pollutant concentrations) through algorithms and processes abnormal data according to the set threshold rules. Then, linear interpolation or other interpolation algorithms are used to fill in the missing data points. Finally, normalization converts data of different dimensions (such as concentration, flow rate, temperature, etc.) to the same range to ensure that each data dimension can be reasonably compared in the subsequent analysis model. Through preprocessing, the data can be unified and standardized, providing a reliable data basis for subsequent evaluation.

[0070] Extracting pollution diffusion dynamic information and water quality impact assessment information from the pre-processed pollutant accumulation information, and analyzing them after extraction to generate pollutant diffusion coefficients and water quality change indices, respectively;

[0071] Extracting the pollution diffusion dynamic information and water quality impact assessment information from the preprocessed pollutant accumulation information can be done by data classification and labeling. First, during the preprocessing process, the pollutant accumulation information has been cleaned and normalized. Then, the software system classifies this information through a data classification algorithm, dividing it into data related to pollution diffusion (such as surface runoff, rainfall intensity, water flow velocity, etc.) and data related to water quality impact (such as pollutant concentration, dissolved oxygen, nitrogen and phosphorus content, etc.). The software automatically identifies and extracts information of corresponding categories based on the labels or data attributes of different information (such as timestamps, location tags, and data sources). The extracted data sets are assigned to different analysis modules, where the pollution diffusion dynamic information is used to calculate the pollution diffusion coefficient, and the water quality impact assessment information is used to generate the water quality change index. In this way, the software can automatically extract and classify the preprocessed information to provide support for subsequent analysis and model generation.

[0072] A pollution accumulation assessment model is constructed for the generated pollutant diffusion coefficient and water quality change index to generate a pollution accumulation coefficient. The generated pollution accumulation coefficient is compared with the pre-set pollution accumulation coefficient threshold range. Based on the comparison results, the pollutant accumulation risk level of the city's central park during seasonal rainfall is evaluated.

[0073] The pre-set threshold interval of the pollution accumulation coefficient can be determined by combining historical data analysis and expert system models. First, the software system can extract pollutant accumulation data from previous seasonal rainfall data and water quality monitoring history records to establish a pollutant accumulation trend model over a long period of time. Based on these historical data, different accumulation levels of normal, light pollution, moderate pollution and heavy pollution can be divided through statistical analysis (such as mean, variance, etc.). In addition, the software system can adjust different risk levels in combination with water quality management standards and environmental safety goals set by experts. In specific implementation, the threshold interval of the pollution accumulation coefficient can be dynamically adjusted through the set algorithm, and the final safety threshold interval can be determined based on multiple parameters such as pollutant concentration, water carrying capacity and ecosystem sensitivity, ensuring that the water quality management system can be flexible and scalable in actual operation.

[0074] In this embodiment, the logic for obtaining the pollutant diffusion coefficient is as follows:

[0075] The pollution diffusion dynamic information is extracted from the pre-processed pollutant accumulation information, including the average surface runoff, average rainfall intensity, average water flow velocity, average water area and initial concentration of pollutants in the city central park at different times during a period of seasonal rainfall, and calibrated as and C0, represents the average surface runoff volume at time m in the city's central park during seasonal rainfall. represents the average rainfall intensity at time m in the city's central park during seasonal rainfall. represents the average water flow velocity at time m in the city's central park during seasonal rainfall. represents the average water area of ​​the city central park at time m during a period of seasonal rainfall, C0 represents the initial concentration of pollutants in the city central park during the seasonal rainfall, m = 1, 2, 3, ..., k, k is a positive integer;

[0076] The extracted pre-processed dynamic information of pollution diffusion can be connected to the sensor network through the data interface in the digital twin model, and obtained from the real-time monitoring data stream using API or database management system. The sensor network deployed in the city’s central park, including water quality monitoring stations, flow meters, meteorological stations, etc., transmits data to the central database in real time. The digital twin model extracts relevant information such as surface runoff, rainfall intensity, flow rate and water area by calling the data interface. The software system will segment the data collected in different time periods according to the timestamp, and average the dynamic information at different times. During the specific extraction, the system will automatically extract this data according to the preset monitoring frequency (for example, once an hour) and integrate it into the model for subsequent analysis.

[0077] The source of these data is mainly through the environmental monitoring equipment deployed in the city's central park. The average surface runoff comes from flow meters deployed at the park's boundaries, which measure the flow rate of rainwater before it flows into the park's water body. The average rainfall intensity is obtained through the meteorological station, which can accurately record the rainfall and calculate the rainfall intensity based on the time interval. The average water flow rate is monitored in real time by the flow velocity sensor installed in the water body, and the average calculation is performed by combining the data of different time periods. The average water body area is calculated by combining the data of the water level sensor with the geographic information of the water body boundary. The rise in water level during rainfall will affect the change in the water body area. The initial concentration of pollutants is detected by water quality monitoring equipment. The initial concentration is the basic value before the start of rainfall. Through the comprehensive data of these sensor networks, the digital twin model can accurately simulate the dynamic process of pollutant diffusion.

[0078] Calculate the pollutant diffusion coefficient. The specific calculation formula is as follows:

[0079]

[0080] Where PDC is the pollutant diffusion coefficient.

[0081] This formula is used to calculate the pollutant diffusion coefficient (PDC), which aims to measure the diffusion speed and distribution range of pollutants in the water body of the city's central park. The formula takes into account multiple factors, such as surface runoff, rainfall intensity, flow rate, water body area, initial concentration of pollutants, etc., which jointly affect the diffusion process of pollutants in the water body. Specifically, surface runoff and rainfall intensity Determines the speed and amount of rainwater entering the water body, and directly affects the transport rate of pollutants. The initial pollutant concentration C0 is the base value when the pollutant enters the water body. A higher initial concentration will lead to a stronger pollution diffusion effect. Affects the migration rate of pollutants. When the water flow is faster, the range of pollutant diffusion is larger. By weighted summation of these dynamic variables in different time periods m, and by coefficient By normalizing multiple time periods, the formula can comprehensively evaluate the cumulative effect of pollutant diffusion during the entire rainfall period and obtain the diffusion trend of pollutants over the entire time period. This calculation method can capture the dynamic changes of pollutants over time and provide a comprehensive diffusion coefficient to help managers assess water pollution risks and take appropriate water quality management measures.

[0082] The size of the pollutant diffusion coefficient directly affects the level of pollutant accumulation risk in the city's central park during seasonal rainfall. A larger pollutant diffusion coefficient indicates that pollutants diffuse rapidly in the water body and diffuse over a wider range. Although this may reduce local pollutant concentrations, it also means that pollutants can quickly spread to a larger area of ​​the water body, increasing the pollution coverage of the entire water body, thereby increasing the accumulation risk. On the contrary, a smaller diffusion coefficient indicates that pollutants diffuse more slowly, and pollutants will be concentrated in certain areas of the water body, which may cause local pollutant concentrations to rise rapidly, resulting in a higher risk of pollution accumulation in these areas. Therefore, the size of the diffusion coefficient helps determine whether pollutants diffuse rapidly over a large area or accumulate locally, affects the level of assessment of pollutant accumulation risk, and guides corresponding water quality management decisions.

[0083] In this embodiment, the logic for obtaining the water quality change index is as follows:

[0084] The water quality impact assessment information was extracted from the pre-processed pollutant accumulation information, including the average concentration of pollutants, average nitrogen content, average phosphorus content, average dissolved oxygen level and average water temperature at different times during a period of seasonal rainfall in the city's central park, and calibrated as and represents the average concentration of pollutants in the city's central park at time n during a period of seasonal rainfall, represents the average nitrogen content of the city's central park at time n during a period of seasonal rainfall, represents the average phosphorus content in the city's central park at time n during a period of seasonal rainfall, represents the average dissolved oxygen level in the city's central park at time n during seasonal rainfall. represents the average water temperature of the city's central park at time n during a period of seasonal rainfall, n = 1, 2, 3, ..., h, h is a positive integer;

[0085] Extracting pre-processed water quality impact assessment information begins with real-time data collection through a variety of sensor systems deployed in the water bodies of the city's central park. These sensors include water quality monitors, dissolved oxygen sensors, temperature sensors, etc., which transmit data to a central database or cloud system via wireless transmission or wired connection. The digital twin model classifies these sensor data by timestamp, location and other information by calling an API or database management system. The software automatically extracts data such as average pollutant concentrations, nitrogen content, phosphorus content, dissolved oxygen levels and water temperature at each moment according to a set time period (such as every hour), and marks this information as water quality impact assessment information. After extraction, the software can store this data in a specific database as needed, or use it directly for dynamic analysis of the model.

[0086] The source of these data mainly relies on sensor equipment deployed in the park's water bodies. The average pollutant concentration is measured by water quality monitors to detect the concentration of suspended particles, dissolved substances and chemical pollutants in the water. These monitors are usually fixed at different depths in the water to obtain comprehensive data. The average nitrogen and phosphorus content are collected by multi-parameter water quality sensors, which are specifically used to detect the content of nutrients, especially nitrogen and phosphorus, which have an important impact on eutrophication of water bodies. The average dissolved oxygen level is monitored in real time by dissolved oxygen sensors, which measure the concentration of oxygen in the water body through chemical or optical principles. The average water temperature is measured by a temperature sensor, which provides real-time temperature data through a buoy monitoring system or a fixed underwater sensor. After preprocessing, the data streams formed by these sensor networks can provide basic support for subsequent analysis and calculation of water quality change indexes.

[0087] Calculate the water quality change index. The specific calculation formula is as follows:

[0088]

[0089] Where WQI is the water quality change index.

[0090] The calculation formula of the Water Quality Change Index (WQI) combines multiple key water quality parameters in a weighted summation method, aiming to assess the impact of pollutant accumulation in the city's central park water body on water quality during seasonal rainfall. Specifically, the pollutant concentration used in the formula Nitrogen content Phosphorus content It reflects the main pollutants and nutrients in the water body. Their increase directly points to the increase of eutrophication and pollution level in the water body. and water temperature It is an important indicator for measuring the health of water quality. The higher the dissolved oxygen content in the water body, the healthier the biological ecosystem. Conversely, it means that the water body is lacking in oxygen, and fish and plants will be affected. Water temperature affects the solubility and biological activity of oxygen, so it is also one of the key factors. This formula takes these indicators into consideration, multiplying the pollutant concentration, nitrogen and phosphorus content to reflect the cumulative effect between pollutants, and dividing them with dissolved oxygen and water temperature to reflect the role of oxygen and temperature in maintaining water quality balance. This method can quantify the comprehensive water quality change trend of water bodies during rainfall, and express data at multiple times in the form of average values ​​to ensure that the evaluation results are continuous and representative. This calculation method helps to fully understand the short-term and long-term impacts of pollutants on water bodies and provide a basis for subsequent management measures.

[0091] The size of the water quality change index is directly related to the risk level of pollutant accumulation in the city's central park during seasonal rainfall. A higher water quality change index indicates that pollutant concentrations, nitrogen content, and phosphorus content are relatively high, while dissolved oxygen levels and water temperatures are relatively low, which means that the water body is seriously polluted, especially eutrophication and hypoxia. In this case, the risk of water quality deterioration is higher, the water ecosystem is prone to imbalance, and the cumulative risk level also increases. On the contrary, a lower water quality change index indicates that there are fewer pollutants in the water body, the dissolved oxygen content and water temperature are within the normal range, the water quality is better, and the risk of pollution accumulation is lower. Therefore, the size of the WQI reflects the water body's tolerance to pollutants and the quality of the environment, helps to judge the degree of threat to the health of the water body caused by the accumulation of pollutants, and assesses the corresponding risk level accordingly.

[0092] In this embodiment, a pollution accumulation assessment model is constructed based on the generated pollutant diffusion coefficient and water quality change index to generate a pollution accumulation coefficient, which specifically includes the following steps:

[0093] Collect several pollutant diffusion coefficients, several water quality change indices and corresponding pollution accumulation coefficients generated in the past period of time, and calibrate them as PDC x , WQI x and PAC x, x represents the serial numbers of several pollutant diffusion coefficients, several water quality change indexes and corresponding pollution accumulation coefficients generated in the past period of time, x = 3, 4, 5, ..., g, g is a positive integer, and the data collected in the past period of time are formed into a historical data set;

[0094] In order to collect the pollutant diffusion coefficient, water quality change index and corresponding pollution accumulation coefficient generated in the past period of time, this can be achieved through the data storage module in the software system. First, the digital twin model is connected to the sensor network to generate and calculate the pollutant diffusion coefficient and water quality change index in real time. Each calculation result is accompanied by a timestamp and location information, and the system automatically stores these data in a database or cloud data warehouse. The software system can set a regular data storage strategy to automatically record the PDC, WQI and corresponding PAC data generated at each moment by hour, day or custom time period. By calling the query API in the database management system, the system can obtain all historical data in the past period of time on demand. These historical data will be marked as time series data to ensure that they can be trained and analyzed in chronological order in subsequent multivariate regression models.

[0095] The value of x is greater than or equal to 3 because in regression analysis, the number of variables determines the minimum number of data points required. Specifically, the pollutant diffusion coefficient, the water quality change index, and the intercept term (constant term) are the three variables in the regression equation, and the regression coefficients (such as β0, β1, and β2) are estimated based on the relationship between these variables and the pollution accumulation coefficient. Therefore, in order to ensure that the three coefficients in the regression equation can be solved, we need at least three independent data points (that is, x≥3). This ensures that each variable has sufficient data to support the estimation of its regression coefficient. If the value of x is less than 3, there is no guarantee that enough equations will be obtained to solve the three unknown regression coefficients, so the value of x must be greater than or equal to 3 to ensure that the regression model can be successfully constructed and obtain reasonable regression coefficients.

[0096] The multivariate regression model is selected as the pollution accumulation assessment model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula:

[0097] PAC x =β0+β1*PDC x +β2*WQI x

[0098] Where β0, β1 and β2 are regression coefficients;

[0099] The multiple regression model is a statistical analysis method used to study the relationship between multiple independent variables and one dependent variable. In the pollution accumulation assessment model, the independent variables include the pollutant diffusion coefficient and the water quality change index, while the dependent variable is the pollution accumulation coefficient. The multiple regression model can automatically adjust the weights of different independent variables through historical data to find the optimal combination of their effects on the dependent variable. The reason for choosing the multiple regression model as the pollution accumulation assessment model is that it can not only handle multiple variables, but also determine the different effects of pollutant diffusion and water quality changes on pollution accumulation by training a large amount of historical data, thereby more accurately predicting the pollution accumulation coefficient. This method effectively utilizes the complex relationship of historical data and can provide reasonable parameter estimates when the interaction relationship between variables is not clear.

[0100] In the multiple regression model, the regression coefficients (β0, β1, and β2) represent the weights of the intercept and the independent variable on the dependent variable, respectively. Specifically, β0 is the intercept of the model, which indicates the basic level of the pollution accumulation coefficient when the pollutant diffusion coefficient and the water quality change index are both zero. β1 is the regression coefficient of the pollutant diffusion coefficient, which indicates the contribution of pollutant diffusion to pollution accumulation. The larger the value, the greater the impact of the diffusion coefficient on pollution accumulation. β2 is the regression coefficient of the water quality change index, which represents the impact of water quality changes on pollution accumulation. The larger the value, the more significant the effect of water quality deterioration on pollution accumulation. By training the model, these regression coefficients can be optimized, and ultimately accurately reflect the degree of influence of different factors on pollution accumulation.

[0101] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined;

[0102] Minimizing the error between the predicted value and the actual value is the core goal of the regression model, because this can improve the accuracy of the model and make the predicted pollution accumulation coefficient closer to the actual observed data. By minimizing the error, the model can continuously adjust the regression coefficients (β0, β1 and β2) so that these coefficients better reflect the impact of the independent variables on pollution accumulation. In this way, the model can not only be applied to historical data, but also make more accurate predictions of future pollution accumulation risks. The ultimate goal of this process is to ensure that the model has high accuracy and can be used for decision support by minimizing the error. In specific implementation, the commonly used method is the least squares method (OLS), which optimizes the regression coefficient by minimizing the residual sum of squares (that is, the sum of the squares of the difference between the predicted value and the actual value). The software system will calculate the difference between the predicted value and the actual value at each time point based on the historical data, and square these differences and sum them. Through iterative algorithms, such as gradient descent, the model will gradually adjust the regression coefficients so that the residual sum of squares reaches the minimum value. This process continuously optimizes the values ​​of β0, β1 and β2 until the pollution accumulation coefficient predicted by the model achieves the best fit with the historical data, thereby ensuring the accuracy and reliability of the model.

[0103] The final regression coefficient is used to construct the pollution accumulation assessment model, and the pollutant diffusion coefficient PDC and water quality change index WQI generated in real time are input to generate the pollution accumulation coefficient PAC in real time.

[0104] In this embodiment, the generated pollution accumulation coefficient PAC is compared with the preset pollution accumulation coefficient threshold interval [PAC min , PAC max ] and compared them. The pollutant accumulation risk level of the city’s central park during seasonal rainfall was evaluated based on the comparison results. The specific comparison analysis is as follows:

[0105] If PAC <PAC min , the pollutant accumulation risk level of the city's central park during seasonal rainfall is low risk level;

[0106] This means that the accumulated pollution in the city's central park is very slight, the pollutants diffuse slowly, and the water quality has not been significantly affected. At this time, the dissolved oxygen level in the water is still at a high level, biodiversity has not been damaged, and the living environment of aquatic plants and fish remains in good condition. The low risk level means that no special water quality management measures are required, and the existing ecosystem regulation capacity is sufficient to maintain the health of the water body. For managers, at this time, only routine monitoring is needed to maintain the long-term stability of water quality, and the management cost is low.

[0107] If PAC min ≤PAC≤PAC max, the pollutant accumulation risk level of the city's central park during seasonal rainfall is medium risk level;

[0108] This means that the accumulation of pollutants in the water has reached a medium level and the water quality has begun to change. The continued accumulation of pollutants may cause the dissolved oxygen level in the water in some areas to drop and the nutrient content in the water to increase, which may cause eutrophication, such as excessive algae growth. The medium risk level prompts managers to take appropriate water quality control measures, such as appropriately increasing water flow and introducing physical or biological treatment measures to prevent further accumulation of pollutants and prevent water quality deterioration. Management requirements at this time are higher, and management strategies need to be adjusted dynamically.

[0109] If PAC>PAC max , the pollutant accumulation risk level in the city’s central park during seasonal rainfall is high.

[0110] It means that the accumulation of pollutants in the water body has reached a high level, the water quality is seriously affected, the dissolved oxygen is rapidly decreasing, eutrophication is intensifying, and the water body becomes turbid. The high risk level indicates that the water ecosystem is already under great pressure, and a large number of aquatic organisms may die, such as fish and plants cannot grow normally, and may even cause the ecological imbalance of the entire water body. At this time, emergency management measures must be taken immediately, such as strengthening water circulation, quickly cleaning up pollutants, or taking chemical or mechanical methods to reduce pollutant concentrations, prevent further deterioration of water quality and restore the balance of the ecosystem. Managers need to invest more resources to deal with high-risk situations, and the cost of governance increases significantly.

[0111] Based on the assessment results, determine the potential impact of pollutant accumulation on water quality and initiate appropriate water quality management measures;

[0112] In this embodiment, based on the assessment results, the potential impact of pollutant accumulation on water quality is determined, and corresponding water quality management measures are initiated, including:

[0113] If the assessment result shows that the risk level of pollutant accumulation in the city's central park during seasonal rainfall is low, the potential impact of pollutant accumulation on water quality is low, and the management measures to be taken are to continue water quality monitoring without adding new intervention measures;

[0114] When the assessment result is a low risk level, it means that the diffusion and accumulation of pollutants are small, the water quality has not been significantly affected, and key water quality parameters such as dissolved oxygen levels, nitrogen and phosphorus content, and temperature in the water remain within the normal range. At this time, the concentration of pollutants is low, and the threat to aquatic ecosystems is relatively small. In order to deal with this situation, the management system only needs to continuously monitor the water quality and no additional intervention measures are required. Specifically, the software can be used to regularly collect data from water monitoring equipment (such as pollutant concentrations, dissolved oxygen levels, etc.), and the changing trends of these data can be analyzed through the digital twin model to ensure stable water quality. If changes in indicators are found, the system will issue an alarm to prompt further monitoring, but no additional physical or chemical treatment will be taken.

[0115] If the assessment result shows that the risk level of pollutant accumulation in the city's central park during seasonal rainfall is medium, the potential impact of pollutant accumulation on water quality is medium, and the management measures to be taken are to increase water mobility and filtration treatment to control pollutant accumulation;

[0116] The medium risk level means that the accumulation of pollutants has had a significant impact on the water quality. The increase in the content of nutrients such as nitrogen and phosphorus in the water body may cause eutrophication, lead to excessive growth of algae, and affect the ecological balance in the water. At this time, measures need to be taken to control the accumulation and spread of pollutants. The software system monitors water quality changes in real time, automatically starts the water body fluidity regulating device, and increases the water flow rate to dilute the pollutant concentration. At the same time, the software will control the water body filtration equipment, start the physical filtration or biological filtration system, and reduce the concentration of suspended pollutants. The system will dynamically adjust the operating intensity of the filtration equipment based on real-time sensor data to ensure that pollutants are controlled within an acceptable range and avoid further deterioration of water quality.

[0117] If the assessment result is that the risk level of pollutant accumulation in the city's central park during seasonal rainfall is high, the potential impact of pollutant accumulation on water quality is high, and the management measures taken are to reduce the concentration of pollutants in the water body through physical, chemical or mechanical means, increase pollutant treatment and water purification.

[0118] A high risk level means that the concentration of pollutants has reached a dangerous level, the water quality has seriously deteriorated, a large number of aquatic organisms may die, eutrophication is serious, and the dissolved oxygen level has dropped significantly. In order to deal with this situation, emergency measures must be taken. After the software system detects a high risk level, the system will automatically start the emergency treatment plan and mobilize mechanical treatment equipment for large-scale water purification, such as reducing the nitrogen and phosphorus content in the water through chemical treatment agents or removing suspended pollutants through mechanical means. At the same time, the system will also start the rapid circulation device of the water body to increase the fluidity of the water body to quickly dilute the pollutants. In addition, the software system can also dispatch external clean water resources to introduce clean water into the polluted water body through the pipeline system to quickly reduce the concentration of pollutants and restore the balance of the water body.

[0119] Continuously monitor the effectiveness of water quality management measures, dynamically adjust water quality management strategies based on real-time feedback information, optimize management measures, and maintain the balance of the water ecosystem in the city’s central park.

[0120] Continuous monitoring of the effectiveness of water quality management measures can be achieved through a variety of real-time sensor networks deployed in the water bodies of the city's central parks. These sensor devices can monitor key indicators of the water body, such as pollutant concentrations, dissolved oxygen levels, nitrogen and phosphorus content, water temperature, etc. These data are continuously transmitted to the central control system through wireless or wired transmission systems, and the software analyzes these data in real time. The software system will compare the monitoring data at each moment according to the set thresholds and baselines to determine whether the current water quality management measures are effective as expected. For example, if the dissolved oxygen level continues to decline, indicating that the existing management measures are not sufficient to cope with the accumulation of pollutants, the system will issue an early warning signal, indicating that the strategy needs to be adjusted. In this way, the system can achieve real-time monitoring to ensure that the water quality is always in a dynamically controllable state.

[0121] When the real-time monitoring shows that the effect of water quality management measures is not as expected, the software system will automatically or semi-automatically adjust the water quality management strategy. The adjustment method can be determined based on the specific data fed back by the sensor. For example, when the pollutant concentration exceeds the preset threshold, the system can increase the operating frequency of the water circulation device and accelerate the flow of water to dilute the pollutant concentration. If the nitrogen and phosphorus content is high, the system will automatically start the relevant filtration system or increase the workload of the biological filter to deal with excess nutrients in the water. If the high water temperature causes the dissolved oxygen level to drop, the system can automatically adjust the water body's oxygen injection system to increase the concentration of dissolved oxygen. All these dynamic adjustments are based on real-time feedback data to ensure that the system can respond flexibly to environmental changes.

[0122] The purpose of continuous monitoring and dynamic adjustment of water quality management strategies is to ensure the long-term health and balance of the water ecosystem in the city's central park. The water environment is easily affected by external factors, especially during seasonal rainfall, when the accumulation of pollutants is complex and water quality is prone to fluctuations. If only fixed management measures are relied upon without dynamic adjustments, it may lead to untimely or insufficient measures, which may cause water quality deterioration or ecosystem imbalance. Therefore, continuous monitoring can provide accurate data support to ensure early detection and early response to problems. Dynamic adjustment strategies ensure the flexibility of management measures, which can respond to real-time environmental changes, prevent the further spread of pollutants, and take remedial measures quickly when necessary. This process is automated through the software system, reducing the time delay of manual intervention and improving the effectiveness and accuracy of water quality management.

[0123] like Figure 2 The urban ecological environment design system based on digital twins shown in the figure includes a water management target setting and environmental analysis module, a pollutant accumulation information collection and transmission module, a pollution accumulation risk assessment and analysis module, a water quality impact assessment and management measure initiation module, and a water quality management dynamic monitoring and strategy adjustment module;

[0124] The water management goal setting and environmental analysis module determines the water management goals and environmental conditions of the city’s central park and builds a digital twin model to simulate the diffusion and accumulation effects of pollutants during seasonal rainfall;

[0125] The pollutant accumulation information collection and transmission module collects pollutant accumulation information in the city’s central park during seasonal rainfall in real time, and transmits the collected pollutant accumulation information to the digital twin model through a data interface;

[0126] The pollution accumulation risk assessment and analysis module analyzes the pollutant accumulation information input into the digital twin model and assesses the pollutant accumulation risk level of the city’s central park during seasonal rainfall;

[0127] The water quality impact assessment and management measures initiation module determines the potential impact of pollutant accumulation on water quality based on the assessment results and initiates corresponding water quality management measures;

[0128] The water quality management dynamic monitoring and strategy adjustment module continuously monitors the effectiveness of water quality management measures, dynamically adjusts water quality management strategies based on real-time feedback information, optimizes management measures, and maintains the balance of the water ecosystem in the city’s central park.

[0129] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0130] The above embodiments can be implemented in whole or in part by software, hardware, 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 process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center containing one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0131] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0132] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0133] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0136] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The urban ecological environment design method based on digital twins is characterized by: The specific steps include: Determine water management objectives and environmental conditions in the city’s central park and build a digital twin model to simulate the dispersion and accumulation effects of pollutants during seasonal rainfall; Collect pollutant accumulation information in the city’s central park during seasonal rainfall in real time, and transmit the collected pollutant accumulation information to the digital twin model through a data interface; Analyze the pollutant accumulation information input into the digital twin model to assess the risk level of pollutant accumulation in the city’s central park during seasonal rainfall; Based on the assessment results, determine the potential impact of pollutant accumulation on water quality and initiate appropriate water quality management measures; Continuously monitor the effectiveness of water quality management measures, dynamically adjust water quality management strategies based on real-time feedback information, optimize management measures, and maintain the balance of the water ecosystem in the city’s central park.

2. The urban ecological environment design method based on digital twin according to claim 1 is characterized in that: The pollutant accumulation information input into the digital twin model was analyzed to assess the pollutant accumulation risk level in the city’s central park during seasonal rainfall, including the following steps: Extract pollutant accumulation information input into the digital twin model and perform preprocessing after extraction; Extracting pollution diffusion dynamic information and water quality impact assessment information from the pre-processed pollutant accumulation information, and analyzing them after extraction to generate pollutant diffusion coefficients and water quality change indices, respectively; A pollution accumulation assessment model is constructed for the generated pollutant diffusion coefficient and water quality change index to generate a pollution accumulation coefficient. The generated pollution accumulation coefficient is compared with the pre-set pollution accumulation coefficient threshold range. Based on the comparison results, the pollutant accumulation risk level of the city's central park during seasonal rainfall is evaluated.

3. The urban ecological environment design method based on digital twin according to claim 2 is characterized in that: The logic for obtaining the pollutant diffusion coefficient is as follows: The pollution diffusion dynamic information is extracted from the pre-processed pollutant accumulation information, including the average surface runoff, average rainfall intensity, average water flow velocity, average water area and initial concentration of pollutants in the city central park at different times during a period of seasonal rainfall, and calibrated as and represents the average surface runoff volume at time m in the city's central park during seasonal rainfall. represents the average rainfall intensity at time m in the city's central park during seasonal rainfall. represents the average water flow velocity at time m in the city's central park during seasonal rainfall. represents the average water area of ​​the city central park at time m during a period of seasonal rainfall, C0 represents the initial concentration of pollutants in the city central park during the seasonal rainfall, m = 1, 2, 3, ..., k, k is a positive integer; Calculate the pollutant diffusion coefficient. The specific calculation formula is as follows: Where PDC is the pollutant diffusion coefficient.

4. The urban ecological environment design method based on digital twins according to claim 3 is characterized in that: The acquisition logic of the water quality change index is as follows: The water quality impact assessment information was extracted from the pre-processed pollutant accumulation information, including the average concentration of pollutants, average nitrogen content, average phosphorus content, average dissolved oxygen level and average water temperature at different times during a period of seasonal rainfall in the city's central park, and calibrated as and represents the average concentration of pollutants in the city's central park at time n during a period of seasonal rainfall, represents the average nitrogen content of the city's central park at time n during a period of seasonal rainfall, represents the average phosphorus content in the city's central park at time n during a period of seasonal rainfall, represents the average dissolved oxygen level in the city's central park at time n during seasonal rainfall. represents the average water temperature of the city's central park at time n during a period of seasonal rainfall, n = 1, 2, 3, ..., h, h is a positive integer; Calculate the water quality change index. The specific calculation formula is as follows: Where WQI is the water quality change index.

5. The urban ecological environment design method based on digital twins according to claim 4 is characterized in that: Construct a pollution accumulation assessment model based on the generated pollutant diffusion coefficient and water quality change index to generate a pollution accumulation coefficient, which specifically includes the following steps: Collect several pollutant diffusion coefficients, several water quality change indices and corresponding pollution accumulation coefficients generated in the past period of time, and calibrate them as PDC x , WQI x and PAC x , x represents the serial numbers of several pollutant diffusion coefficients, several water quality change indexes and corresponding pollution accumulation coefficients generated in the past period of time, x = 3, 4, 5, ..., g, g is a positive integer, and the data collected in the past period of time are formed into a historical data set; The multivariate regression model is selected as the pollution accumulation assessment model, and is trained through historical data sets to determine the value of the regression coefficient according to the formula: PAC x =β0+β1*PDC x +β2*WQI x Where β0, β1 and β2 are regression coefficients; By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined; The final regression coefficient is used to construct the pollution accumulation assessment model, and the pollutant diffusion coefficient PDC and water quality change index WQI generated in real time are input to generate the pollution accumulation coefficient PAC in real time.

6. The urban ecological environment design method based on digital twins according to claim 5 is characterized in that: The generated pollution accumulation coefficient PAC is compared with the pre-set pollution accumulation coefficient threshold interval [PAC min , PAC max ] and compared them. The pollutant accumulation risk level of the city’s central park during seasonal rainfall was evaluated based on the comparison results. The specific comparison analysis is as follows: If PAC <PAC min , the pollutant accumulation risk level of the city's central park during seasonal rainfall is low risk level; If PAC min ≤PAC≤PAC max , the pollutant accumulation risk level of the city's central park during seasonal rainfall is medium risk level; If PAC>PAC max , the pollutant accumulation risk level in the city’s central park during seasonal rainfall is high.

7. The urban ecological environment design method based on digital twins according to claim 6 is characterized in that: Based on the assessment results, the potential impact of pollutant accumulation on water quality is determined and corresponding water quality management measures are initiated, including: If the assessment result shows that the risk level of pollutant accumulation in the city's central park during seasonal rainfall is low, the potential impact of pollutant accumulation on water quality is low, and the management measures to be taken are to continue water quality monitoring without adding new intervention measures; If the assessment result shows that the risk level of pollutant accumulation in the city's central park during seasonal rainfall is medium, the potential impact of pollutant accumulation on water quality is medium, and the management measures to be taken are to increase water mobility and filtration treatment to control pollutant accumulation; If the assessment result is that the risk level of pollutant accumulation in the city's central park during seasonal rainfall is high, the potential impact of pollutant accumulation on water quality is high, and the management measures taken are to reduce the concentration of pollutants in the water body through physical, chemical or mechanical means, increase pollutant treatment and water purification.

8. An urban ecological environment design system based on digital twins, used to implement the urban ecological environment design method based on digital twins as described in any one of claims 1 to 7, characterized in that: It includes water management target setting and environmental analysis module, pollutant accumulation information collection and transmission module, pollution accumulation risk assessment and analysis module, water quality impact assessment and management measures initiation module, and water quality management dynamic monitoring and strategy adjustment module; The water management goal setting and environmental analysis module determines the water management goals and environmental conditions of the city’s central park and builds a digital twin model to simulate the diffusion and accumulation effects of pollutants during seasonal rainfall; The pollutant accumulation information collection and transmission module collects pollutant accumulation information in the city’s central park during seasonal rainfall in real time, and transmits the collected pollutant accumulation information to the digital twin model through a data interface; The pollution accumulation risk assessment and analysis module analyzes the pollutant accumulation information input into the digital twin model and assesses the pollutant accumulation risk level of the city’s central park during seasonal rainfall; The water quality impact assessment and management measures initiation module determines the potential impact of pollutant accumulation on water quality based on the assessment results and initiates corresponding water quality management measures; The water quality management dynamic monitoring and strategy adjustment module continuously monitors the effectiveness of water quality management measures, dynamically adjusts water quality management strategies based on real-time feedback information, optimizes management measures, and maintains the balance of the water ecosystem in the city’s central park.

Images