Green infrastructure placement system for mitigating urban heat island effects

Abstract

The present invention relates to a green infrastructure placement system for mitigating the urban heat island effect and reducing carbon. The green infrastructure placement system for mitigating the urban heat island effect and reducing carbon comprises: an input / output interface that transmits and receives data with a GIS database and receives user data; a processor that performs optimization calculations based on the user data and GIS data; and a memory that stores optimization calculation and analysis data. The processor receives and analyzes map data, analyzes the area where rooftop greening is possible, the area where wall greening is possible, and the area where street trees can be planted based on the input map data, analyzes the carbon storage amount and cooling effect for the analyzed green space, performs optimization calculations, derives a green space placement scenario for each scenario based on the results of the optimization calculations, and displays the derived scenario to the user.

Description

Technology Field

[0001] The present invention relates to a green infrastructure deployment system for mitigating the urban heat island phenomenon, and more specifically, to an optimized green infrastructure deployment system capable of mitigating the urban heat island (UHI) phenomenon and maximizing carbon reduction effects. Background Technology

[0002] As urbanization progresses rapidly, the proportion of artificial structures (e.g., high-rise buildings) and paved roads increases in densely populated areas, acting as a major cause of the Urban Heat Island (UHI) phenomenon.

[0003] The urban heat island effect refers to the phenomenon where urban areas maintain higher temperatures than surrounding rural areas. Caused primarily by asphalt roads, concrete buildings, and industrial activities, this results in heat absorbed during the day not being sufficiently released at night. Consequently, this leads to rising urban temperatures, increased energy consumption, and worsening air pollution, making it a critical challenge that must be addressed for sustainable urban development and to respond to climate change, such as global warming.

[0004] Various technological approaches have been researched and developed to address these issues. Initially, the focus was primarily on expanding green spaces within cities, with representative methods proposed including planting street trees, creating parks, and greening rooftops and walls. In particular, plants have been regarded as essential elements for mitigating the urban heat island effect, as they have the effect of lowering temperatures through transpiration and shade formation.

[0005] Recently, research utilizing GIS (Geographic Information System) technology and optimization algorithms is actively underway to overcome spatial limitations and achieve more efficient heat reduction effects.

[0006] GIS technology is useful for analyzing environmental characteristics of specific regions using satellite and geospatial data, and research is ongoing to design appropriate green space layouts within cities based on this.

[0007] Furthermore, with the application of multi-objective optimization algorithms, research is also continuing to design optimal green space layouts that consider various goals, such as temperature reduction effects, carbon storage, and cost efficiency, rather than simply increasing green space area.

[0008] Furthermore, with the advancement of IoT (Internet of Things) and AI-based data analysis technologies, systems capable of continuously adjusting green space placement strategies by collecting and analyzing real-time climate data are also being researched.

[0009] Through this, green space management measures capable of flexibly responding to climate change or urban development plans in specific regions are being introduced, and demonstration studies utilizing smart green space management systems are underway in some advanced cities.

[0010] Based on these underlying technologies, there is a growing demand for technologies that go beyond simply expanding green spaces to effectively mitigate the urban heat island effect by designing optimal locations and combinations. In particular, technologies that derive realistically applicable green space layout plans within urban spaces by considering various environmental factors are gaining attention and are establishing themselves as essential elements for sustainable urban development and climate change response. The problem to be solved

[0011] One aspect aims to provide an optimal green infrastructure deployment system to mitigate the urban heat island effect.

[0012] In another aspect, we aim to provide optimal green space placement strategies to maximize carbon storage and create a sustainable urban environment.

[0013] In another aspect, we aim to provide a function that can analyze and visualize the results of green space placement in real time by utilizing GIS technology and open-source map visualization tools. means of solving the problem

[0014] A green infrastructure placement system for mitigating the urban heat island effect and reducing carbon according to one aspect includes: an input / output interface that transmits and receives data with a GIS database and receives user data; a processor that performs optimization calculations based on the user data and GIS data; and a memory that stores optimization calculation and analysis data. The processor receives and analyzes map data, analyzes the area where rooftop greening is possible, the area where wall greening is possible, and the area where street trees can be planted based on the input map data, analyzes the carbon storage amount and cooling effect for the analyzed green space, performs optimization calculations, derives a green space placement scenario for each scenario based on the results of the optimization calculations, and can display the derived scenario to the user.

[0015] In addition, for each of the scenarios provided by the processor, information on the rooftop greening area, wall greening area, and street tree area included in the corresponding region may be included.

[0016] In addition, the processor may provide at least one green space placement scenario that considers temperature reduction, carbon reduction, and budget limits.

[0017] In addition, the input / output interface receives a temperature reduction target, carbon storage target, or expected limit value entered by a user, and the processor can perform optimization calculations based on the temperature reduction target, carbon storage target, or expected limit value entered by the user.

[0018] In addition, the processor can derive an optimal green space placement strategy that simultaneously considers temperature reduction, carbon storage, and budget limits by applying an NSGA-II-based multi-objective optimization algorithm.

[0019] In addition, the above memory stores green space layout optimization results and analysis data, and can be retrained and updated as needed.

[0020] In addition, the processor may be characterized by applying ArcGIS-based spatial analysis techniques to filter the area suitable for rooftop greening, the area suitable for wall greening, and the area suitable for street tree planting.

[0021] In addition, the processor can calculate green space placement scenarios and expected effects according to long-term and short-term scenarios, provide comparative information based on the calculated information, and display a user-customized green space placement strategy based on this.

[0022] According to another aspect of the present invention, a method for deploying a green infrastructure deployment system for mitigating the urban heat island effect and reducing carbon emissions may be provided, comprising a processor that executes each of the steps described below, and the method comprising: a map data input step in which the green infrastructure deployment system receives and analyzes map data; a step of analyzing the area where rooftop greening is possible, the area where wall greening is possible, and the area where street trees can be planted based on the input map data; a step of analyzing the carbon storage amount and cooling effect for the analyzed green space and performing optimization calculations; a step of deriving a green space deployment strategy for each scenario based on the results of the optimization calculations; and a step of providing the derived scenario to a user and displaying it so that the user can select it.

[0023] In addition, by applying an NSGA-II-based multi-objective optimization algorithm, an optimal green space placement strategy can be derived that simultaneously considers temperature reduction, carbon storage, and budget limits. Effects of the invention

[0024] The present invention can optimize the placement of green spaces to suit the environment of each city by utilizing GIS data and a multi-objective optimization algorithm. Therefore, it can provide a method to effectively mitigate the urban heat island phenomenon.

[0025] In addition, by quantitatively analyzing the carbon storage amount, it can be designed to achieve the carbon sequestration effect of the target set by the user.

[0026] In addition, through GIS-based data visualization and real-time application capabilities, customized green space placement strategies for each city can be established using the same system anywhere in the world. Brief explanation of the drawing

[0027] FIG. 1 is an overall block diagram of a green infrastructure deployment system and a user terminal according to an embodiment. Figure 2 is a hardware server configuration diagram of a green infrastructure deployment system according to an embodiment. Figure 3 is a software server configuration diagram of a green infrastructure deployment system according to an embodiment. Figure 4 is a configuration diagram of a control unit provided in a green infrastructure deployment system according to an embodiment. Figure 5 is an example diagram showing street tree green space information analyzed by a green infrastructure placement system according to an embodiment. Figure 6 is an example diagram showing information on rooftop greening possible spaces analyzed by a green infrastructure layout system according to an embodiment. Figure 7 is a graph based on a plurality of expected scenarios analyzed by a green infrastructure deployment system according to an embodiment. Figure 8 is an example diagram according to a short-term scenario analyzed by a green infrastructure deployment system according to an embodiment. Figure 9 is an example table based on a long-term scenario analyzed by a green infrastructure deployment system according to an embodiment. Figure 10 is an example table according to an example long-term scenario in which the analysis results of a green infrastructure deployment system according to an embodiment are displayed. FIG. 11 is a flowchart of the operation of a green infrastructure deployment system according to an embodiment. Specific details for implementing the invention

[0028] Throughout the specification, the same reference numerals refer to the same components. This specification does not describe all elements of the embodiments, and general content in the art to which the invention pertains or content that overlaps between embodiments is omitted.

[0029] The terms 'part, module, component, device' as used in the specification may be implemented in software or hardware, and according to embodiments, a plurality of 'parts, modules, components, devices' may be implemented as a single component, or a single 'part, module, component, device' may include a plurality of components.

[0030] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are directly connected but also cases where they are indirectly connected, and indirect connections include connections made via a wireless communication network.

[0031] Furthermore, when it is stated that a part "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0032] The terms first, second, etc. are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0033] Singular expressions include plural expressions unless there is an obvious exception in the context.

[0034] In each step, identification codes are used for convenience of explanation and do not describe the order of the steps; the steps may be performed differently from the specified order unless a specific order is clearly indicated in the context.

[0035] The operating principle and embodiments of the present invention will be described below with reference to the attached drawings.

[0036] FIG. 1 is an overall block diagram of a green infrastructure deployment system and a user terminal according to an embodiment, and FIG. 2 and FIG. 3 are block diagrams describing the hardware or software configuration of a green infrastructure deployment system according to an embodiment.

[0037] Figure 4 is a configuration diagram of a control unit provided in a green infrastructure deployment system according to an embodiment.

[0038] The green infrastructure deployment system (1) includes a user device (200) and a server (100).

[0039] The user device (200) is capable of communicating with the server (100), and the user device (200) and the server (100) can transmit and receive mutual information, signals, or data.

[0040] Accordingly, the user device (200) can run a service platform of the green infrastructure deployment system (1), and the user device (200) may be one or more.

[0041] The service platform of the green infrastructure deployment system may provide an application for providing green infrastructure deployment services. Here, the application may be an application for providing green infrastructure deployment services.

[0042] Accordingly, the user device (200) can control the download, setup, and execution of an application to provide green infrastructure deployment services, and can provide a screen corresponding to the execution of the application to the user of the user device (i.e., client).

[0043] The user device (200) can be implemented as a computer or portable terminal capable of connecting to an external device (e.g., server) via a network, and is not limited to a specific device.

[0044] Here, the computer includes, for example, a laptop, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser, and the portable terminal is, for example, a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, smartphone, etc., and wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMDs).

[0045] The user device (200) can transmit location information to the server to receive green infrastructure deployment services through an application that provides green infrastructure deployment services.

[0046] The server (100) may be a local server and may run a platform for green infrastructure deployment services.

[0047] Such a server (100) can be implemented as a computer or portable terminal that can connect to an external device (e.g., user device, vehicle, second server, etc.) through a network.

[0048] Computers include, for example, laptops, desktops, laptops, tablet PCs, slate PCs, etc. equipped with a web browser, and portable terminals are wireless communication devices that ensure portability and mobility, and may include all kinds of handheld-based wireless communication devices such as PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminals, smartphones, etc.

[0049] The server (100) can be provided as a single device integrated with a green infrastructure deployment system.

[0050] The server (100) may include a server program on the system operation side, a web server for a website, an application server and a database server that provide green infrastructure deployment services, etc.

[0051] The server (100) is a platform device for cloud-based green infrastructure deployment services, which can secure high computing power and large-capacity database storage at a low cost, and can ensure stable system operation and high flexibility.

[0052] The server (100) can analyze rooftop greening, wall greening, and street tree greening spaces using map information received from one or more user devices (200), optimize the carbon storage amount and cooling effect of each greening type, calculate result values ​​for each scenario, and transmit and display information to the user devices (200).

[0053] The configuration of such a server (100) will be explained in detail later.

[0054] Specifically, as illustrated in FIG. 2, the server (100) includes an input / output interface (101), a processor (102), and a memory (103).

[0055] A server (100) according to one embodiment may include key hardware components such as an input / output interface (101), a processor (102), and a memory (103) to mitigate the urban heat island effect and optimize carbon reduction.

[0056] The input / output interface (101) includes a configuration for transmitting and receiving data between the server (100) and devices such as external sensors, databases, and user interfaces. Accordingly, the input / output interface (101) can collect input data in conjunction with GIS data, environmental sensors (temperature, humidity, wind speed), satellite data, etc.

[0057] Additionally, the input / output interface (101) can output result data through a display device and a network communication device.

[0058] The processor (102) is a component that performs major operations and control of the server (100), and plays the role of analyzing input data according to the method of the present invention and deriving analysis results.

[0059] This processor (102) may be composed of one or more processors. In this case, the one or more processors may be a general-purpose processor such as a CPU, AP, DSP (Digital Signal Processor), a graphics-dedicated processor such as a GPU, VPU (Vision Processing Unit), or an artificial intelligence-dedicated processor such as an NPU.

[0060] One or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if one or more processors are dedicated artificial intelligence processors, the dedicated artificial intelligence processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0061] The predefined behavioral rules or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a basic artificial intelligence model is trained using multiple training data by a learning algorithm, thereby creating predefined behavioral rules or artificial intelligence models configured to perform desired characteristics (or objectives).

[0062] Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is executed, or through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, and one embodiment of the present invention may include a method for deploying green infrastructure according to a reinforcement learning algorithm.

[0063] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and performs neural network operations through operations between the results of operations of the previous layer and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. Artificial neural networks may include deep neural networks (DNNs), such as, but are not limited to, CNNs (Convolutional Neural Networks), DNNs (Deep Neural Networks), RNNs (Recurrent Neural Networks), RBMs (Restricted Boltzmann Machines), DBNs (Deep Belief Networks), BRDNNs (Bidirectional Recurrent Deep Neural Networks), Deep Q-Networks, and LSTM algorithms.

[0064] Accordingly, the processor (102) may execute an LSTM-based temperature prediction model, a CNN-based plant monitoring or a reinforcement learning-based water usage optimization algorithm.

[0065] Next, the memory (103) serves to store data required during the computation process performed by the processor (102) and supports the execution of software programs and algorithms. The memory may include a main memory (RAM) and a secondary memory (e.g., SSD, HDD).

[0066] Specifically, the memory (103) includes a storage device that stores GIS data, environmental data, simulation results, weights of learned AI models, etc., and can store optimal placement scenarios for short-term and long-term goals and continuously update the optimization model by comparing existing data with new data.

[0067] The server (100) performs the role of analyzing environmental data within the city in real time, including these hardware elements, and deriving an optimal green infrastructure placement strategy.

[0068] Next, FIG. 3 is described as a software configuration block diagram of a server (100).

[0069] The server (100) includes a control unit (320), a communication unit (310), and a storage unit (330). Each component can work organically with one another to perform the function of an urban heat island optimization system.

[0070] First, the communication unit (310) can perform the role of transmitting and receiving data with external systems such as IoT sensors in the city, weather agency APIs, and GIS databases.

[0071] Accordingly, the communication unit (310) can collect a large amount of environmental data in real time through wireless communication (Wi-Fi, LTE, 5G) and wired communication. Specifically, the communication unit (100) may include various short-range communication modules that transmit and receive signals using a wireless communication network at a short range, such as a Bluetooth module, an infrared communication module, an RFID (Radio Frequency Identification) communication module, a WLAN (Wireless Local Access Network) communication module, an NFC communication module, and a Zigbee communication module.

[0072] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as USB (Universal Serial Bus), HDMI (High Definition Multimedia Interface), DVI (Digital Visual Interface), RS-232 (recommended standard 232), power line communication, or POTS (plain old telephone service).

[0073] In addition to Wi-Fi modules and WiBro (Wireless broadband) modules, the wireless communication module may include wireless communication modules that support various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), and LTE (Long Term Evolution).

[0074] Next, the control unit (320) refers to a central processing unit that performs core computation and optimization functions of the server (100).

[0075] For example, the control unit (320) includes a temperature prediction module, which can analyze future temperature changes through LSTM-based climate prediction.

[0076] In addition, the control unit (320) includes a plant health monitoring module and can analyze the health status of plants in the green space using CNN.

[0077] Additionally, the control unit (320) includes a water usage optimization module and may generate an optimal water supply strategy using reinforcement learning.

[0078] In addition, the control unit (320) can derive short-term and long-term scenarios and propose an optimal green infrastructure layout.

[0079] Next, the storage unit (330) includes a database that stores data and computation results processed by the green infrastructure deployment system (1), and the main data stored may include GIS-based urban green space data, temperature change prediction model data, carbon storage amount and cooling effect data for each green space type, deployment optimization results and policy simulation data, etc.

[0080] Therefore, the server (100) can use the data stored in the storage unit (330) as training data.

[0081] Accordingly, the server (100) collects real-time data through the communication unit (310), performs AI-based optimization operations in the control unit (320), and accumulates results in the storage unit (330) to enable continuous model improvement and simulation.

[0082] The operation of this control unit (320) is performed by the processor (102) of FIG. 2, and the hardware of FIG. 2 and the software of FIG. 3 are organically combined so that the urban heat island mitigation and carbon reduction optimization system can operate.

[0083] The control unit (320) provided in such a server (100) may include a detailed configuration as illustrated in FIG. 4.

[0084] For example, the control unit (320) may include an information collection unit (321), an information processing unit (322), and an information analysis unit (323).

[0085] Each of the information collection unit (321), information processing unit (322), and information analysis unit (323) functions may be performed by one processor or by different processors.

[0086] The configuration of the control unit of this embodiment will be divided into an information collection unit (321), an information processing unit (322), and an information analysis unit (323) and will be explained in detail later.

[0087] The control unit (320) may include at least one processor for controlling the operation of the server (100) and at least one memory in which a program and data for controlling the operation of the server (100) are stored.

[0088] At least one processor may include an algorithm for controlling the operation of internal components of the server (100), at least one memory for storing data in the form of a program, and one or more processor chips that perform the aforementioned operation using the data stored in at least one memory, or one or more processing cores.

[0089] At least one processor can process various data and various signals using instructions, data, programs and / or software stored in memory.

[0090] At least one processor may include one or more of a CPU (Central Processing Unit), GPU (Graphics Processing Unit), APU (Accelerated Processing Unit), MIC (Many Integrated Core), DSP (Digital Signal Processor), NPU (Neural Processing Unit), hardware accelerator, or machine learning accelerator.

[0091] The memory can store data necessary for various embodiments.

[0092] Depending on the purpose of data storage, the memory may be implemented in the form of memory embedded in the server (100) or in the form of memory that can be attached to the server (100). For example, data for operating the server (100) may be stored in memory embedded in the server (100), and data for the expansion functions of the server (100) may be stored in memory that can be attached to the server (100).

[0093] Meanwhile, the memory embedded in the server (100) may be implemented as at least one of volatile memory (e.g., DRAM (dynamic RAM), SRAM (static RAM), or SDRAM (synchronous dynamic RAM), non-volatile memory (e.g., OTPROM (one time programmable ROM), PROM (programmable ROM), EPROM (erasable and programmable ROM), EEPROM (electrically erasable and programmable ROM), mask ROM, flash ROM, flash memory (e.g., NAND flash or NOR flash), hard drive, or solid state drive (SSD).

[0094] In addition, the memory that can be attached to the server (100) may be implemented in the form of a memory card (e.g., CF (compact flash), SD (secure digital), Micro-SD (micro secure digital), Mini-SD (mini secure digital), xD (extreme digital), MMC (multi-media card), etc.) or an external memory that can be connected to a USB port (e.g., USB memory), but is not limited thereto.

[0095] The memory may include one or more memory chips or one or more memory blocks.

[0096] At least one component may be added or removed in response to the performance of the components of the server (100) illustrated in FIG. 4. Additionally, it will be readily understood by those skilled in the art that the relative positions of the components may be changed in response to the performance or structure of the server (100).

[0097] Each component shown in Fig. 4 refers to a software and / or hardware component such as a Field Programmable Gate Array (FPGA) and an Application Specific Integrated Circuit (ASIC).

[0098] The information collection unit (321) collects one or more user devices (200) or external environment data in real time.

[0099] The data collected by the information collection unit (321) may include weather data, GIS data, environmental sensor data, satellite images and drone data or user input data, and all data that can be used in the green infrastructure deployment algorithm may be included as information.

[0100] Specifically, weather data may include real-time climate data such as temperature, humidity, and wind speed, and the information collection unit (321) can collect weather information of a specific area by utilizing the weather agency API and IoT sensors.

[0101] Next, GIS (Geographic Information System) data is an information system for efficiently utilizing geographic information necessary for human life by converting it into computer data, and is called a geographic information system. Accordingly, the information collection unit (321) can collect spatial data such as street trees, rooftop greening, and wall greening areas within cities around the world.

[0102] Next, the information collection unit (321) can obtain environmental sensor data. For example, environmental sensor data may include CO2 concentration, air quality, and soil moisture content.

[0103] In addition, the information collection unit (321) may include satellite images and drone data, and may receive input from the user regarding green space placement goals and budget information set by the user.

[0104] Next, the information processing unit (322) performs the role of processing the data from the government collection unit (321) for analysis. For example, the information processing unit (322) can filter data and remove outliers, perform GIS-based identification and mapping of green spaces, analyze patterns of environmental change within the city, simulate data collected in real time, and perform the role of linking with a prediction model.

[0105] Next, the information analysis unit (323) includes a core computation module that executes AI-based analysis and optimization algorithms based on data processed by the information processing unit (322).

[0106] Specifically, the information analysis unit (323) includes a temperature prediction model, and uses an LSTM-based machine learning model to analyze climate patterns and predict future temperature changes.

[0107] In addition, the health status of green spaces can be evaluated and analyzed by utilizing a plant health monitoring model to analyze satellite images and plant sensor data.

[0108] In addition, the information analysis unit (323) includes a water usage optimization model, so that it can analyze to minimize resource waste by generating an optimal water supply schedule for green spaces using reinforcement learning, and by including a placement optimization algorithm, it can derive an optimal green infrastructure placement strategy according to short-term and long-term scenarios by utilizing NSGA-II (non-dominant alignment genetic algorithm).

[0109] In the above, through FIGS. 1 to 4, we have examined the configuration and respective functions of the green infrastructure deployment system (1).

[0110] Hereinafter, an embodiment performed in the green infrastructure deployment system (1) described in FIGS. 1 to 4 will be described in detail.

[0111] First, the example diagrams in FIGS. 5 and 6 are examples of information collected by the information collection unit (321) of the green infrastructure deployment system (1).

[0112] FIG. 5 is an example diagram showing street tree green space information analyzed by a green infrastructure placement system according to an embodiment, and FIG. 6 is an example diagram showing rooftop greening possible space information analyzed by a green infrastructure placement system according to an embodiment.

[0113] For example, FIG. 5 is an example diagram visualizing the results of an analysis of potential street tree planting spaces based on GIS data by a green infrastructure placement system according to one embodiment.

[0114] The green infrastructure placement system (1) can automatically identify optimal street tree placement areas by considering roads and pedestrian spaces within the city.

[0115] Specifically, the green infrastructure placement system (1) analyzes areas where street trees can be installed adjacent to roads using ArcGIS-based Street Line data and buffering techniques, and displays suitable areas for street trees along roads as suitability intensity in color.

[0116] For example, dark green areas indicate areas that are very suitable for planting street trees, while light green or gray areas indicate areas that are relatively less suitable or difficult to plant street trees.

[0117] Accordingly, the green infrastructure placement system (1) can analyze the roadside space based on collected GIS data, derive a suitable planting area, evaluate the possibility of planting street trees, and suggest an appropriate distance and placement from the existing road.

[0118] Next, FIG. 6 is an example diagram showing information on a rooftop greening-possible space analyzed by a green infrastructure placement system (1) according to an embodiment. The green infrastructure placement system (1) can evaluate the suitability of a building rooftop to identify a building that can be greened and propose an appropriate greening arrangement.

[0119] The green infrastructure placement system (1) is performed through the analysis of ArcGIS-based Red Band data and can detect building rooftops with specific reflectances to select areas where rooftop greening can be applied. Additionally, based on the analysis of the structural stability and strength of the building, the area where greening is possible is calculated, and an optimal placement plan can be derived considering the budget and feasibility of construction entered by the user.

[0120] For example, dark red areas indicate rooftops that are very suitable for greening, while light red, pink, or ivory areas indicate rooftops that are relatively less suitable or difficult to green.

[0121] Accordingly, the green infrastructure layout system (1) can analyze the rooftop green space to determine whether greening is possible based on the building's rooftop structure data, and calculate an optimal layout plan by considering the expected cooling effect and carbon storage amount.

[0122] For example, based on the figures of FIGS. 5 and 6, the green infrastructure placement system (1) utilizes Arc GIS data to identify the space where street trees can be installed adjacent to the road and the rooftop area of ​​the building.

[0123] Specifically, the green infrastructure placement system (1) can perform optimization calculations using a mathematical function that predicts the carbon storage amount and cooling effect of each type of green space. Through this, it is possible to automatically derive a green space placement strategy that can mitigate the urban heat island effect and maximize carbon reduction effects.

[0124] For example, the optimal carbon reduction effect within the city can be derived by applying the following [Equation 1] and [Equation 2] functions for predicting carbon storage by green space type.

[0125] [Formula 1]

[0126] C tree = N tree xG Biomass xF carbon

[0127] However, C tree is total carbon storage (kg CO2 / year), N tree is the number of street trees that can be planted per unit area, G Biomass is the average biomass growth rate (kg / year), F carbon represents the carbon storage ratio relative to biomass. Through this, the total annual carbon storage expected in the area can be estimated based on the area of ​​the street tree installation zone extracted in Figure 5.

[0128] As another example, the estimated annual carbon storage can be calculated based on the area of ​​the rooftop greening zone according to the following [Equation 2].

[0129] [Equation 2]

[0130] C roof = A roof xD veg xF carbon

[0131] However, C roof is the carbon storage capacity of rooftop greening (kg CO2 / year), A roof is the rooftop area eligible for greening, D veg is vegetation density per unit area (kg / m²) 2 ), Fcarbon represents the carbon storage ratio relative to biomass. Through this, the estimated annual carbon storage amount can be calculated based on the area of ​​the rooftop greening zone extracted in Fig. 6.

[0132] Next, the cooling effect can be predicted based on [Equation 3] and [Equation 4]. [Equation 3] is a formula for estimating the cooling effect caused by planting street trees, and [Equation 4] is a formula for estimating the cooling effect of rooftop greening.

[0133] [Equation 3]

[0134] T red,tree = N tree xE shade + A leaf xE transpiration

[0135] However, T red,tree is the expected temperature reduction due to roadside trees, N tree is the number of street trees that can be planted per unit area, E shade is the average shade effect of the tree (°C decrease / tree), A leaf is the total leaf area of ​​street trees (m² 2 ), E transpiration is the cooling effect due to transpiration (°C decrease / m 2 This means that the expected annual temperature reduction in the area can be estimated based on the area of ​​the street tree installation zone extracted in Figure 5.

[0136] Likewise, based on the following [Equation 4], the expected annual temperature reduction can be estimated based on the area of ​​the rooftop greening zone.

[0137] T red, roof = A roof x α cooling

[0138] However, T red, roof is the expected temperature reduction due to rooftop greening, A roof is the rooftop greening area, α coolingrepresents the cooling effect per unit area (°C reduction / ㎡). Through this, the cooling effect can be estimated based on the area of ​​the rooftop greening zone extracted in Figure 6.

[0139] In addition, although not described in FIGS. 5 and 6, the green infrastructure placement system (1) can estimate carbon storage and cooling effects due to wall greening.

[0140] A green infrastructure deployment system (1) according to one embodiment can derive an optimal green infrastructure deployment strategy that maximizes carbon storage and cooling effects by applying a multi-objective optimization algorithm to the carbon storage amount and cooling effect calculated in [Equation 1] to [Equation 4]. Below, an example of calculating results for a user's request scenario is described.

[0141] FIG. 7 is a graph showing the results of an analysis of a green infrastructure deployment system (1) according to an embodiment under various expected scenarios. The graph includes the results of a comparative analysis of carbon storage, temperature reduction effects, and cost efficiency under various deployment scenarios of green infrastructure.

[0142] Specifically, the green infrastructure deployment system (1) can present green infrastructure deployment optimization results considering short-term and long-term goals by utilizing NSGA-II (Non-dominated Sorting Genetic Algorithm II). Here, NSGA-II (Non-dominated Sorting Genetic Algorithm II) is an evolutionary algorithm that solves multi-objective optimization (MOO) problems. Unlike conventional single-objective optimization, NSGA-II considers multiple conflicting objective functions simultaneously and follows a method of deriving the set of best solutions (Pareto-optimal solutions).

[0143] The X-axis of Figure 7 was graphed by predicting scenario results based on various scenarios (e.g., setting short-term / long-term goals or target temperature reduction amount, cost reduction).

[0144] The X-axis represents various scenarios (e.g., setting short-term / long-term goals and target temperature reduction of 1°C, 3°C, 5°C, and considering cost reduction), and the Y-axis represents green area (㎡). The green graph represents (Tree Area, m²): street tree area, the light green graph represents (Green Roof Area, m²): rooftop greening area, and the yellow represents (Green Wall Area, m²): wall greening area.

[0145] The green infrastructure placement system (1) of the present invention optimizes the area of ​​street trees, rooftop greening, and wall greening according to each scenario to maximize the goals of mitigating the urban heat island effect and reducing carbon emissions.

[0146] For example, in the case of the short-term goal scenario, it can be confirmed that the results show a relatively large area for street tree planting to mitigate the urban heat island, while the areas for wall and rooftop greening are arranged at an appropriate level.

[0147] In the case of the long-term goal scenario, by actively utilizing rooftop and wall greening along with street tree planting to maximize carbon reduction effects, it can be confirmed that results were obtained in which carbon storage and temperature reduction effects are balanced across the entire city in the long term.

[0148] When considering the cost-saving scenario, it can be confirmed that adopting a wall greening method leads to cost reduction.

[0149] FIG. 8 is an example diagram according to a short-term scenario analyzed by a green infrastructure deployment system according to an embodiment, and FIG. 9 is an example table according to a long-term scenario analyzed by a green infrastructure deployment system according to an embodiment.

[0150] Figure 8 shows the results of optimizing the placement of green infrastructure based on the setting of short-term goals. This system applies a strategy to maximize the immediate heat island mitigation effect in the short term and enables the achievement of the target heat reduction amount by optimally arranging street trees, rooftop greening, and wall greening areas.

[0151] For example, the short-term optimization strategy shown in Figure 8 involves planting street trees to maximize the immediate heat reduction effect, and it can be seen that this is a strategy that can rapidly lower the temperature in the city center in the short term.

[0152] It can be confirmed that a strategy has been derived in which rooftop and wall greening, which account for a small proportion compared to street tree planting, are utilized as auxiliary means to perform a complementary role to street trees.

[0153] If the optimization is recalculated based on an increase in the target temperature reduction amount (3°C → 5°C) within the system, it can be seen that the ratio of rooftop greening and wall greening area increases together as the temperature reduction target increases.

[0154] Next, Figure 9 shows that the area of ​​rooftop and wall greening has increased to maximize the carbon storage effect. In other words, the long-term scenario in Figure 9 is a result calculated to ensure that carbon reduction and temperature mitigation effects can be continuously maintained over the long term.

[0155] The green infrastructure placement system (1) of the present invention can provide an optimized green space placement strategy based on short-term and long-term goal scenarios presented in FIGS. 7 to 9. Additionally, although not separately illustrated, it may be designed to obtain customized optimization results by allowing the user to directly specify desired goals (amount of temperature reduction, amount of carbon storage, budget, etc.). The system (1) of the present invention may additionally include a function that can automatically calculate and present an optimal green infrastructure placement strategy immediately based on user input data.

[0156] Accordingly, the user can directly set various environmental and economic goals, and the system can automatically suggest the optimal green infrastructure placement suitable for those goals. To this end, a green infrastructure placement system (1) according to one embodiment performs optimization calculations using the following key user input values.

[0157] Users can directly input a temperature reduction goal (T goal). For example, if the goal is to reduce the temperature by 2°C or 3.5°C in a specific area, the system can calculate and suggest the optimal ratio of street trees, rooftop greening, and wall greening to achieve the goal.

[0159] Users can also set a carbon storage goal (C goal). If a specific annual carbon storage target (e.g., 1.2 tons / year) is set, the system analyzes combinations of street trees, rooftop greening, and wall greening to optimize placement strategies to meet the target.

[0160] The budget limit (B limit) can also be set directly by the user. For example, it can be optimized to achieve the maximum heat reduction effect within a set budget (e.g., 5 million USD), and the system prioritizes the placement of cost-effective green types to produce optimal results.

[0161] Therefore, this system can perform multi-objective optimization by executing the NSGA-II algorithm based on target values ​​entered by the user. It derives the most appropriate green space placement strategy by simultaneously considering target temperature reduction, carbon storage, and budget, and can automatically calculate and propose area allocations for each green space type.

[0162] In addition, the green infrastructure placement system (1) of the present invention may include a real-time simulation function. When a user changes input values, an optimized green space placement result is immediately derived, and the expected temperature reduction effect, carbon storage amount, and cost-effectiveness can be provided simultaneously. Through this, the user can intuitively verify and apply the optimal green space placement strategy tailored to the desired goal.

[0163] In addition, as an example, the green infrastructure placement system (1) can also calculate the optimal green space placement strategy by considering the type and quantity of trees according to the percentage per area set by the user and the nationality and geographical characteristics of the user.

[0164] For example, the user 1000m 2 If 30% of the area is set as green space, a combination of street trees, shrubs, ground cover plants, etc. suitable for that area can be proposed.

[0165] In addition, the green infrastructure deployment system (1) can intuitively check recommendation results through real-time data visualization. For example, visual representation based on a map can be made using GIS data, and in particular, HTML-based GIS visualization code can be built using open source OpenStreetMap contributors such as 'Leaflet' so that it can be accessed anywhere in the world.

[0166] For example, FIG. 10 is a schematic diagram showing the results of a green infrastructure placement system (1) visually displayed on a map according to the characteristics of each region.

[0167] The street tree area (green marker) corresponds to location [-7.2754, 112.7321], and is a suitable area for planting street trees as it has wide roads and pedestrian areas. Therefore, the green infrastructure layout system (1) displays that the street trees (Urban Forest) have a high carbon storage capacity of 100 kgCO2 / m2 / year, so that the user can verify this information.

[0168] Next, the rooftop greening area (blue marker) corresponds to location [-7.2575, 112.7521], which is a densely populated area with large buildings within a commercial district and is suitable for rooftop greening. This greening method can be displayed so that users can verify that it contributes to mitigating the urban heat island effect by providing an average temperature reduction effect of 2.0°C.

[0169] Next, the wall greening zone (red marker) corresponds to location [-7.2432, 112.7377], which is a densely populated area with five-story mid-rise buildings and is suitable for wall greening. Wall greening plays a complex role in environmental improvement by simultaneously providing carbon storage and temperature reduction effects. Through this, it can be displayed so that users can verify that it contributes to temperature control and air quality improvement within the city.

[0170] Accordingly, the green infrastructure deployment system (1) according to the present invention can provide a variety of possible scenarios tailored to the characteristics of each region and city.

[0171] That is, the green infrastructure deployment system (1) can utilize a multi-objective optimization algorithm to consider three elements of green infrastructure according to short-term and long-term goal scenarios through the Non-Dominated Sorting Genetic Algorithm.

[0172] The green infrastructure deployment system (1) can therefore adjust the installation ratio of each infrastructure according to the rate of heat reduction, and it is possible to derive various scenarios rather than just one best method.

[0173] Therefore, since the green infrastructure placement system (1) can propose various scenarios, it can display areas where installation is realistically possible, allowing the user to select them while avoiding areas with high assessed land values ​​or planned development plans when making policy decisions.

[0174] In the above, the functions provided by the green infrastructure placement system (1) have been described. Below, the operation process of the green infrastructure placement system (1) of the present invention, which is designed to apply an optimization algorithm utilizing GIS data to maximize the effects of mitigating the urban heat island effect and reducing carbon, and to provide a user-customized green space placement strategy based on this, is configured in steps as shown in the flowchart, and the details of each step are as follows.

[0175] In the map data input (1101) step, the processor (102) in the system receives GIS-based map data and performs analysis to optimize the placement of green spaces within the city. The map data may consist of satellite data, urban planning data, environmental sensor data, etc., thereby obtaining spatial information to analyze potential green areas for rooftops, walls, and street trees within the city.

[0176] In addition, map data can be updated in real-time to maintain up-to-date status and can reflect the structural characteristics of buildings, existing green spaces, road networks, etc.

[0177] In the analysis of rooftop greening, wall greening, and street tree greening spaces (1102), the processor (102) automatically identifies greening spaces based on input map data and determines the applicable greening type for each space. In this process, ArcGIS-based spatial analysis techniques can be used to calculate the area suitable for rooftop greening, determine building structures suitable for wall greening, and identify areas suitable for planting street trees around roads.

[0178] In step 1102, the processor (102) can select optimal green space placement candidate sites by taking into account building structure, urban density, pedestrian space, environmental constraints, etc. However, the processor (102) may also perform the task of identifying only green space possible spaces at a map location selected by the user.

[0179] In the step of optimizing carbon storage and cooling effects for each type of green space (1103), optimization operations are performed to predict carbon storage and cooling effects for selected rooftops, walls, and street tree green spaces. To this end, the processor (102) applies an LSTM-based temperature prediction model, a CNN-based vegetation health analysis model, and an NSGA-II-based multi-objective optimization algorithm to mathematically analyze the temperature reduction effect and carbon reduction effect of each type of green space.

[0180] For example, an LSTM-based temperature prediction model can be used to analyze climate change over time and predict future temperature patterns. This model takes weather data (temperature, humidity, wind speed, precipitation) and urban environment data (road network, green space, building density) as input and predicts the expected temperature at a specific point in the future. Accordingly, the processor (102) is designed to learn urban heat island data and seasonal patterns from the past 10 years to predict short-term and long-term temperature changes.

[0181] For example, a CNN-based vegetation health analysis model is used to analyze the condition of green infrastructure (street trees, rooftop greening, and vertical greening) and to identify areas requiring maintenance and improvement of healthy green spaces. This model can also receive satellite imagery, drone footage, soil sensor data, and infrared imagery to analyze plant growth status, soil moisture levels, and leaf color changes (indicating the presence of disease or water stress).

[0182] In addition, for example, the processor (102) can derive an optimal green space placement strategy by simultaneously considering temperature reduction, carbon reduction, and budget constraints using an NSGA-II-based multi-objective optimization algorithm. The model can perform optimization calculations by utilizing LSTM-based temperature prediction results and CNN-based vegetation health analysis results. Therefore, when a user-set temperature reduction target (°C), carbon storage target (tons / year), and budget limit (USD) are input as input values, the optimal placement area and expected effect of street trees, rooftop greening, and wall greening can be output as the result of the optimization calculation.

[0183] Accordingly, for example, when a user's policy goal (e.g., temperature reduction of 3°C, carbon storage of 1.2 tons / year, budget of 5 million USD) is entered, the processor (102) can perform an operation to optimally place the most appropriate green space type by reflecting the user's policy goal.

[0184] Subsequently, in the step of calculating the result value for each scenario (1104), the processor (102) calculates and compares the result value for each scenario based on the green space placement strategy derived through optimization calculation. In this process, based on the scenarios presented in FIGS. 7 to 9 (short-term / long-term goals, temperature reduction amount, carbon storage amount, budget consideration), the optimally placed green space area and expected effect for each scenario are quantitatively calculated. For example, if street trees of 75㎡, rooftop greening of 45㎡, and wall greening of 30㎡ are placed in a specific area, the expected heat reduction effect and carbon storage amount can be automatically calculated and provided.

[0185] In the step of selecting a desired scenario (1105), the calculated results are provided to the user, enabling the user to select the optimal scenario. This system provides visual data for each scenario (map-based analysis results, simulation graphs, and expected effects) through a user interface (UI), allowing the user to directly select a scenario that aligns with policy objectives based on this data. The selected scenario can be utilized for establishing and implementing actual green space placement strategies, and, if necessary, can be optimized by modifying simulation results in real time or reflecting new objectives.

[0186] Through this series of processes, this system optimizes the placement of green infrastructure based on data and supports the establishment of user-customized environmental policies rather than simply presenting scenarios. This enables the maximization of effects such as urban heat island mitigation, carbon reduction, and energy savings.

[0187] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium that stores instructions executable by a computer. The instructions may be stored in the form of program code, and when executed by a processor, they may generate a program module to perform the operation of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0188] Computer-readable recording media include all types of recording media that store instructions that can be decoded by a computer. Examples include ROM (Read Only Memory), RAM (Random Access Memory), magnetic tape, magnetic disk, flash memory, optical data storage devices, etc.

[0189] As described above, the disclosed embodiments have been explained with reference to the attached drawings. Those skilled in the art will understand that the present invention may be practiced in forms different from the disclosed embodiments without changing the technical concept or essential features of the present invention. The disclosed embodiments are illustrative and should not be interpreted restrictively. Explanation of the symbols

[0190] 100: Green Infrastructure Deployment System 101: Input / Output Interface 102: Processor 103: Memory 320: Control unit 310: Communications Department 330: Storage section 321: Information Gathering Department 322: Information Processing Unit

Claims

Claim 1 A green infrastructure placement system for mitigating the urban heat island effect and reducing carbon emissions comprises: an input / output interface that transmits and receives data with a GIS database and receives user data; a processor that performs optimization calculations based on the user data and GIS data; and a memory that stores optimization calculation and analysis data, wherein the processor receives and analyzes map data, analyzes the area where rooftop greening is possible, the area where wall greening is possible, and the area where street trees can be planted based on the input map data, analyzes the carbon storage amount and cooling effect for the analyzed green space, performs optimization calculations, derives a green space placement scenario for each scenario based on the results of the optimization calculations, and displays the derived scenario to a user. Claim 2 A green infrastructure placement system according to claim 1, comprising information on rooftop greening area, wall greening area, and street tree area included in the corresponding region for each of the scenarios provided by the processor. Claim 3 In claim 2, the processor provides a green infrastructure placement system including at least one green space placement scenario that considers temperature reduction, carbon reduction, and budget limits. Claim 4 A green infrastructure deployment system according to claim 3, wherein the input / output interface receives a temperature reduction target, carbon storage target, or expected limit value entered by a user, and the processor performs an optimization operation based on the temperature reduction target, carbon storage target, or expected limit value entered by the user. Claim 5 In claim 4, the processor is a green infrastructure placement system that derives an optimal green space placement strategy considering temperature reduction, carbon storage, and budget limits simultaneously by applying an NSGA-II-based multi-objective optimization algorithm. Claim 6 In paragraphs 1 through 5, the memory stores green space layout optimization results and analysis data, and is capable of retraining and updating as needed, in a green infrastructure layout system. Claim 7 A green infrastructure placement system according to claim 1, wherein the processor filters the rooftop greening area, the wall greening area, and the street tree planting area by applying an ArcGIS-based spatial analysis technique. Claim 8 In paragraph 3, the processor calculates green space placement scenarios and expected effects according to long-term and short-term scenarios, provides comparative information based on the calculated information, and displays a user-customized green space placement strategy based thereon. Claim 9 A method for deploying a green infrastructure deployment system for mitigating the urban heat island effect and reducing carbon, comprising a processor that executes each step described below, and comprising: a map data input step in which the green infrastructure deployment system receives and analyzes map data; a step of analyzing the area where rooftop greening is possible, the area where wall greening is possible, and the area where street trees can be planted based on the input map data; a step of analyzing the carbon storage amount and cooling effect for the analyzed green space and performing optimization calculations; a step of deriving a green space deployment strategy for each scenario based on the results of the optimization calculations; and a step of providing the derived scenario to a user and displaying it so that the user can select it. Claim 10 A green infrastructure placement method according to claim 9, which derives an optimal green space placement strategy that simultaneously considers temperature reduction, carbon storage, and budget limits by applying an NSGA-II-based multi-objective optimization algorithm.

Images