Layout system and method for climate-adaptive land space ecological infrastructure planning

Abstract

The application discloses a climate-adaptive land space ecological infrastructure planning layout system and method, relates to the field of facility management, and can automatically adjust a redundancy multiple according to the frequency of historical extreme climate events, dynamically optimizes a climate data processing strategy, and enhances the adaptability and anti-risk ability of the system by introducing an extreme climate threshold judgment mechanism. In addition, by collecting climate data and dynamically adjusting the valve state, the system automatically optimizes the drainage pipe network operation strategy, improves the self-adaptability of the system, and simultaneously, by statistically analyzing the valve switching frequency and automatically upgrading the frequently-switched valve to a remote control valve, the self-optimization and upgrading of the system are realized. In summary, the application can significantly improve the configuration efficiency, operation efficiency and maintenance efficiency of the land space flood prevention infrastructure, and provides scientific technical support and management means for urban flood control and drainage and ecological infrastructure construction.

Description

Technical Field

[0001] This invention belongs to the field of facility management, and more specifically, relates to a system and method for planning and laying out climate-adaptive national spatial ecological infrastructure. Background Technology

[0002] Traditional configuration methods lack dynamic adjustment mechanisms in the face of extreme weather events and cannot automatically optimize data processing strategies based on the frequency of historical extreme weather events, resulting in insufficient system adaptability and risk resistance. In addition, traditional drainage network operation and management lacks real-time response capabilities and cannot automatically adjust operation strategies according to environmental changes. In terms of valve control, traditional configuration methods mostly adopt fixed control methods and lack statistical analysis of valve usage status and intelligent upgrade mechanisms, making it impossible to achieve system self-optimization and maintenance. Summary of the Invention

[0003] In response to the problems in related technologies, this invention proposes a climate-adaptive land space ecological infrastructure planning and layout system and method to overcome the aforementioned technical problems existing in the existing related technologies.

[0004] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution: This invention provides a method for planning and laying out climate-adaptive national spatial ecological infrastructure, comprising the following steps: S1. Set the types of ecological infrastructure and its performance parameters, climate response indicators and drainage network structure parameters, and collect existing infrastructure, area and climate history data in the national land space. S2. Construct the final infrastructure-pipeline layout mapping model based on the data collected in S1; S3. Set an extreme climate threshold. If the historical data is greater than or equal to the extreme climate threshold, double the climate data according to the redundancy factor, and input the doubled data into the mapping model in S2 for mapping. S4. Based on the mapping results in S3, arrange the current ecological infrastructure and drainage network and install manually controlled valves with numbers. Collect valve opening and closing status and climate index data within the period and construct the final connection control valve status mapping model. S5. Collect climate data in real time and input it into the mapping model in S4 to map and adjust the valve status; after repeated execution, count the number of switching times of each valve, and replace the valve with the number of switching times greater than the preset threshold with a remote control valve. S6. After the valve replacement in S5 is completed, repeat the valve status adjustment process in S5 and count the number of control valve switching times again. When the number of switching times reaches the preset condition, increase the redundancy multiple in S3. After increasing, expand the infrastructure configuration and repeat the statistical process in S4, S5 and S6 until the number of switching times no longer reaches the preset condition.

[0005] Preferably, step S1 includes the following steps: S11. Define several types of ecological infrastructure used in the national land space that are rainwater-resistant and can be quickly deployed, to obtain a set of ecological infrastructure types; the set of ecological infrastructure types includes prefabricated rainwater storage tanks and prefabricated infiltration wells, etc. Based on the set of ecological infrastructure types, several performance parameter types are set for each type of facility to obtain the set of infrastructure performance parameter types. S12. Set several climate response indicators to obtain a climate response indicator type set; the climate response indicator type set includes rainfall per unit time, precipitation frequency, temperature per unit time, and humidity per unit time, etc.; then set several structural parameter types corresponding to the drainage pipe network used in the land space to obtain a drainage pipe network structural parameter type set; the drainage pipe network structural parameter type set includes the number of main pipes and the total number of branch pipes between adjacent main pipes. S13. Based on the set of climate response index types and the set of ecological infrastructure types, collect the corresponding climate response index data, total land area data, and corresponding drainage network structure parameter data, the number of various ecological infrastructures and their performance parameters in several existing land spaces with drainage pipe networks, to obtain the existing climate response index dataset, the existing total land area dataset, the existing structure parameter dataset, the existing infrastructure layout quantity set and the existing infrastructure performance parameter dataset. By comprehensively monitoring and collecting data on climate response indicators, and combining them with drainage network topology parameters, a data foundation covering the entire chain of climate-driven factors, facility response, and network capacity has been formed.

[0006] Preferably, step S2 includes the following steps: S21. Based on the existing climate response index dataset, the existing total land area dataset, the existing structural parameter dataset, the existing infrastructure layout quantity dataset, and the existing infrastructure performance parameter dataset, construct a mapping model with various climate response index data and total land area data as inputs and drainage pipe network structural parameter data, various ecological infrastructure layout quantity and performance parameter data as outputs, to obtain the final infrastructure-pipe network layout mapping model. By integrating existing multi-source heterogeneous spatial data, the model can identify the optimal pipeline topology parameters and ecological facility combinations under different climatic conditions, thus possessing stronger adaptability and robustness in the face of future climate change.

[0007] Preferably, step S3 includes the following steps: S31. Set the initial redundancy multiple and the threshold for the number of extreme climate events, and combine historical data to obtain various climate response index data of the current national land space and the number of extreme climate events in history, so as to obtain the current initial climate response index dataset and the current number of extreme climate events. If the current number of extreme weather events is greater than or equal to the threshold number of extreme weather events, the data in the current initial climate response index dataset is doubled according to the initial redundancy factor to obtain the current final climate response index dataset; otherwise, no doubling is performed. S32. Input the current final climate response index dataset and the current land area data into the final infrastructure-pipeline layout mapping model for mapping to obtain the current structural parameter dataset, the current infrastructure layout quantity set and the current infrastructure performance parameter dataset. When the system detects that the number of historical extreme weather events in the target area has reached or exceeded a preset threshold, it will automatically start the data redundancy amplification program, enabling the subsequent mapping model to optimize the infrastructure layout under more stringent climate scenarios. This effectively avoids the problem of insufficient infrastructure defense caused by the limitations of historical data in traditional planning, and ensures that the planning scheme has sufficient safety margin.

[0008] Preferably, step S4 includes the following steps: S41. Based on the current infrastructure layout quantity set and the current infrastructure performance parameter dataset, the ecological infrastructure of the current land space is arranged; then, based on the current structural parameter dataset, the drainage network of the current land space is arranged. During the arrangement process, a manual connection control valve is installed in each main pipe and branch pipe of the drainage network of the current land space to obtain the current first connection control valve set; each valve in the current first connection control valve set is numbered and has two states: open and closed. S42. Set the current valve switch data acquisition cycle; after the installation of each connected control valve in S41 is completed, divide the current valve switch data acquisition cycle into multiple sub-cycles. In each sub-cycle, obtain the average data of various climate response indicators and the corresponding number and switch status of each connected control valve to obtain the historical climate response indicator dataset, the historical connected control valve number set, and the historical connected control valve status dataset. S43. Based on the historical climate response index dataset, the historical connectivity control valve number set, and the historical connectivity control valve status dataset, construct a mapping model with various climate response index data as input and the numbers and on / off states of each connectivity control valve as output, and obtain the final connectivity control valve status mapping model. The system can dynamically adjust the water flow path and distribution strategy within the pipeline network according to real-time climate conditions, rather than the traditional fixed flow direction mode; by setting an adaptive valve status acquisition cycle and keeping the valve status stable in each sub-cycle, the synchronization between the control strategy and changes in climate conditions is ensured.

[0009] Preferably, step S5 includes the following steps: S51. After the current valve switch data collection cycle ends, set the climate response index data collection interval and collect various climate response index data of the current land space in real time based on this interval to obtain the current real-time climate response index dataset. The current real-time climate response index dataset is input into the final connectivity control valve state mapping model for mapping, to obtain the current real-time connectivity control valve number set and the current real-time connectivity control valve state dataset; S52. Based on the current real-time connectivity control valve number set and the current real-time connectivity control valve status dataset, adjust the status of the connectivity control valves set in the drainage network in the current national land space in real time. S53. Repeat S51 and S52 multiple times and record the datasets mapped in S52 during each repetition and integrate them to obtain the current first statistical connectivity control valve number set and the current first statistical connectivity control valve status dataset. Set a first switching count threshold; calculate the number of state switching for each connection control valve based on the current first statistical connection control valve number set and the current first statistical connection control valve status dataset to obtain the current first statistical status switching count set; S54. Replace the connection control valves corresponding to the data in the current first statistical state switching count set that are greater than or equal to the first switching count threshold with connection control valves controlled by remote signals to obtain the current second connection control valve set; By statistically analyzing the valve state switching frequency, the system can identify control nodes that operate frequently. These nodes are often located at critical positions in the system's operation, thus providing accurate decision-making basis for subsequent equipment upgrades. Upgrading valves with high-frequency switching to remote signal control valves not only improves control accuracy and response speed but also enhances the system's maintainability and remote management capabilities.

[0010] Preferably, step S6 includes the following steps: S61. Set the threshold for the number of control valve switching and the second switching count threshold; Based on the current second connected control valve set, repeat S51 and S52 multiple times, record the dataset mapped in S52 during each repetition, and integrate them to obtain the current second statistical connected control valve number set and the current second statistical connected control valve status dataset. Based on the current second statistical connection control valve number set and the current second statistical connection control valve status dataset, the number of state switching times for each connection control valve is calculated again to obtain the current second statistical state switching count set. S62. If the current second statistical state switching count set contains data greater than or equal to the second switching count threshold and the corresponding number of data is greater than or equal to the control valve switching count threshold, increase the initial redundancy factor and repeat S31 and S32 to obtain the current expanded structural parameter dataset, the current expanded infrastructure layout set, and the current infrastructure performance parameter dataset; otherwise, it is not necessary to increase the initial redundancy factor. Based on the current expanded structural parameter dataset, the current expanded infrastructure layout quantity set, and the current infrastructure performance parameter dataset, the drainage network and ecological infrastructure of the current national land space are expanded or replaced; after expansion or replacement, S41, S42, S43, S51, S52, S53, S54, and S61 are repeated until the current second statistical state switching count set contains data greater than or equal to the second switching count threshold and the corresponding number of data is less than the control valve switching count threshold, or the current second statistical state switching count set does not contain data greater than or equal to the second switching count threshold; When multiple valves are detected to be switching at high frequency, the system automatically triggers a dynamic adjustment mechanism for redundancy multiples. By expanding the initial climate data, the system re-optimizes the infrastructure layout and configuration, thereby reducing the pressure on each valve and pipeline and extending the average service life of each valve and pipeline. It also avoids the limitations of one-time static design in traditional planning and ensures that the infrastructure configuration is always highly matched with dynamic climate conditions and operational requirements.

[0011] The climate-adaptive territorial spatial ecological infrastructure planning and layout system includes a data acquisition module, a layout mapping model construction module, a doubling and mapping module, a state mapping model construction module, a control valve replacement module, and a multiplier adjustment module. The data acquisition module is used to collect existing data on infrastructure, area, and historical climate in the national territory. The layout mapping model building module is used to build the final infrastructure-pipeline layout mapping model; The doubling and mapping module is used to double climate data; The state mapping model building module is used to build the final connected control valve state mapping model; The control valve replacement module is used to adjust or replace the valve status; The redundancy adjustment module is used to adjust the current redundancy multiple and expand the infrastructure configuration after adjustment.

[0012] The present invention has the following beneficial effects: 1. The infrastructure-pipeline layout mapping model constructed in this invention can effectively predict and optimize infrastructure configuration schemes, improving the scientificity and rationality of resource allocation. By introducing an extreme climate threshold judgment mechanism, the redundancy factor can be automatically adjusted according to the frequency of historical extreme climate events, dynamically optimizing climate data processing strategies and enhancing the system's adaptability and risk resistance. In addition, by collecting climate data in real time and dynamically adjusting valve status, the drainage pipeline operation strategy can be automatically optimized according to real-time environmental changes, improving the system's adaptability. Furthermore, by statistically analyzing the number of valve switching and automatically upgrading frequently switched valves to remote control valves, the system achieves self-optimization and upgrading. In summary, this invention can significantly improve the configuration efficiency, operation efficiency, and maintenance efficiency of land space precipitation prevention infrastructure, providing scientific technical support and management methods for urban flood control, drainage, and ecological infrastructure construction. 2. In this invention, when the system detects that the number of historical extreme weather events in the target area reaches or exceeds a preset threshold, it will automatically start a data redundancy amplification program, thereby effectively avoiding the problem of insufficient infrastructure defense caused by the limitations of historical data in traditional planning. Especially in the context of climate change exacerbating the frequent occurrence of extreme weather, it ensures that the planning scheme has sufficient safety margin. 3. In this invention, by selecting only the control valves that switch at high frequencies for replacement, the equipment cost is reduced to the greatest extent while meeting the drainage requirements; Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of the invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a flowchart illustrating the climate-adaptive land space ecological infrastructure planning and layout method of the present invention. Figure 2 This is a contour cloud map of the spatial precipitation ecological infrastructure regulation capacity of the land in this invention; wherein, the precipitation regulation comprehensive index is a dimensionless index; Figure 3 This is a heat map showing the correlation between territorial spatial ecological infrastructure, climate, and pipeline networks in this invention. Figure 4The graphs are line graphs of climate data and drainage network valve data of this invention; the upper left is a line graph of historical climate data and year, the lower left is a line graph of valve switching frequency and valve number, the upper right is a line graph of current climate data and month, and the lower right is a line graph of valve control status and valve number. Figure 5 This is a hierarchical clustering tree diagram of the control valves for the land space drainage network in this invention. Figure 6 This is a scatter plot showing the iterative optimization of the drainage network control valves according to the present invention. Detailed Implementation

[0015] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0016] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0017] Example 1 Please see Figure 1 , Figure 4 This embodiment describes a method for planning and laying out climate-adaptive national spatial ecological infrastructure, which includes the following steps: S1. Set the types of ecological infrastructure and its performance parameters, climate response indicators and drainage network structure parameters, and collect existing infrastructure, area and climate history data in the national land space. Please see Figure 2 , Figure 3 S1 includes the following steps: S11. Define several types of ecological infrastructure used in the national land space that are rainwater-resistant and can be quickly deployed, to obtain a set of ecological infrastructure types; the set of ecological infrastructure types includes prefabricated rainwater storage tanks and prefabricated infiltration wells, etc. Based on the set of ecological infrastructure types, several performance parameter types are set for each type of facility to obtain the set of infrastructure performance parameter types. The contents of the infrastructure performance parameter types are shown in Table 1 below: Table 1. Examples of Infrastructure Performance Parameter Types

[0018] S12. Set several climate response indicators to obtain a climate response indicator type set; the climate response indicator type set includes rainfall per unit time (such as daily average rainfall), precipitation frequency, temperature per unit time (such as daily average temperature), and humidity per unit time (daily average relative humidity, absolute humidity, etc.); the climate response indicator data in the climate response indicator type set can be monitored in real time by sensors such as temperature and humidity sensors. Then, several structural parameter types are defined for the drainage pipe network (used to discharge rainwater) used in the national land space, resulting in a set of drainage pipe network structural parameter types; the set of drainage pipe network structural parameter types includes the number of main pipes and the total number of branch pipes between adjacent main pipes; S13. Based on the set of climate response index types and the set of ecological infrastructure types, collect the corresponding climate response index data, total land area data, and corresponding drainage network structure parameter data, the number of various ecological infrastructures and their performance parameters in several existing land spaces with drainage pipe networks, to obtain the existing climate response index dataset, the existing total land area dataset, the existing structure parameter dataset, the existing infrastructure layout quantity set and the existing infrastructure performance parameter dataset. By mapping and associating ecological facilities (such as prefabricated rainwater storage tanks and prefabricated infiltration wells) with their performance parameters (such as corrosion resistance and filtration efficiency), facility selection and layout are no longer based solely on experience-based judgments, but rather on optimized configuration based on their actual performance characteristics. Simultaneously, through comprehensive monitoring and data collection of climate response indicators (such as rainfall intensity and temperature and humidity changes), combined with drainage network topology parameters (the relationship between the number of main and branch pipes), a data foundation covering the entire chain of climate-driven factors, facility responses, and network capacity is formed. This multi-source heterogeneous data fusion processing method effectively solves the problem of the disconnect between climate factors and engineering parameters in traditional planning, providing high-dimensional data support for subsequent assessments of facility regulation effectiveness. Furthermore, by collecting and aggregating multi-dimensional data on climate, network, and ecology from existing land space samples, data support is provided for the subsequent construction of relevant mapping models, significantly enhancing the system resilience and self-regulation capacity of land space in the face of extreme precipitation, temperature fluctuations, and other climate change scenarios. S2. Construct the final infrastructure-pipeline layout mapping model based on the data collected in S1; S2 includes the following steps: S21. Based on the existing climate response index dataset, the existing total land area dataset, the existing structural parameter dataset, the existing infrastructure layout quantity dataset, and the existing infrastructure performance parameter dataset, construct a mapping model with various climate response index data and total land area data as inputs and drainage pipe network structural parameter data, various ecological infrastructure layout quantity and performance parameter data as outputs, to obtain the final infrastructure-pipe network layout mapping model. S21 includes the following steps: S211. Construct an initial infrastructure-pipeline layout mapping model and set a first training data ratio (e.g., 8:2 or 7:3, which can be adjusted adaptively according to the actual training situation); divide the existing climate response index dataset, the existing total land area dataset, the existing structural parameter dataset, the existing infrastructure layout quantity set, and the existing infrastructure performance parameter dataset according to the first training data ratio to obtain the first training dataset and the first test dataset. S212. Set a first training error threshold (10%~15%, which can be adjusted adaptively according to the actual training situation); input the first training dataset into the initial infrastructure-pipeline layout mapping model for training; during the training process, if the training error is less than the first training error threshold, stop training and obtain the trained infrastructure-pipeline layout mapping model; otherwise, continue training until the training error is less than the first training error threshold. S213. Set a first test accuracy threshold (90%~95%, which can be adjusted adaptively according to the actual test situation); input the first test dataset into the trained infrastructure-pipeline layout mapping model for testing; after the test is completed, obtain the first test accuracy data; if the first test accuracy data is greater than or equal to the first test accuracy threshold, use the trained infrastructure-pipeline layout mapping model as the final infrastructure-pipeline layout mapping model; otherwise, return to S212 to continue training the trained infrastructure-pipeline layout mapping model and repeat S213 until the first test accuracy data is greater than or equal to the first test accuracy threshold. The initial infrastructure-pipeline layout mapping model adopts a multi-branch fusion fully connected neural network model. The overall structure of this model uses parallel branches to process different types of input data: climate reflection index data is extracted through an independent fully connected branch, which contains three fully connected layers (128 neurons in the first layer, 64 neurons in the second layer, and 32 neurons in the third layer), with each layer followed by a ReLU activation function (corrected linear unit, used to introduce nonlinear transformation); the total land area data is encoded through a separate two-layer fully connected branch (64 neurons and 32 neurons); the features extracted by each branch are converged in the fusion layer and then enter a shared deep processing network, which consists of four fully connected layers (256, 128, 64, and 32 neurons respectively), and also uses the ReLU activation function to enhance expressive power; the output layer is divided into three parallel sub-networks according to task requirements: drainage pipeline structure parameter prediction branch (containing a hidden layer of 16 neurons and an output layer for the target parameter dimension), ecological infrastructure layout quantity branch (8-neuron hidden layer with quantity prediction output), and performance parameter data branch (12-neuron hidden layer with parameter output). The model can fully capture the complex correlations and interactions between variables through a purely fully connected architecture, achieving an accurate mapping from climate and spatial driving factors to infrastructure layout schemes; By establishing quantitative correlations between climate factors (rainfall, temperature, humidity, etc.) and spatial characteristics (land area) and infrastructure layout (pipeline structure, quantity and performance of ecological facilities), planning and layout no longer rely on single indicators or subjective judgments, but are optimized based on historical data statistical patterns and systematic analysis. By integrating multi-source heterogeneous data from existing spaces, the model can identify optimal pipeline topology parameters (such as the ratio of main and branch pipes) and ecological facility combination schemes (such as the quantity ratio and performance requirements of water tanks, filter wells, etc.) under different climate conditions, thus possessing stronger adaptability and robustness in the face of future climate change. This mapping relationship mining based on machine learning or statistical regression not only considers the impact of individual facility performance parameters on the overall system efficiency, but also reveals the nonlinear coupling mechanism between climate driving factors and infrastructure response through data training, providing quantifiable decision support and precise design guidance for the planning and layout of ecological facilities in the current land space. S3. Set an extreme climate threshold. If the historical data is greater than or equal to the extreme climate threshold, double the climate data according to the redundancy factor, and input the doubled data into the mapping model in S2 for mapping. S3 includes the following steps: S31. Set the initial redundancy multiple and the threshold for the number of extreme climate events (which can be adaptively set according to the proportion of actual extreme climate events considered), and combine historical data to obtain various climate response index data of the current national land space and the number of extreme climate events in history, so as to obtain the current initial climate response index dataset and the current number of extreme climate events. If the current number of extreme weather events is greater than or equal to the threshold number of extreme weather events, the data in the current initial climate response index dataset is doubled according to the initial redundancy factor to obtain the current final climate response index dataset; otherwise, no doubling is performed. For example, a new urban area covers approximately 50 square kilometers. According to historical meteorological data analysis, the average annual rainfall in this area is 800 mm, the maximum daily rainfall is 150 mm, the average annual temperature is 16 degrees Celsius, and the relative humidity remains around 70% year-round. In the past decade, this area has experienced three extreme weather events (such as torrential rain and sustained high temperatures). The threshold for the number of extreme weather events is set at 2, and the initial redundancy factor is 1.5. First, a complete dataset of climate response indicators for the new area was collected, including the daily average rainfall sequence for the past year (e.g., 3.2 mm in January and 12.8 mm in July), the daily average temperature variation curve (up to 38 degrees Celsius and down to -2 degrees Celsius), and the average relative humidity values ​​for each month of the year (range 65%-75%). Since historical data shows that the area has experienced three extreme weather events, exceeding the preset threshold of two extreme weather events, it indicates that the area is highly likely to experience similar extreme weather events in the future.

[0019] Based on this, the system determines that a redundancy amplification mechanism needs to be activated, which involves multiplying all currently collected climate response index data by an initial redundancy factor of 1.5 for enhancement processing. For example, the original maximum daily rainfall of 150 mm becomes 225 mm after processing; similarly, the extreme high temperature of 38 degrees Celsius is adjusted to 57 degrees Celsius; and so on to generate the current final climate response index dataset. S32. Input the current final climate response index dataset and the current land area data into the final infrastructure-pipeline layout mapping model for mapping to obtain the current structural parameter dataset, the current infrastructure layout quantity set and the current infrastructure performance parameter dataset. By introducing a redundancy factor adjustment mechanism and an extreme climate frequency threshold judgment, a dynamic adaptive data preprocessing system was constructed, significantly improving the robustness and foresight of territorial spatial planning in response to extreme climate events. Specifically, firstly, by establishing an intelligent linkage between the frequency of historical extreme climate events and the enhanced processing of current climate data, when the system detects that the number of historical extreme climate events in the target area reaches or exceeds a preset threshold, it automatically initiates a data redundancy amplification program. This program systematically amplifies key climate indicator data, including rainfall intensity, extreme temperature values, and humidity fluctuations, according to the initial redundancy factor. This amplification is not a simple linear multiplication, but rather based on a safety system. The expanded boundary conditions of the data-driven approach enable subsequent mapping models to optimize infrastructure layout under more stringent climate scenarios. This adaptive data augmentation mechanism effectively avoids the problem of insufficient infrastructure defense caused by the limitations of historical data in traditional planning. Especially against the backdrop of climate change exacerbating the frequency of extreme weather events, it ensures that the planning scheme has sufficient safety margins. As a result, the output pipeline structure parameters, ecological facility layout schemes, and performance requirements can automatically adapt to the climate risk levels of different regions, realizing a shift from a passive response to an active defense planning concept, and significantly improving the climate resilience and long-term adaptability of the national spatial infrastructure system. S4. Based on the mapping results in S3, arrange the current ecological infrastructure and drainage network and install manually controlled valves with numbers. Collect valve opening and closing status and climate index data within the period and construct the final connection control valve status mapping model. S4 includes the following steps: S41. Based on the current infrastructure layout quantity set and the current infrastructure performance parameter dataset, the ecological infrastructure of the current national land space is arranged; then, based on the current structural parameter dataset, the drainage pipe network of the current national land space is arranged. During the arrangement process, a manual connection control valve is installed in each main pipe and branch pipe of the drainage pipe network of the current national land space to obtain the current first connection control valve set; each valve in the current first connection control valve set is numbered and set to two states: on and off (e.g., 0 represents off, 1 represents on). S42. Set the current valve switch data acquisition cycle; After the installation of each connected control valve in S41 is completed, divide the current valve switch data acquisition cycle into multiple sub-cycles (the length of the sub-cycle can be adaptively set according to the actual situation, such as taking one day or one hour as a sub-cycle, requiring that the values ​​of each climate response index fluctuate little within the sub-cycle and that the opening and closing of the connected control valves remain unchanged). In each sub-cycle, obtain the average data of various climate response indicators and the corresponding number and opening and closing status of each connected control valve to obtain the historical climate response index dataset, the historical connected control valve number set, and the historical connected control valve status dataset. S43. Based on the historical climate response index dataset, the historical connectivity control valve number set, and the historical connectivity control valve status dataset, construct a mapping model with various climate response index data as input and the numbers and on / off states of each connectivity control valve as output, and obtain the final connectivity control valve status mapping model. S43 includes the following steps: S431. Construct an initial connectivity control valve state mapping model and set a second training data ratio (e.g., 8:2 or 7:3, which can be adjusted adaptively according to the actual training situation); divide the historical climate reflection index dataset, the historical connectivity control valve number set, and the historical connectivity control valve state dataset according to the second training data ratio to obtain the second training dataset and the second test dataset. S432. Set a second training error threshold (10%~15%, which can be adjusted adaptively according to the actual training situation); input the second training dataset into the initial connected control valve state mapping model for training; during the training process, if the training error is less than the second training error threshold, stop training and obtain the trained connected control valve state mapping model; otherwise, continue training until the training error is less than the second training error threshold. S433. Set a second test accuracy threshold (90%~95%, which can be adjusted adaptively according to the actual test situation); input the second test dataset into the trained connected control valve state mapping model for testing; after the test is completed, obtain the second test accuracy data; if the second test accuracy data is greater than or equal to the second test accuracy threshold, use the trained connected control valve state mapping model as the final connected control valve state mapping model; otherwise, return to S432 to continue training the trained connected control valve state mapping model and repeat S433 until the second test accuracy data is greater than or equal to the second test accuracy threshold. The initial connectivity control valve state mapping model adopts a spatiotemporal feature fusion deep neural network model, and the overall model architecture adopts a dual-stream parallel input design; as detailed below. (1) The time series processing branch is specifically for processing the time dimension changes of climate reflection index data. It includes a time convolutional layer (with a kernel size of 3, a stride of 1, and 64 output channels) to extract short-term change patterns of climate indicators. Then, a max pooling layer (with a pooling window size of 2 and a stride of 2) is used for feature dimensionality reduction. Finally, a gated recurrent unit layer (with 128 hidden units) is used to capture long-term temporal dependencies. (2) Spatial feature processing branch: For the spatial topology of pipeline valves, a graph convolutional network architecture is adopted, which includes two graph convolutional layers (the first layer outputs a feature dimension of 64 and the second layer outputs a feature dimension of 32). Each layer is followed by a batch normalization layer and a ReLU activation function (corrected linear unit, used to introduce nonlinear transformation) to enhance the expressive power.

[0020] (3) The features extracted from the two branches above are weighted and integrated in the fusion layer through the attention mechanism. The attention weight dimension is 128, which can adaptively identify the most important climate indicators and time nodes for valve control decisions. The fused features are input into a fully connected processing network, which consists of three fully connected layers (the number of neurons is 256, 128 and 64 respectively). Each layer uses the ReLU activation function. Finally, the opening and closing state of each valve is predicted through the output layer (containing the number of neurons of the valve, the activation function is the Sigmoid function, the output range is 0-1, and it is converted to 0 / 1 state after thresholding). This model is specifically designed to handle complex system control problems with spatiotemporal correlations. It can effectively capture the temporal evolution characteristics of climate indicators and the spatial distribution patterns of pipeline valve states. In addition, the graph convolutional network can better preserve the topological information of the connection relationships between valves, realizing intelligent mapping from multidimensional climate driving factors to precise control strategies for pipeline valves. By constructing a dynamic valve control mapping model, the drainage network system has achieved an intelligent upgrade from passive response to active regulation. Specifically, a precise mapping relationship between climate driving factors and the operational status of key control nodes (connecting control valves) in the network has been established. By installing control valves at each main and branch pipe node and assigning them clear identification numbers and on / off states, a refined control matrix covering the entire network has been formed. This enables the system to dynamically adjust the water flow path and distribution strategy within the network based on real-time climate conditions (such as rainfall intensity, temperature changes, and humidity fluctuations), rather than the traditional fixed flow direction mode. By setting an adaptive valve status acquisition cycle (such as sub-cycles in hours or days) and maintaining valve status stability within each sub-cycle, the synchronization of control strategies with climate condition changes is ensured. The accumulation of historical data and the training of the mapping model enable the system to learn and optimize the optimal valve combination strategy under different climate scenarios, achieving intelligent redistribution of network flow, safe diversion of rainfall exceeding standards, and rapid isolation of local faults, thereby significantly improving the overall drainage system's operational efficiency, risk resistance, and climate adaptability. S5. Collect climate data in real time and input it into the mapping model in S4 to map and adjust the valve status; after repeated execution, count the number of switching times of each valve, and replace the valve with the number of switching times greater than the preset threshold with a remote control valve. S5 includes the following steps: S51. After the current valve switch data acquisition cycle ends, set the climate response index data acquisition interval (which can be adaptively set according to the actual climate conditions) and collect various climate response index data of the current land space in real time based on this to obtain the current real-time climate response index dataset. The current real-time climate response index dataset is input into the final connectivity control valve state mapping model for mapping, to obtain the current real-time connectivity control valve number set and the current real-time connectivity control valve state dataset; S52. Based on the current real-time connectivity control valve number set and the current real-time connectivity control valve status dataset, adjust the status of the connectivity control valves set in the drainage network in the current national land space in real time. S53. Repeat S51 and S52 multiple times (the specific number of repetitions can be adaptively set according to the actual situation) and record the datasets mapped in S52 during each repetition and integrate them to obtain the current first statistical connectivity control valve number set and the current first statistical connectivity control valve status dataset. Set a first switching number threshold (which can be adaptively set according to actual conditions); calculate the number of state switching for each connected control valve based on the current first statistical connected control valve number set and the current first statistical connected control valve status dataset to obtain the current first statistical status switching number set; S54. Replace the connection control valves corresponding to the data in the current first statistical state switching count set that are greater than or equal to the first switching count threshold with connection control valves controlled by remote signals to obtain the current second connection control valve set; By constructing a dynamic valve status monitoring and optimization mechanism, the drainage network control system has achieved an intelligent evolution from passive response to proactive optimization. Specifically, by establishing a closed-loop feedback system for real-time climate data acquisition and dynamic valve status adjustment, and by setting adaptive data acquisition intervals, the system can promptly capture subtle changes in climate conditions and quickly translate these changes into specific valve control operations, thereby achieving real-time optimized configuration of water flow paths within the network. This not only improves the system's response speed to sudden extreme weather events but also accumulates rich operational data through repeated mapping and adjustment processes, providing a solid foundation for subsequent statistical analysis and equipment optimization. Secondly... By statistically analyzing the valve state switching frequency, the system can identify control nodes that operate frequently. These nodes are often located at critical points in the system's operation, thus providing accurate decision-making basis for subsequent equipment upgrades. Upgrading high-frequency switching valves to remote signal control valves not only improves control accuracy and response speed but also enhances the system's maintainability and remote management capabilities. This represents a leap from basic manual control to intelligent and networked management, significantly improving the overall operational efficiency, energy efficiency, and long-term reliability of the drainage network system. Furthermore, by selecting only high-frequency switching control valves for replacement, equipment costs are minimized while still meeting drainage requirements. S6. After the valve replacement in S5 is completed, repeat the valve status adjustment process in S5 and count the number of control valve switching times again. When the number of switching times reaches the preset condition, increase the redundancy multiple in S3. After increasing, expand the infrastructure configuration and repeat the statistical process in S4, S5 and S6 until the number of switching times does not reach the preset condition. Please see Figure 5 , Figure 6 S6 includes the following steps: S61. Set the threshold for the number of control valve switching and the second switching number threshold (which can be adaptively set according to the actual situation, and this value is much larger than the first switching number threshold). Based on the current second connected control valve set, repeat S51 and S52 multiple times (the specific number of repetitions can be adaptively set according to the actual situation) and record the dataset mapped in S52 during each repetition and integrate them to obtain the current second statistical connected control valve number set and the current second statistical connected control valve status dataset. Based on the current second statistical connection control valve number set and the current second statistical connection control valve status dataset, the number of state switching times for each connection control valve is calculated again to obtain the current second statistical state switching count set. S62. If the current second statistical state switching count set contains data greater than or equal to the second switching count threshold and the corresponding number of data is greater than or equal to the control valve switching count threshold, increase the initial redundancy factor and repeat S31 and S32 to obtain the current expanded structural parameter dataset, the current expanded infrastructure layout set, and the current infrastructure performance parameter dataset; otherwise, it is not necessary to increase the initial redundancy factor. Based on the current expanded structural parameter dataset, the current expanded infrastructure layout quantity set, and the current infrastructure performance parameter dataset, the drainage network and ecological infrastructure of the current national land space are expanded or replaced; after expansion or replacement, S41, S42, S43, S51, S52, S53, S54, and S61 are repeated until the current second statistical state switching count set contains data greater than or equal to the second switching count threshold and the corresponding number of data is less than the control valve switching count threshold, or the current second statistical state switching count set does not contain data greater than or equal to the second switching count threshold; By constructing a multi-level adaptive optimization loop mechanism, the drainage pipe network system has achieved an intelligent upgrade from static design to dynamic evolution. Specifically, by establishing a self-learning feedback optimization system based on valve switching frequency and setting a dual threshold mechanism (controlling the threshold for the number of valve switching and the threshold for the number of switching times), bottleneck nodes and performance defects in system operation can be accurately identified. When multiple valves are detected to be switching at high frequency, the system automatically triggers a dynamic adjustment mechanism for redundancy multiples. By expanding the initial climate data, the infrastructure layout configuration is re-optimized, thereby reducing the pressure on each valve and pipeline and extending the average service life of each valve and pipeline. This avoids the limitations of one-time static design in traditional planning, enabling the system to continuously improve itself based on actual operating performance, ensuring that the infrastructure configuration is always highly matched with dynamic climate conditions and operational requirements. Through multiple rounds of repeated execution and statistical analysis, the system can not only identify weak links that need upgrading, but also improve the overall system's carrying capacity and adaptability through scalable modifications.

[0021] Example 2 This embodiment discloses a climate-adaptive territorial spatial ecological infrastructure planning and layout system. The system can implement the methods of the above embodiments, including a data acquisition module, a layout mapping model construction module, a doubling and mapping module, a state mapping model construction module, a control valve replacement module, and a multiplier adjustment module. The data acquisition module is used to collect existing data on infrastructure, area, and historical climate in the national territory. The layout mapping model building module is used to build the final infrastructure-pipeline layout mapping model; The doubling and mapping module is used to double climate data; The state mapping model building module is used to build the final connected control valve state mapping model; The control valve replacement module is used to adjust or replace the valve status; The redundancy adjustment module is used to adjust the current redundancy multiple and expand the infrastructure configuration after adjustment.

[0022] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0023] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present invention.

Claims

1. A method for planning and laying out climate-adaptive national spatial ecological infrastructure, characterized in that, Includes the following steps: S1. Set the types of ecological infrastructure and its performance parameters, climate response indicators and drainage network structure parameters, and collect existing infrastructure, area and climate history data in the national land space. S2. Construct the final infrastructure-pipeline layout mapping model based on the data collected in S1; S3. Set an extreme climate threshold. If the historical data is greater than or equal to the extreme climate threshold, double the climate data according to the redundancy factor, and input the doubled data into the mapping model in S2 for mapping. S4. Based on the mapping results in S3, arrange the current ecological infrastructure and drainage network and install manually controlled valves with numbers. Collect valve opening and closing status and climate index data within the period and construct the final connection control valve status mapping model. S5. Collect climate data in real time, input it into the mapping model in S4 for mapping, and adjust the valve status; after repeated execution, count the number of switching times of each valve, and replace the valve with the number of switching times greater than the preset threshold with the remote control valve. S6. After the valve replacement in S5 is completed, repeat the valve status adjustment process in S5 and count the number of control valve switching times again. When the number of switching times reaches the preset condition, increase the redundancy multiple in S3. After increasing, expand the infrastructure configuration and repeat the statistical process in S4, S5 and S6 until the number of switching times no longer reaches the preset condition.

2. The method for planning and layout of climate-adaptive territorial spatial ecological infrastructure according to claim 1, characterized in that: The structural parameter types include the number of main pipes and the total number of branch pipes between adjacent main pipes.

3. The method for planning and layout of climate-adaptive territorial spatial ecological infrastructure according to claim 2, characterized in that: The final infrastructure-pipeline layout mapping model described in S2 takes various climate response index data and total land area data as inputs and outputs drainage pipeline structure parameter data, the number of various ecological infrastructures and their performance parameters as outputs.

4. The method for planning and layout of climate-adaptive territorial spatial ecological infrastructure according to claim 3, characterized in that, S3 includes the following steps: S31. Set the initial redundancy multiple and the threshold for the number of extreme weather events, and obtain data on various climate response indicators of the current national land space and the number of extreme weather events in history; If the current number of extreme weather events is greater than or equal to the threshold for the number of extreme weather events, the data in the current initial climate response index dataset will be doubled according to the initial redundancy factor; otherwise, no doubling will be performed. S32. Input the doubled data and the current land area data into the final infrastructure-pipeline layout mapping model for mapping.

5. The method for planning and layout of climate-adaptive national spatial ecological infrastructure according to claim 4, characterized in that, S4 includes the following steps: S41. Based on the mapping results of S32, arrange the ecological infrastructure of the current land space, and then arrange the drainage network of the current land space. During the arrangement process, install manual connection control valves in each main pipe and branch pipe of the drainage network of the current land space, and number each valve and set it to have two states: open and closed. S42. Divide the current valve switch data acquisition cycle into multiple sub-cycles. In each sub-cycle, acquire the average data of various climate response indicators and the corresponding number and switch status of each connected control valve.

6. The method for planning and layout of climate-adaptive territorial spatial ecological infrastructure according to claim 5, characterized in that: The input to the final connectivity control valve state mapping model described in S4 is various climate response index data, and the output is the number and on / off status of each connectivity control valve.

7. The method for planning and layout of climate-adaptive territorial spatial ecological infrastructure according to claim 6, characterized in that, S5 includes the following steps: S51. Collect various climate response index data of the current national land space in real time and input them into the final connection control valve state mapping model for mapping; S52. Based on the mapping results in S51, the status of the connection control valves set in the drainage network in the current national land space is adjusted in real time.

8. The method for planning and layout of climate-adaptive national spatial ecological infrastructure according to claim 7, characterized in that, The S5 also includes: S53. Repeat S51 and S52 multiple times and record the dataset obtained from the mapping in S52 during each repetition and integrate it. Then set the first switching threshold and calculate the number of state switching for each connected control valve based on the integration results; S54. Replace the state switching count corresponding to the state switching count that is greater than or equal to the first switching count threshold with the remote signal controlled state switching valve to obtain the current second state switching valve set.

9. The method for planning and layout of climate-adaptive national spatial ecological infrastructure according to claim 8, characterized in that, S6 includes the following steps: S61. Set the threshold for the number of control valve switching and the second switching count threshold; Based on the current second connected control valve set, repeat S51 and S52 multiple times, record the dataset mapped in S52 during each repetition, and integrate them to obtain the current second statistical connected control valve number set and the current second statistical connected control valve status dataset. Based on the current second statistical connection control valve number set and the current second statistical connection control valve status dataset, the number of state switching times for each connection control valve is calculated again to obtain the current second statistical state switching count set. S62. If the current second statistical state switching count set contains data greater than or equal to the second switching count threshold and the corresponding number of data is greater than or equal to the control valve switching count threshold, increase the initial redundancy factor and repeat S31 and S32 to obtain the current expanded structural parameter dataset, the current expanded infrastructure layout set, and the current infrastructure performance parameter dataset; otherwise, it is not necessary to increase the initial redundancy factor. Based on the current expanded structural parameter dataset, the current expanded infrastructure layout quantity set, and the current infrastructure performance parameter dataset, the drainage pipe network and ecological infrastructure of the current land space are expanded or replaced. After expansion or replacement, S41, S42, S51, S52, S53, S54, and S61 are repeated until there is data in the current second statistical state switching count set that is greater than or equal to the second switching count threshold, and the corresponding number of data is less than the control valve switching count threshold, or there is no data in the current second statistical state switching count set that is greater than or equal to the second switching count threshold.

10. A system for implementing the climate-adaptive land space ecological infrastructure planning and layout method as described in any one of claims 1-9, characterized in that: It includes a data acquisition module, a layout mapping model construction module, a doubling and mapping module, a state mapping model construction module, a control valve replacement module, and a multiplier adjustment module; The data acquisition module is used to collect existing data on infrastructure, area, and historical climate in the national territory. The layout mapping model building module is used to build the final infrastructure-pipeline layout mapping model; The doubling and mapping module is used to double climate data; The state mapping model building module is used to build the final connected control valve state mapping model; The control valve replacement module is used to adjust or replace the valve status; The redundancy adjustment module is used to adjust the current redundancy multiple and expand the infrastructure configuration after adjustment.

Images