47 results about "Urban surface" patented technology

The invention relates to the technical field of three-dimensional reconstruction, in particular to a multi-mode remote sensing data driven refined city three-dimensional reconstruction method and system, and the method comprises the steps: obtaining an original satellite optical image for providing city surface information; synthetic aperture radar (SAR) data is obtained and used for assisting reconstruction of a point cloud data missing region; the method comprises the following steps: acquiring laser radar data carried by a flight aerial carrier for acquiring high-precision three-dimensional point cloud; performing data preprocessing; carrying out fusion on the preprocessed multi-modal data; on the basis of the fused features, complementing space detail information; on the basis of the refined features, progressive reconstruction is carried out, vertexes and edges are gradually added from the initial vertexes, and a grid model is constructed; in the reconstruction process, performing semantic segmentation on the grid model by using a multi-category segmentation network, and judging the category of each triangular patch; time sequence reconstruction is completed through fusion of multi-temporal data, and a dynamic city change model is generated; and complementation of advantages of different modal data is realized.

The invention provides a high-temporal-spatial-resolution surface temperature reconstruction system for urban thermal environment refined monitoring, and relates to the field of electric digital data processing. Comprising a multi-source heterogeneous data intelligent acquisition and preprocessing module, an urban thermal environment multi-dimensional feature knowledge modeling module, a physical constraint deep learning surface temperature reconstruction module and an intelligent monitoring early warning and decision support module. The multi-source heterogeneous data intelligent acquisition and preprocessing module is responsible for collecting and preprocessing various remote sensing and ground observation data, and the urban thermal environment multi-dimensional feature knowledge modeling module constructs a knowledge system of an urban underlying surface, a three-dimensional form and a thermal process. The physical constraint deep learning surface temperature reconstruction module is used for realizing accurate reconstruction of high temporal-spatial resolution surface temperature, and the intelligent monitoring early warning and decision support module converts a reconstruction result into visual display, risk early warning and regulation and control decision suggestions; according to the system, high-precision, physically consistent and interpretable urban surface temperature reconstruction can be realized.

The invention discloses an urban blue-green space microclimate prediction system and method based on AI fusion. The method comprises the following steps of: 1, acquiring field microclimate measured data through linkage of a portable weather station and a GPS (Global Positioning System); 2, utilizing a machine learning downscaling algorithm and a deep learning semantic segmentation technology to extract high-resolution land surface temperature and urban land surface coverage classification data from the remote sensing image; 3, constructing a time-space aligned multi-modal GIS data set, and constructing a high-precision microclimate prediction model by using an ensemble learning algorithm; and 4, introducing an SHAP interpretability framework, carrying out deep analysis on the model, and quantifying the contribution degree of various environmental elements to a microclimate prediction result and the complex nonlinear influence of the contribution degree. According to the method, unprecedented high-precision and explainable scientific decision support can be provided for formulating urban planning, landscape design and thermal environment mitigation strategies, and development of healthy, sustainable and climate-flexible cities is powerfully promoted.

The embodiment of the invention discloses an urban surface feature three-dimensional model simplification processing method, system and device and a storage medium, and realizes efficient simplification of urban surface features and accurate reservation of structural information. Aiming at the problems of key feature loss, low semantic segmentation precision, easy model structure deformation and the like caused by a unified simplification strategy in a traditional method, a semantic segmentation technology based on deep learning is proposed, and a city scene is segmented into categories of buildings, vegetation and the like in combination with multi-feature fusion (geometry, color and topology) and a graph convolutional network, so that the segmentation accuracy is remarkably improved; a personalized simplification strategy is adopted, the edge collapse sequence of the building is restrained through an improved QEM algorithm, the simplification rate reaches 90% or above, a facade structure is reserved, the vegetation simplification rate exceeds 76%, and the overall form is maintained; and in combination with grid filtering and region growth optimization, noise is effectively eliminated, and the boundary is smoothed.

The invention provides an urban inland inundation risk analysis method and device and electronic equipment, and belongs to the technical field of data processing, and the method comprises the steps: building an urban surface inundation simulation model, and obtaining an urban inland inundation ponding map; performing superposition analysis on the facility distribution diagram, the population distribution diagram and the waterlogging ponding diagram to obtain a ponding risk value, a plurality of sub-facility influence values, a plurality of sub-population influence values and a plurality of sub-economic loss values of each grid unit; determining a waterlogging risk grade value of any grid unit based on a weighted summation result of the plurality of sub-element values; the first weight of the plurality of child element values is predetermined based on the importance degree of the child element relative to the parent element; and determining a waterlogging risk grade map of the city based on the waterlogging risk grade values of all the grid units. According to the method, the self influence and extension influence caused by waterlogging and ponding events in the city can be comprehensively considered, the waterlogging risk grade map of the city can be determined more scientifically and reasonably, and the region seriously influenced by waterlogging in the city can be accurately identified.

The embodiment of the invention provides a city change monitoring analysis early warning method and system based on remote sensing ground feature data. The method is applied to the technical field of remote-sensing image change monitoring. The method comprises the steps of obtaining front and back time sequence images of urban ground features; inputting the front and back time sequence images of the urban ground features into a pre-trained urban ground feature change monitoring model to obtain an urban ground feature change result; wherein the urban surface feature change monitoring model is constructed based on a cGAN network model, and comprises a generator and a discriminator; the urban surface feature change monitoring model is trained through the following steps: acquiring front and back time sequence images of urban surface features; marking the change areas of the time sequence images before and after the urban surface features to obtain corresponding change label maps, and taking the time sequence images before and after the urban surface features and the corresponding change label maps as training samples; and alternately training a generator and a discriminator by using the training sample to obtain an urban ground feature change monitoring model. Therefore, monitoring and early warning of urban ground feature changes are realized.

The invention provides an urban surface heat island intensity evaluation method, which comprises the following steps of: acquiring a satellite multi-band data image of a target region in a research period, dividing a water body and an urban built-up region on the basis, and selecting part of the water body as a reference station region; extracting seasonal and tendency factors according to the long-term observed surface temperature data of the reference base station area, correcting the surface temperature data of the reference base station area to obtain corrected temperature, and comparing the corrected temperature with the surface temperature of the urban built-up area to obtain the surface heat island intensity of the urban built-up area. Therefore, the fluctuation trend of seasons to the temperature of the reference station area is quantified, the spatial distribution of the urban thermal environment and the thermal risk is clearer and more visual and is convenient to position, and evaluation errors caused by seasons and background climate changes can be reduced.

The application provides a method for determining inflow hydrograph of urban stormwater inlet, which is in line with actual urban runoff conditions and can effectively reduce the error of calculation results. The urban area is divided into multiple sub-regions according to the road network, and the net rainfall is discharged from the stormwater inlet, and the single stormwater inlet in the sub-region is calculated respectively; the urban surface runoff is calculated by using the comprehensive runoff coefficient method, and the runoff coefficient not greater than 1 is used to represent the runoff after the rainfall is intercepted and lost on the ground; for the rainfall in the small urban area, the ground water flow is in the form of slope flow and shallow concentrated flow; the catchment time is the sum of the two, the slope flow with a flow line not greater than 90m is calculated by using the Manning dynamics method to calculate the surface runoff flow time; after the slope flow stops flowing for 90m, the shallow concentrated flow with a water depth greater than 3cm appears at this time, and the stormwater inlet design flow inflow calculation formula is: Q = F * (P - S) / (T + 90) wherein Q is the stormwater inlet inflow, L / min; F is the average catchment area controlled by each stormwater inlet, m 2 .

The invention discloses a method for regulating and controlling a thermal environment by an urban form under coupling of human eyes and a bird's-eye view angle. The method comprises the following steps of: inverting a surface temperature based on a radiation transfer equation method and a Landsat-8 remote sensing image; carrying out fine extraction on urban ground feature information fused with multi-modal data; constructing a three-dimensional comprehensive representation system of the urban form under the coupling of a bird's-eye view angle and a human eye view angle; establishing an urban surface temperature prediction model fusing an urban two-dimensional form, an urban three-dimensional form in a bird's-eye view angle and an urban three-dimensional form in a human eye view angle under different spatial scales; and an optimal configuration method for regulating and controlling the surface thermal environment by the urban form under the fine scale and the rough scale is explored. According to the method, a scientific basis can be provided for quantitative regulation and control and space planning optimization of the urban thermal environment, and the effects of refined cooling and thermal environment improvement under urban space structure optimization and greening configuration adjustment are achieved.

The application provides a city surface area classification method and related equipment. The city surface area classification method comprises: obtaining a first target parameter of a to-be-determined city surface area, the first target parameter comprising a characteristic building height, an average building height, a building height standard deviation, a building coverage rate, an impervious surface ratio, a characteristic vegetation canopy height, an average vegetation canopy height, and a vegetation coverage rate of the to-be-determined city surface area; inputting an electronic map corresponding to the to-be-determined city surface area and the first target parameter into a city surface area classification model to obtain a city surface area type corresponding to the to-be-determined city surface area output by the city surface area classification model, the city surface area type being used for analysis or simulation of heat waves, air quality, and extreme weather of the to-be-determined city surface area. In the application, the fineness and determination accuracy of the city surface area type are improved.

The invention discloses a city layout optimization simulation method, system and device for relieving a city heat island effect, and the method comprises the steps: S100: carrying out the grid division of a target city region, adding the city surface temperature data and city data to corresponding grid points, and obtaining a grid city model; s200, extracting average city surface temperature data and influence factor data of each grid point in the grid city model, and respectively constructing a surface temperature prediction model of each grid point by adopting a geographically weighted regression model; and S300, taking the average urban surface temperature data and the influence factor data of each grid point as a state space, taking each influence factor and the action type as an action space, performing reinforcement learning, and simulating an optimization scheme of the urban layout. According to the method, the optimal city layout simulation scheme capable of keeping city functions, controlling optimization cost and relieving a heat island effect can be automatically learned, so that scientific guidance is provided for city layout optimization.

This invention discloses a DEM data correction method that takes into account the characteristics of surface runoff routes, belonging to the field of digital elevation model construction technology. It solves the problem that in some scenarios, region-based DEMs can no longer accurately simulate the surface runoff process, thus preventing DEMs from playing their due role in urban surface runoff simulation. The key technical points are that the method includes the following steps: S1, data preparation: acquiring DEM data of the analysis area and marking the outlet and boundary positions in the DEM raster; S2, marking the flow direction of the raster cell at the outlet location as 0, indicating that the water flow cell of that raster does not flow to other raster cells; S3, finding the raster cells adjacent to the outlet cell and calculating the flow direction of each raster cell according to the principle of maximizing elevation difference. The effect is that this invention covers the key technology of raster elevation value correction based on surface flow direction characteristics, which can improve the application value of DEM data in the field of hydrological analysis.

The invention discloses a gate pump real-time control method for regulating and controlling urban flood. The method comprises the following steps: S1, collecting urban river data; s2, constructing an urban hydrological model, and simulating an urban rainfall-runoff forming process according to detailed space division and different surface runoff characteristics; s3, constructing a river network hydrodynamic model, and simulating a river network system by considering hydraulic conditions of pump stations, gates, weir flows and reservoir and lake facilities; s4, the hydrological model describing the urban surface runoff and confluence process and the hydrodynamic model describing the water flow evolution process in the urban river network are coupled through the section node water exchange process to construct a hydrological and hydrodynamic coupling model; s5, compiling a water engineering real-time control rule based on the warning water level and ecological water level data of the river channel; s6, inputting the real-time control rule of the water engineering into the hydrological and hydrodynamic coupling model, evaluating the performance of the method through a rainstorm event, and quantitatively analyzing the response of flood to the real-time control of the water engineering; according to the invention, accurate regulation and control of the river network and effective relief of flood are realized.

The invention provides an urban surface and underground space flood simulation method based on a hydrodynamic model, and belongs to the technical field of urban flood disaster prevention and control and hydrological hydraulic engineering. The method comprises the steps of urban surface and underground space generalization processing, model element coupling association establishment, model element algorithm setting and model result calibration verification. The model established by the method has high-performance and high-precision computing power, can efficiently and accurately simulate the flowing form of flood in the urban complex underground space, and provides support for urban flood early warning.

This invention relates to a method for predicting urban surface temperature by combining LSTM and geographic information, belonging to the field of spatiotemporal modeling technology for urban surface temperature. It includes the following steps: S1: Acquire temporal LST and geospatial feature data to construct a spatiotemporal sequence input; S2: Based on geospatial features, generate the initial hidden state and cell state of a Long Short-Term Memory (LSTM) network through linear mapping; S3: Introduce spatial weights based on spatial distance to spatially weight and adjust the hidden state of the LSTM, modeling spatial heterogeneity; S4: Employ a spatial cross-attention mechanism to model the correlation between geographic location information and the hidden state, fuse spatial information, and output the prediction result. By sequentially introducing the above mechanisms, this invention achieves collaborative modeling of the temporal dependence and spatial non-stationarity of surface temperature without interfering with the LSTM temporal modeling process, significantly improving prediction accuracy and stability, especially in complex urban environments and cross-regional applications.

The present invention provides a method, device and electronic device for analyzing urban waterlogging risk, belonging to the field of data processing technology, the method comprising: establishing an urban surface flooding simulation model to obtain a waterlogging map of the city; performing overlay analysis on a facility distribution map, a population distribution map and a waterlogging map to obtain a waterlogging risk value, several sub-facility impact values, several sub-population impact values ​​and several sub-economic loss values ​​of each grid unit; determining a waterlogging risk level value of any grid unit based on a result of weighted summation of multiple sub-element values; the first weight of multiple sub-element values ​​is predetermined based on the importance of the sub-element relative to the parent element; determining a waterlogging risk level map of the city based on the waterlogging risk level values ​​of all grid units. The present invention can comprehensively consider the inherent impact and extended impact of waterlogging events occurring in the city, more scientifically and reasonably determine a waterlogging risk level map of the city, and accurately identify areas in the city that are severely affected by waterlogging.

The invention discloses a high-resolution city high-temperature monitoring method coupled with a city climate model and deep learning, and belongs to the field of high-temperature monitoring and early warning. Aiming at the problems of low spatial resolution, insufficient utilization of multi-source information, untight fusion of a physical mechanism and deep learning and the like in the prior art, multi-source information such as high-resolution remote sensing images, ground meteorological observation, urban surface attributes and the like is combined, and urban climate physical modeling and deep learning algorithms are creatively integrated; and high-precision inversion and dynamic monitoring of the urban high-temperature spatial pattern are realized. According to the method, comprehensiveness, timeliness and scientificity of data can be considered, the monitoring precision and prediction capability of urban high temperature distribution are effectively improved, and powerful data support is provided for early warning, risk assessment and scientific management of urban high temperature disasters.

The invention relates to a system for the planted retention of rainwater (1) in an area of a sealed urban surface (2) or a road surface with pipeline infrastructure (3) running underground, comprising: - a root-resistant and water-resistant trough (4) which extends at least partially or completely below the level of the sealed surface (2), - a structure substrate (5) arranged in the trough (4), which structure substrate has intermediate spaces or pores and capillary properties for storing water and is optionally covered from above by means of a cover layer (6), - a shaft arrangement (7) having a water inflow (8), a water feed (9) and at least one water outflow (10), - wherein the water inflow (8), for receiving the rainwater (1) drained from the sealed surface (2), is connected to a collector (11) for the rainwater (1), - wherein the shaft arrangement (7) conducts the received rainwater (1) via the water feed (9) into the trough (4) optionally until a particular fill level (12) is reached or drains excess or contaminated rainwater (1) via the water outflow (10) into a channel (13), - wherein a plant tray (14) protruding upwards above the trough (4), for receiving a tree substrate (15) and a tree-root ball (16) embedded in the tree substrate (15), is provided, - and wherein a fastening device (17), for anchoring the tree-root ball (16) and the plant tray (14) in the region of the trough (4), is provided.

The invention relates to an experimental device and an experimental method for urban surface-underground space flood simulation, the experimental device comprises an underground space model, a surface model and a rainfall simulation device, and the underground space model is internally provided with a plurality of underground building models; the ground surface model is located above the underground space model and comprises a ground model and a channel model, a river channel model, a pipe network model and a ground facility model which are located on the ground model, and the channel model is communicated with the ground model and the underground building model; the rainfall simulation device is configured to spray water drops to the earth surface model and simulate extreme rainfall. When the experimental device is in a working state, the rainfall simulation device simulates extreme rainfall to the earth surface model, the pipe network model collects and discharges the rainfall to the river channel model, and the river channel model discharges water; after the drainage capacity of the pipe network model and the river channel model reaches a threshold value, the ground model and the ground facility model cooperatively simulate the evolution process of waterlogging on the ground surface, and after waterlogging accumulation is higher than a preset value, the waterlogging enters the underground building model from the channel model.

The application discloses a kind of high-resolution urban high temperature monitoring methods coupled with urban climate model and deep learning, belong to high temperature monitoring and early warning field.Aiming at the problems such as low spatial resolution of prior art, insufficient use of multi-source information and not close fusion of physical mechanism and deep learning, combined with high-resolution remote sensing image, ground meteorological observation and urban surface attribute and other multi-source information, innovatively integrate urban climate physical modeling and deep learning algorithm, realize the high-precision inversion and dynamic monitoring of urban high temperature spatial pattern.The application can consider comprehensiveness, timeliness and scientificity of data, effectively improve the monitoring precision and prediction ability of urban high temperature distribution, and provide strong data support for urban high temperature disaster warning, risk assessment and scientific management.

The present application discloses a method and device for analyzing factors affecting urban surface temperature, a storage medium, and a computer device. The method comprises: performing surface temperature inversion calculation on Landsat‑8 remote sensing image data to determine surface temperature information; performing regional segmentation on a target research city according to airborne laser radar point cloud data and aerial image data, identifying the land use type of each area, and obtaining a land use classification distribution map; extracting a building height model for land use classified as a building and a canopy height model for land use classified as a forest, and assigning the building height model and the canopy height model to the land use classification distribution map; performing block division on the target research city according to aerial image data and OSM data, extracting POI features, two-dimensional morphological features, and three-dimensional morphological features of each block, and identifying the functional area type of each block; and for each functional area type, identifying the factors affecting surface temperature in the two-dimensional morphological features and the three-dimensional morphological features.

The invention discloses a surface temperature inversion method and system based on an urban complex geometric structure, and the method comprises the steps: obtaining a thermal infrared remote sensing image, an atmosphere contour line, WVC, DSM, land utilization data, and a spectrum library of a certain city; the thermal infrared reflection wave band data, the atmospheric profile bottom layer temperature, the atmospheric parameters, the sky visual factor and the urban surface material emissivity are obtained by preprocessing the thermal infrared reflection wave band data, the atmospheric profile bottom layer temperature, the atmospheric parameters and the urban surface material emissivity; introducing a sky visual factor to quantify an urban geometric structure, and providing an urban pixel thermal radiation model; calculating a surface temperature data set, an effective emissivity average value data set, an effective emissivity difference value data set and an on-satellite brightness temperature data set, constructing a simulation data set together with a sky visual factor, and dividing the simulation data set into a training data set, a test data set and a verification data set; fitting a local regression coefficient of the GWRSW model by using the training data set and the test data set; and inputting the verification data set into the GWRSW model to estimate the surface temperature of the urban pixel. According to the method, the land surface temperature inversion precision in a complex urban environment is effectively improved.

The invention discloses an urban surface heat storage estimation method based on a stationary satellite, and the method comprises the following steps: constructing a data set based on various satellite remote sensing data; estimating urban surface thermal inertia based on the data set in combination with a surface temperature change rule; based on the hourly surface temperature and the estimated surface thermal inertia, hourly urban scale surface thermal storage is obtained. According to the urban surface heat storage estimation method based on the stationary satellite, hour-by-hour large-scale urban area surface heat storage can be obtained, and the defects that the ground observation range is limited, and the numerical simulation error is large are overcome.

The invention belongs to the technical field of mountainous city heat island effect, and discloses a mountainous city heat island surface space-time evolution analysis method based on a local climate region, comprising the following steps: S1, data acquisition; s2, LCZ partition grid scale selection is carried out; s3, LCZ parameter selection is carried out; s3, LCZ classification is carried out; s4, LCZ internal type conversion is carried out; s5, inverting the surface temperature and calculating the heat island intensity; s6, analyzing the surface spatial form and space-time evolution characteristics; based on a local climate region theory, the mountain city surface heat island intensity and LCZ space-time evolution are analyzed and studied by utilizing remote sensing and geographic information system combined mapping and surface temperature inversion, so that the dynamic balance between urban sustainable development and ecological safety is maintained while the mountain city heat island effect is relieved, and the economic benefit is improved. And powerful support is provided for adaptation and mitigation measure planning of climatic changes in cities.

The application discloses an environment-friendly emission auxiliary system and implementation method for urban surface drilling, which comprises a collecting head and a grading bin, the collecting head is used for collecting the mixture of sludge and water discharged by an orifice anchoring pipe and introducing the mixture into the grading bin; wherein the grading bin comprises a main bin, a flow guide plate one, a flow guide plate two and an overflow brush plate; the front end side wall of the main bin is connected with the collecting head; the flow guide plate one and the flow guide plate two are vertically inserted into the main bin near the front end and the rear end, and the lower ends are not in contact with the bottom plate of the main bin; the overflow brush plate is vertically inserted into the main bin and is located between the flow guide plate one and the flow guide plate two, and the lower end is tightly attached to the bottom of the grading bin; the flow guide plate one, the flow guide plate two and the overflow brush plate divide the main bin into three spaces connected with each other from front to back, so that the water flow forms an S-shaped flow path. By using the auxiliary system, the mixture of sludge and water discharged by drilling is collected, and the sludge and water are quickly separated through two-stage filtration and two-stage sedimentation.

The invention discloses an urban surface deformation analysis method based on multi-scale blind source decomposition. The method specifically comprises the following steps: S1, obtaining a time sequence surface deformation field and various deformation inducement data; s2, performing spatial multi-scale decomposition on the time sequence earth surface deformation field, and separating the time sequence earth surface deformation field into a large-scale deformation component and a small-scale deformation component; s3, performing preliminary correlation analysis on the large-scale deformation component and the first type of deformation incentive data; s4, performing blind source separation on the large-scale deformation component confirmed by the preliminary correlation analysis, and decoupling the large-scale deformation component into a plurality of statistical independent deformation source signals; s5, performing deep correlation analysis on each decoupled deformation source signal and the corresponding first type of deformation inducement data; s6, performing association analysis on the small-scale deformation component and the second type of deformation inducement data; and S7, comprehensively analyzing the driving mechanism of the ground surface deformation of the research area. According to the method, the multi-source and multi-scale superposition earth surface deformation signals can be effectively decoupled, and the scale dependence driving mechanism of the signals is disclosed.

The present disclosure provides a method for analyzing urban thermal radiation based on sky view factor, including: operation S10, calculating the urban surface emissivity based on different building components; operation S20, performing atmospheric correction on the in-pupil radiance and obtaining the atmospheric effect parameters; operation S30, obtaining the sky view factor of the urban area of different building components based on the solved DSM data; operation S40, pre-constructing an urban thermal radiation analysis model based on the sky view factor, taking the urban surface temperature, urban surface emissivity, urban sky view factor, and atmospheric effect parameters as input parameters, and calculating the satellite in-pupil urban radiance. It also provides an urban thermal radiation analysis model for executing the above urban thermal radiation analysis method, which is applicable to the analysis and correction of urban area thermal radiation of satellite or airborne remote sensing data.

The invention discloses an estimation method for predicting urban surface temperature based on urban green land information acquired by remote sensing. The method is characterized by comprising the following steps: acquiring remote sensing image data of a target city; preprocessing the remote sensing image data, constructing a label data set, calculating the surface temperature of the target city, and extracting the built-up area range of the target city; urban green land is extracted in the built-up area range; calculating a vegetation index and a landscape index based on the urban green land distribution range; the vegetation index and the landscape index serve as independent variables, the surface temperature serves as a dependent variable, an optimal independent variable is obtained through screening, three machine learning models are constructed through the optimal independent variable to serve as prediction models, and the prediction precision of the three prediction models is compared to obtain an optimal prediction model; the method has the advantages that the surface temperature is reflected quantitatively through the urban green land information, a basis for green land planning is provided for livable environment construction of a city, and the stability of a prediction model is kept.

The invention discloses an urban surface runoff pollution cascade ecological interception and purification system and an application method thereof, and relates to the technical field of ecological slope protection and rainwater management. An included angle exists between the bottom of a buffer module and the horizontal plane, and a first side wall and a second side wall are oppositely arranged and located on the two sides of a bottom water guide element correspondingly; in the direction from the first side wall to the second side wall, the height of the bottom water guide element is gradually reduced, the upper portion of the bottom water guide element is a water permeable layer capable of permeating rainwater, the permeated water enters the bottom water guide element, and the multi-stage filter layer in the bottom water guide element can treat the water entering the bottom water guide element. The multiple buffer modules are sequentially arranged in the first direction, the first direction is parallel to the first side wall, the adjacent bottom water guiding elements are communicated, in the first direction, the heights of the multiple bottom water guiding elements are gradually reduced, and the bottom water guiding element located at the lowest end is communicated with a rainwater collecting module. Construction is convenient, the rainwater retention time can be prolonged, and the rainwater purification efficiency is improved.

This invention relates to the field of intelligent computing technology for urban hydrology and hydrodynamics, and discloses a method for coupled modeling of urban flooding surface and drainage pipe network based on a surrogate model. The method first constructs a surface-pipe network coupled hydrodynamic numerical model based on topographic data, drainage pipe network structure data, and rainfall input, generating training data such as node head, pipe segment flow, and surface water depth. Based on this, a surrogate model for the underground pipe network and a surrogate model for the surface are constructed respectively, achieving efficient prediction of the pipe network hydrodynamic state and surface water depth distribution. Furthermore, a feature modulation coupling mechanism driven by the pipe network state is proposed. By establishing a spatial mapping relationship between pipe network nodes and surface grids, the pipe network hydrodynamic state is transformed into rasterized features, and modulation parameters are generated to linearly modulate the intermediate features of the surface model. This achieves implicit coupled modeling of the underground drainage process and surface flood evolution without explicitly solving the water exchange equation. Finally, through serial coupling of the joint training and inference stages, a fast, stable, and physically consistent simulation of the urban surface-pipe network system is achieved. This method effectively reduces computational complexity and improves simulation efficiency and stability, and can be applied to scenarios such as urban flooding early warning, drainage scheduling, and risk assessment.