CN114676473A - Green infrastructure spatial layout optimization method based on artificial intelligence algorithm - Google Patents
Green infrastructure spatial layout optimization method based on artificial intelligence algorithm Download PDFInfo
- Publication number
- CN114676473A CN114676473A CN202210102135.3A CN202210102135A CN114676473A CN 114676473 A CN114676473 A CN 114676473A CN 202210102135 A CN202210102135 A CN 202210102135A CN 114676473 A CN114676473 A CN 114676473A
- Authority
- CN
- China
- Prior art keywords
- green infrastructure
- green
- artificial intelligence
- intelligence algorithm
- infrastructure
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Abstract
The invention discloses a green infrastructure space layout optimization method based on an artificial intelligence algorithm. The method comprises the following steps: acquiring basic data and monitoring data of a research area; constructing a rainfall flood management model of the research area by adopting basic data of the research area; determining the value of the basic characteristic parameters of the green infrastructure and determining the water flow direction of the green infrastructure; constructing a green infrastructure space layout optimization model based on the combination of an artificial intelligence algorithm and an SWMM model; and obtaining an optimal layout scheme based on the simulation result of the green infrastructure space layout optimization model. The invention provides a key technology for optimizing the spatial layout of the green infrastructure from the aspects of artificial intelligence algorithm and spatial layout, provides an innovative research framework for scientific planning and optimized layout of sponge city construction, and also provides technical means and decision reference for rainfall flood management in highly-urbanized areas.
Description
Technical Field
The invention relates to the field of artificial intelligence and urban hydrology, in particular to a green infrastructure space layout optimization method based on an artificial intelligence algorithm.
Background
The strengthening of urban rainwater management plays an important role in solving the urban water safety problem, and the traditional concept of 'enabling rainwater to be far away from the city as soon as possible' cannot meet the rainfall flood management requirements of modern cities, and is replaced by a new concept of building a 'sponge city'. The system has the advantages that the development rainwater system with low influence, the urban rainwater pipe canal system and the overproof rainwater runoff discharge system are integrated, and the green infrastructure is the core technology for building the development rainwater system with low influence. The research on the space optimization layout of the green infrastructure has great significance in the aspects of establishing a reasonable and efficient rainwater system with low influence, preventing and reducing flood in cities, relieving water resource crisis, purifying water quality, compensating ecological environment and the like (Raei E, Alizadeh M R, Nikoo M R, et al. Multi-object determination-marketing for green in-water treatment planning (LID-BMPs) in the Journal of water storage management under availability [ J ]. Journal of Hydrology,2019, 579: 124091).
The role of the green infrastructure in urban rainfall flood management is important, and the optimization research of the spatial layout of the green infrastructure also obtains certain achievements (Huang C L, Hsu N S, Liu H J, et al. optimization of low impact level layout definitions for social flood assessment [ J ]. Journal of moisture, 2018,564: 542-; (2) and the applicability and feasibility evaluation of a common optimization method are lacked, and whether the calculated optimal solution is a global optimal solution is difficult to judge. Therefore, the invention establishes a green infrastructure space layout optimization framework based on an artificial intelligence algorithm, and discusses a global optimal scheme by integrating a plurality of optimization method results. The expected result can provide theoretical support and technical support for the national sponge city planning and construction, and has important practical significance for the problem of urban water safety management.
Disclosure of Invention
In order to obtain a global optimal green infrastructure spatial layout scheme, the invention provides that the spatial relationship of green infrastructures and the water flow direction are also used as a factor for optimization, and green infrastructure spatial layout optimization based on an artificial intelligence algorithm is provided for guiding the relevant planning of sponge city construction. An optimization model is constructed by adopting an artificial intelligence algorithm, and a global optimal result is extracted by adopting a multi-method result, so that a more comprehensive calculation method is provided for the spatial layout of the green infrastructure.
The purpose of the invention is realized by at least one of the following technical solutions.
A green infrastructure spatial layout optimization method based on an artificial intelligence algorithm comprises the following steps:
s1, acquiring basic data and monitoring data of the research area;
s2, constructing a rainfall flood Management Model (SWMM) of the research area by adopting basic data of the research area;
s3, determining the value of a basic characteristic parameter of a Green Infrastructure (GI), and determining the water flow direction of the Green Infrastructure;
s4, constructing a green infrastructure space layout optimization model based on combination of an artificial intelligence algorithm and an SWMM model;
And S5, obtaining an optimal layout scheme based on the simulation result of the green infrastructure space layout optimization model.
Further, in step S1, the basic data of the research area includes geographic digital elevation information, land use type, river network data, and pipe network data;
monitoring data of the research area comprise rainfall, pipeline/river flow and inspection well water level;
the geographical digital elevation information of the research area is elevation data of the research area; the land utilization type is an underlying surface type of a research area and is divided into a permeable underlying surface and an impermeable underlying surface; the river network data comprises river network spatial distribution and river terrain data; the pipe network data comprises pipe network space distribution, pipeline length, pipeline section shape, pipe diameter, inspection well depth and a connection mode of the pipeline and the inspection well;
acquiring geographical digital elevation information, land utilization types, river network data and pipe network data of a research area by a local water department;
the geographical digital elevation information, land utilization type, river network data and pipe network data of the research area need to be limited to the same coordinate system.
Further, in step S2, the pipeline flow and the inspection well water level data in step S1 should be adopted, and the rationality and accuracy of the SWMM model should be calibrated and verified by comparing the simulation result with the monitoring data, specifically as follows:
The simulation result and the monitoring data of the specific comparison are the water level of the inspection well and the flow process of a pipe network and a river channel, the accuracy of SWMM model simulation is evaluated by adopting a Nash efficiency coefficient (NSE), and the calculation formula is as follows:
wherein Y isiThe observed value of the water level of the inspection well, the flow of the pipe network or the flow of the river channel at the ith moment is obtained;
predicting the water level of the inspection well, the flow of a pipe network or the flow of a river channel at the ith moment for the SWMM model;
the average value of all observed values; n is the total number of observations; the NSE has a value range of (- ∞, 1)]When the numerical value of NSE is closer to 1, the simulation result of the SWMM model can reflect the real situation; the NSE value of the constructed SWMM model cannot be lower than a set threshold value, and otherwise, the constructed SWMM model is reconstructed.
Further, in step S3, the green infrastructure includes a surface layer green infrastructure, a pavement layer green infrastructure, a soil layer green infrastructure, and a livestock water layer green infrastructure;
basic characteristic parameters of the surface layer green infrastructure comprise the dam water storage height, the vegetation coverage rate, the Manning coefficient and the surface gradient of the surface layer;
the basic characteristic parameters of the green infrastructure of the pavement layer comprise the thickness, the porosity ratio, the water impermeability, the permeability and the blocking factor of the pavement layer;
The basic characteristic parameters of the soil layer green infrastructure comprise the thickness, the pore ratio, the soil water holding rate, the wilting point, the hydraulic conductivity grade and the water suction of the soil layer;
the basic characteristic parameters of an aquifer green infrastructure include the thickness, porosity, infiltration rate and blocking factor of the aquifer.
Further, in step S3, the water flow direction between the green infrastructures is from high to low according to the positions of the green infrastructures.
Further, in step S4, an objective function, a constraint condition, and an artificial intelligence algorithm of the green infrastructure spatial layout optimization model are constructed, specifically as follows:
the objective function is used for guiding an optimization objective of the green infrastructure space layout optimization model, and the optimization objective comprises the full life cycle cost and the runoff and water quality control efficiency; optimizing the whole green infrastructure spatial layout optimization model towards the goal of lowest cost and highest efficiency;
the constraint condition is used for limiting the layout of the green infrastructure, and comprises the arrangement of the green infrastructure according to local conditions and the arrangement area of the green infrastructure in a certain area can not exceed the area of the certain area;
the artificial intelligence algorithm is used for searching the optimal spatial layout including the position, the area and the connection relation in the constraint condition range according to the objective function; and (3) adopting a multi-objective optimization algorithm, including SPEA, NSGA and MOEA.
Further, the full lifecycle cost fcThe method comprises the following specific steps:
wherein r is the number of types of green infrastructure facilities; k is a calculation period in units of years; i is annual rate in units of%; csThe unit is element for the total construction cost of LID measures; cmThe management and maintenance cost for LID measure one year, the unit is element; bjConstruction cost unit price for the jth LID measure in units of units/m2； PjCost per unit of element/m for management of class j LID measures2；SjTotal area for type j LID measures in m2(ii) a n is the number of years.
Further, the runoff and water quality control efficiency feThe method comprises the following specific steps:
wherein f ismIs the mth target value; maxfmIs the maximum value of the mth target; f. of1The runoff control efficiency is improved; f. of2Efficiency is controlled for water quality; wmThe weight coefficient of the mth target can be set according to the importance of the target; b is the total number of water outlets in the research area; a is the serial number of the water outlet; vaIs the total runoff quantity of the a-th water outlet, and the unit is m3；TSSaThe total TSS discharge amount of the a-th water outlet is kg;
the runoff control efficiency and the water quality control efficiency of different schemes are calculated by adopting an SWMM model.
Further, the green infrastructure includes recessed greens preferably disposed in an otherwise public area, green roofs preferably disposed in an otherwise public area, and permeable mats preferably disposed in an otherwise impermeable area.
Further, in step S5, the simulation result based on the green infrastructure spatial layout optimization model includes results calculated by a plurality of artificial intelligence algorithms, the result of each algorithm is a local optimal result, the global optimal result is determined by using an outsourcing line method, and the optimal scheme of the green infrastructure spatial layout at different costs is determined.
Compared with the prior art, the invention has the beneficial effects that:
the invention can calculate the optimized layout scheme of the green infrastructure of the research area under different costs, provides the optimized factor of the green infrastructure connection relation, adopts various artificial intelligence algorithms to avoid the simulation result from falling into the local optimal solution, provides a new way for constructing the global optimal space layout of the green infrastructure, and provides a more comprehensive calculation method for planning and constructing the sponge city.
Drawings
FIG. 1 is a flow chart of a green infrastructure spatial layout optimization method based on an artificial intelligence algorithm of the present invention;
FIG. 2 is a schematic diagram of a green infrastructure water flow direction of a green infrastructure spatial layout optimization method based on an artificial intelligence algorithm according to an embodiment of the present invention;
fig. 3 is a schematic diagram of the artificial intelligence algorithm and SWMM model calling relationship of the green infrastructure spatial layout optimization method based on the artificial intelligence algorithm in the embodiment of the present invention (taking NSGA II as an example);
Fig. 4 is a schematic diagram of obtaining a globally optimal leading edge based on local optimal leading edges of multiple artificial intelligence algorithms in a green infrastructure spatial layout optimization method based on an artificial intelligence algorithm according to an embodiment of the present invention.
Fig. 5 is a global optimal leading edge comparison diagram of 3 embodiments of the present invention.
Detailed Description
The following description will further explain embodiments of the present invention by referring to the figures and examples. The same or similar symbols and signs mentioned in the description of the present specification represent the same or similar physical meanings or have the same or similar functions, and the drawings used in the present specification are only for better explaining the present invention and the applicability of the present invention is not limited thereto.
The embodiment is as follows:
a green infrastructure spatial layout optimization method based on artificial intelligence algorithm, as shown in fig. 1, includes the following steps:
s1, acquiring basic data and monitoring data of the research area;
basic data of a research area comprise geographical digital elevation information, land utilization types, river network data and pipe network data;
the monitoring data of the research area comprises rainfall, pipeline/river flow and inspection well water level;
the geographical digital elevation information of the research area is elevation data of the research area; the land utilization type is the type of the underlying surface of the research area and is divided into a permeable underlying surface and an impermeable underlying surface; the river network data comprises river network spatial distribution and river terrain data; the pipe network data comprises pipe network space distribution, pipeline length, pipeline section shape, pipe diameter, inspection well depth and a connection mode of the pipeline and the inspection well;
Acquiring geographical digital elevation information, land utilization types, river network data and pipe network data of a research area by a local water department;
the geographical digital elevation information, land utilization type, river network data and pipe network data of the research area need to be limited to the same coordinate system.
S2, constructing a rainfall flood Management Model (SWMM) of the research area by adopting basic data of the research area;
the pipeline flow and inspection well water level data of the step S1 are obtained through monitoring, and the rationality and accuracy of the SWMM model are calibrated and verified in a mode of comparing a simulation result with monitoring data, and the method specifically comprises the following steps:
the simulation result and the monitoring data of the specific comparison are the water level of the inspection well and the flow process of a pipe network and a river channel, the accuracy of SWMM model simulation is evaluated by adopting a Nash efficiency coefficient (NSE), and the calculation formula is as follows:
wherein, YiThe observed value of the water level of the inspection well, the flow of the pipe network or the flow of the river channel at the ith moment is obtained;
predicting the water level of the inspection well, the flow of a pipe network or the flow of a river channel at the ith moment for the SWMM model;
the average value of all observed values; n is the total number of observations; the NSE has a value range of (- ∞, 1)]When the numerical value of NSE is closer to 1, the simulation result of the SWMM model can reflect the real situation; in this embodiment, the NSE value of the constructed SWMM model cannot be lower than 0.7, otherwise, it needs to be reconstructed.
S3, determining the value of a basic characteristic parameter of a Green Infrastructure (GI), and determining the water flow direction of the Green Infrastructure; in this example, four different green infrastructures, namely, a green roof, a sunken green land, a permeable pavement and a bioretention pond, are selected for explanation.
In this embodiment, taking water permeable pavement as an example, the basic characteristic parameters of the green infrastructure should include the parameters shown in the following table.
TABLE 1 Green infrastructure basic characteristic parameters table (permeable pavement for example)
The water flow direction between the green infrastructures is from high to low according to the positions of the green infrastructures.
In this embodiment, the roof is at the highest position, and the permeable pavement, the bioretention pond are the second time, then the concave greenbelt, and finally the water outlet. Water flow may be from an elevated green infrastructure to a lower green infrastructure, and vice versa. The connection scheme of this example is shown in figure 2.
S4, constructing a green infrastructure space layout optimization model based on combination of an artificial intelligence algorithm and an SWMM model;
constructing an objective function, a constraint condition and an artificial intelligence algorithm of a green infrastructure spatial layout optimization model, which comprises the following specific steps:
The objective function is used for guiding an optimization objective of the green infrastructure space layout optimization model, and the optimization objective comprises the full life cycle cost and the runoff and water quality control efficiency; optimizing the whole green infrastructure spatial layout optimization model towards the goal of lowest cost and highest efficiency;
the constraint condition is used for limiting the layout of the green infrastructure, and comprises the green infrastructure which is arranged according to local conditions and the area of a certain land can not be exceeded when the green infrastructure is arranged in the area of the land;
the artificial intelligence algorithm is used for searching the optimal spatial layout including the position, the area and the connection relation in the constraint condition range according to the objective function; the artificial intelligence algorithm adopts a multi-objective optimization algorithm, including SPEA, NSGA and MOEA. In the embodiment, three multi-objective optimization algorithms are adopted, including SPEA II, MOEA \ D and NSGA II.
The full lifecycle cost fcThe method comprises the following specific steps:
wherein r is the number of types of green infrastructure facilities; k is a calculation period in years; i is annual rate in%; csThe unit is element for the total construction cost of LID measures; cmThe unit is element for the management and maintenance cost of LID measure for one year; b isjConstruction cost unit price for the jth LID measure in units of units/m 2； PjCost per unit of element/m for class j LID measures2；SjTotal area for type j LID measures in m2(ii) a n is the number of years.
Efficiency f for controlling runoff and water qualityeThe method comprises the following specific steps:
wherein, fmIs the mth target value; maxfmIs the maximum value of the mth target; f. of1The runoff control efficiency is improved; f. of2Efficiency is controlled for water quality; wmThe weighting factor for the mth target can be set according to the importance of the target, W in the embodiment1＝0.5，W20.5; b is the total number of water outlets in the research area; a is the serial number of the water outlet; vaIs the total runoff quantity of the a-th water outlet, and the unit is m3；TSSaThe total TSS discharge amount of the a-th water outlet is kg;
runoff control efficiency and water quality control efficiency of different schemes are calculated by adopting an SWMM model, and the calling relationship between a multi-objective optimization algorithm and the SWMM model is shown in figure 3 (taking an NSGA algorithm as an example). A green infrastructure space layout scheme is established by a multi-objective optimization algorithm, the obtained scheme is input into an SWMM model for calculation, a calculation result is fed back to the multi-objective optimization algorithm, and whether iteration is finished or not is judged; if yes, stopping iteration; if not, a new scheme is constructed by the multi-objective optimization algorithm for recalculation.
The green infrastructure includes recessed greens preferably in an otherwise public area where greens and water are impervious, green roofs preferably in an otherwise roofed area, and permeable mats preferably in an otherwise impervious pavement area.
S5, obtaining an optimal layout scheme based on the simulation result of the green infrastructure spatial layout optimization model;
the simulation result based on the green infrastructure spatial layout optimization model comprises results calculated by a plurality of artificial intelligence algorithms, the result of each algorithm is a local optimal result, an outsourcing line method is adopted to determine a global optimal result, and optimal schemes of the green infrastructure spatial layout under different costs are determined.
Example 2:
the present embodiment is different from embodiment 1 in that the multi-objective optimization algorithm employs only the NSGA II algorithm.
Example 3:
this example differs from example 1 in that there is no water flow connection between the green infrastructure in this example.
And (4) comparing the results: a certain area in Guangzhou city is selected as a research area, and the calculation results of the three embodiments in a 5-year designed rainstorm scene are calculated respectively, as shown in FIG. 5, the results of the three embodiments are shown. From the figure, it can be found that the leading edge curve of example 1 is optimal. Example 2 calculated using only the NSGA II algorithm, the resulting leading edge curve is inferior to the results of example 1 at costs below 120 and above 250 ten thousand. The green infrastructure of example 3 is connected without water flow, i.e. regardless of the connection, the resulting solution is inferior to the results of example 1 at whatever cost.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (10)
1. A green infrastructure space layout optimization method based on an artificial intelligence algorithm is characterized by comprising the following steps:
s1, acquiring basic data and monitoring data of the research area;
s2, constructing a rainfall flood Management Model (SWMM) of the research area by adopting basic data of the research area;
s3, determining the value of a basic characteristic parameter of a Green Infrastructure (GI), and determining the water flow direction of the Green Infrastructure;
s4, constructing a green infrastructure space layout optimization model based on combination of an artificial intelligence algorithm and an SWMM model;
And S5, obtaining an optimal layout scheme based on the simulation result of the green infrastructure space layout optimization model.
2. The method for optimizing the spatial layout of the green infrastructure based on the artificial intelligence algorithm as claimed in claim 1, wherein in the step S1, the basic data of the research area includes geographical digital elevation information, land use type, river network data and pipe network data;
the monitoring data of the research area comprises rainfall, pipeline/river flow and inspection well water level;
the geographical digital elevation information of the research area is elevation data of the research area; the land utilization type is the type of the underlying surface of the research area and is divided into a permeable underlying surface and an impermeable underlying surface; the river network data comprises river network spatial distribution and river terrain data; the pipe network data comprises pipe network space distribution, pipeline length, pipeline section shape, pipe diameter, inspection well depth and a connection mode of the pipeline and the inspection well;
acquiring geographical digital elevation information, land utilization types, river network data and pipe network data of a research area by a local water department;
the geographical digital elevation information, land utilization type, river network data and pipe network data of the research area need to be limited to the same coordinate system.
3. The artificial intelligence algorithm-based green infrastructure spatial layout optimization method according to claim 2, wherein the pipeline flow and inspection well water level data in the step S1 are adopted in the step S2, and the rationality and accuracy of the SWMM model are calibrated and verified in a mode of comparing simulation results with monitoring data, and the method is specifically as follows:
the simulation result and the monitoring data of the specific comparison are the water level of the inspection well and the flow process of a pipe network and a river channel, the accuracy of SWMM model simulation is evaluated by adopting a Nash efficiency coefficient (NSE), and the calculation formula is as follows:
wherein Y isiThe observed value of the water level of the inspection well, the flow of the pipe network or the flow of the river channel at the ith moment is obtained;
predicting the water level of the inspection well, the flow of a pipe network or the flow of a river channel at the ith moment for the SWMM model;
the average value of all observed values; n is the total number of observations; the NSE has a value range of (- ∞, 1)]When the numerical value of NSE is closer to 1, the simulation result of the SWMM model can reflect the real situation; the NSE value of the constructed SWMM model cannot be lower than a set threshold value, and otherwise, the constructed SWMM model is reconstructed.
4. The artificial intelligence algorithm-based green infrastructure spatial layout optimization method of claim 1, wherein in step S3, the green infrastructure includes a surface layer green infrastructure, a pavement layer green infrastructure, a soil layer green infrastructure and a livestock water layer green infrastructure;
The basic characteristic parameters of the surface layer green infrastructure comprise the water storage height of the dike dam of the surface layer, the vegetation coverage rate, the Manning coefficient and the surface gradient;
the basic characteristic parameters of the pavement layer green infrastructure comprise the thickness, the porosity ratio, the water impermeability, the permeability and the blocking factor of the pavement layer;
the basic characteristic parameters of the soil layer green infrastructure comprise the thickness, the porosity, the soil water retention rate, the wilting point, the hydraulic conductivity gradient and the water suction of the soil layer;
the fundamental characteristic parameters of an aquifer green infrastructure include the thickness, porosity, infiltration rate and obstruction factor of the aquifer.
5. The method for optimizing the spatial layout of green infrastructures based on artificial intelligence algorithm according to claim 4, wherein in step S3, the water flow direction between green infrastructures is from high to low according to the position of the green infrastructures.
6. The method for optimizing the spatial layout of the green infrastructure based on the artificial intelligence algorithm according to claim 1, wherein in step S4, the objective function, the constraint condition and the artificial intelligence algorithm of the model for optimizing the spatial layout of the green infrastructure are constructed, specifically as follows:
The objective function is used for guiding an optimization objective of the green infrastructure space layout optimization model, and the optimization objective comprises the full life cycle cost and the runoff and water quality control efficiency; optimizing the whole green infrastructure spatial layout optimization model towards the goal of lowest cost and highest efficiency;
the constraint condition is used for limiting the layout of the green infrastructure, and comprises the arrangement of the green infrastructure according to local conditions and the arrangement area of the green infrastructure in a certain area can not exceed the area of the certain area;
the artificial intelligence algorithm is used for searching the optimal spatial layout including the position, the area and the connection relation in the constraint condition range according to the objective function; the artificial intelligence algorithm adopts a multi-objective optimization algorithm, including SPEA, NSGA and MOEA.
7. The method of claim 6, wherein the full-lifecycle cost f is an artificial intelligence algorithm-based green infrastructure spatial layout optimization methodcThe method comprises the following specific steps:
wherein r is the number of types of green infrastructure facilities; k is a calculation period in years; i is annual rate in%; csThe unit is element for the total construction cost of LID measures; cmThe unit is element for the management and maintenance cost of LID measure for one year; b is jConstruction cost unit price for the jth LID measure in units of units/m2；PjCost per unit of element/m for management of class j LID measures2；SjTotal area for type j LID measures in m2(ii) a n is the number of years.
8. The method of claim 6, wherein the runoff and water quality control efficiency f is an artificial intelligence algorithm-based green infrastructure spatial layout optimization methodeThe method comprises the following specific steps:
wherein f ismIs the mth target value; maxfmIs the maximum value of the mth target; f. of1The runoff control efficiency is improved; f. of2Efficiency is controlled for water quality; wmThe weight coefficient of the mth target can be set according to the importance of the target; b is the total number of water outlets in the research area; a is the serial number of the water outlet; vaIs the total runoff quantity of the a-th water outlet, and the unit is m3；TSSaThe total TSS discharge amount of the a-th water outlet is kg;
the runoff control efficiency and the water quality control efficiency of different schemes are calculated by adopting an SWMM model.
9. The method of claim 6, wherein the green infrastructure spatial layout optimization based on artificial intelligence algorithm comprises a concave green land area and a waterproof common area, a green roof area and a permeable pavement area.
10. The method for optimizing the spatial layout of the green infrastructure based on the artificial intelligence algorithm according to any one of claims 1 to 9, wherein in step S5, the simulation result based on the model for optimizing the spatial layout of the green infrastructure comprises a plurality of results calculated by the artificial intelligence algorithm, each result of the algorithm is a local optimal result, an outsourcing line method is used to determine a global optimal result, and an optimal scheme of the spatial layout of the green infrastructure at different costs is determined.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210102135.3A CN114676473A (en) | 2022-01-27 | 2022-01-27 | Green infrastructure spatial layout optimization method based on artificial intelligence algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210102135.3A CN114676473A (en) | 2022-01-27 | 2022-01-27 | Green infrastructure spatial layout optimization method based on artificial intelligence algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114676473A true CN114676473A (en) | 2022-06-28 |
Family
ID=82072966
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210102135.3A Pending CN114676473A (en) | 2022-01-27 | 2022-01-27 | Green infrastructure spatial layout optimization method based on artificial intelligence algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114676473A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115409244A (en) * | 2022-08-03 | 2022-11-29 | 北京大学深圳研究院 | Green infrastructure multi-objective decision optimization method applied to rainfall flood management |
| CN117391252A (en) * | 2023-11-02 | 2024-01-12 | 华南农业大学 | Green infrastructure space layout optimization method considering complex rainfall pattern |
-
2022
- 2022-01-27 CN CN202210102135.3A patent/CN114676473A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115409244A (en) * | 2022-08-03 | 2022-11-29 | 北京大学深圳研究院 | Green infrastructure multi-objective decision optimization method applied to rainfall flood management |
| CN117391252A (en) * | 2023-11-02 | 2024-01-12 | 华南农业大学 | Green infrastructure space layout optimization method considering complex rainfall pattern |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492259B (en) | Urban hydrologic simulation system | |
| CN109492299B (en) | Water resource simulation method based on SWMM and MODIflow coupling | |
| CN110543984B (en) | Urban water surface rate planning method based on water safety | |
| CN114676473A (en) | Green infrastructure spatial layout optimization method based on artificial intelligence algorithm | |
| CN111582755A (en) | Mountain torrent disaster comprehensive risk dynamic assessment method based on multi-dimensional set information | |
| CN111062125B (en) | Hydrological effect evaluation method for sponge type comprehensive pipe gallery | |
| CN114252128B (en) | Underground pipe gallery water inflow monitoring and early warning system and method | |
| CN113011685A (en) | Simulation prediction method for water level change of inland lake in runoff data-free area | |
| Gao et al. | A distribution optimization method of typical LID facilities for sponge city construction | |
| CN110838079A (en) | Intelligent city flood control and drainage remote monitoring system and method | |
| CN114372685A (en) | Urban rainstorm waterlogging risk assessment method based on SWMM model | |
| CN109559098A (en) | A kind of low influence development facility analogy method in sponge city pilot area | |
| CN115391712A (en) | Urban flood risk prediction method | |
| CN112052561A (en) | Method for formulating waterlogging prevention emergency plan of drainage system | |
| CN106156949A (en) | A kind of rainwater based on waterlogging risk assessment is low affects development project method | |
| CN114139258A (en) | Urban inland inundation modeling evaluation method and system and computer readable storage medium | |
| CN112907047A (en) | Sponge city performance evaluation system | |
| CN115758886A (en) | Optimal distribution method of storage tanks based on rain flood pipe network model and decision tree algorithm | |
| CN110287595B (en) | Method for analyzing disaster reduction effect of different underlying surfaces of city | |
| CN110232479A (en) | A kind of city flood control by reservoir regulation compensation optimizing dispatching method | |
| CN112084671A (en) | Urban time-varying gain rainfall-runoff process simulation calculation method | |
| Yang et al. | Optimal designs of LID based on LID experiments and SWMM for a small-scale community in Tianjin, north China | |
| CN115700634A (en) | Rainfall flood regulation and storage space optimization layout method based on future risks | |
| CN112052545A (en) | Urban surface runoff and pipe network confluence coupling method based on cellular automaton | |
| CN115859676A (en) | Multi-level urban waterlogging coupling simulation method considering climate elements |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |