CN114611756A - Urban combined drainage system water quantity load prediction method based on remote sensing technology - Google Patents
Urban combined drainage system water quantity load prediction method based on remote sensing technology Download PDFInfo
- Publication number
- CN114611756A CN114611756A CN202210129309.5A CN202210129309A CN114611756A CN 114611756 A CN114611756 A CN 114611756A CN 202210129309 A CN202210129309 A CN 202210129309A CN 114611756 A CN114611756 A CN 114611756A
- Authority
- CN
- China
- Prior art keywords
- data
- catchment
- area
- rainfall
- urban
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000005516 engineering process Methods 0.000 title claims abstract description 17
- 239000010865 sewage Substances 0.000 claims abstract description 109
- 238000013507 mapping Methods 0.000 claims abstract description 44
- 238000012544 monitoring process Methods 0.000 claims abstract description 30
- 230000033228 biological regulation Effects 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000002360 preparation method Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract description 5
- 230000010485 coping Effects 0.000 abstract description 2
- 241000196324 Embryophyta Species 0.000 description 31
- 238000012549 training Methods 0.000 description 21
- 238000010586 diagram Methods 0.000 description 8
- 238000010606 normalization Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000004913 activation Effects 0.000 description 5
- 238000010200 validation analysis Methods 0.000 description 5
- 230000007423 decrease Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012897 Levenberg–Marquardt algorithm Methods 0.000 description 1
- DFPOZTRSOAQFIK-UHFFFAOYSA-N S,S-dimethyl-beta-propiothetin Chemical compound C[S+](C)CCC([O-])=O DFPOZTRSOAQFIK-UHFFFAOYSA-N 0.000 description 1
- 241000219094 Vitaceae Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 235000021021 grapes Nutrition 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Pure & Applied Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Analysis (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Entrepreneurship & Innovation (AREA)
Abstract
The invention discloses a method for predicting water load of an urban combined drainage system based on a remote sensing technology, which comprises the following steps: indirectly estimating the sewage discharge amount of the urban residential area by using multi-source remote sensing data; utilizing DEM data and city-level rainfall data to estimate rainfall catchment area and catchment amount of a potential catchment area; integrating water quantity monitoring data of a pipe network, an intercepting well, a regulation and storage pool and a sewage plant, mapping sewage discharge, catchment area, catchment quantity and various water quantity monitoring data to a unified geographical space grid, and constructing a city residential area combined drainage system model; forecasting the water volume load of each district pipe network, a cut-off well, a regulation and storage pool and a sewage plant based on the constructed model by utilizing the latest multi-source remote sensing data, rainfall forecast data and the like, and carrying out early warning work; the system monitors and gives early warning to the combined drainage system in the rainfall period, assists in carrying out scheduling work, thereby providing reference for planning construction of relevant urban facilities, rain and sewage diversion projects and the like and coping with urban overflow pollution events.
Description
Technical Field
The invention relates to the field of urban combined drainage systems, in particular to a method and a method for predicting water load of an urban combined drainage system based on a remote sensing technology.
Background
Along with the rapid expansion of cities in China, the discharge amount of domestic sewage of residents is increased, the operating pressure of a combined drainage system built in an early stage is gradually increased, facilities are independent of one another, and overall scheduling and management are lacked; meanwhile, as most of the pipe networks in the early stage do not adopt rain and sewage diversion measures, a large amount of rain water is gathered in the rainy season, so that the water quantity in the pipes is increased rapidly. In recent years, frequent and serious extreme rainfall events bring more challenges to the operation of a combined system drainage system, and more urban overflow pollution events are caused.
Aiming at the water quantity monitoring of the urban combined system drainage system, the traditional method usually only monitors the independent point position of the drainage system, and lacks the prediction and early warning work based on rain and sewage source head analysis. Therefore, a prediction method for the water load of the urban combined drainage system is established, the water quantity of the urban combined drainage system is predicted, analyzed and early warned before the potential rainfall period, and the urban combined drainage system has a good support effect on urban flood prevention and disaster reduction.
Disclosure of Invention
The invention aims to overcome the defects and provides a method for predicting the water load of an urban combined drainage system based on a remote sensing technology, which is supported by a multi-source satellite remote sensing technology, constructs a water load model of the urban combined drainage system through deep learning, monitors and gives an early warning to the combined drainage system in a rainfall period, assists in carrying out scheduling work, thus providing reference for planning construction of urban related facilities, rain and sewage diversion engineering and the like and coping with urban overflow pollution events.
In order to solve the technical problems, the invention adopts the technical scheme that: a method for predicting water load of an urban combined drainage system based on a remote sensing technology comprises the following steps:
s1, indirectly estimating the sewage discharge amount of the urban residential area by using multi-source satellite remote sensing data and combining the data of the sky map and the Gaode map;
s2, estimating rainfall catchment area and catchment amount of the potential road surface catchment area by using DEM data and city-level rainfall data, and forming a unified mapping geographic space grid R according to the DEM data and the rainfall data;
s3, respectively mapping sewage discharge, rainfall catchment area and catchment amount of each residential area of a city to a unified grid R as input, respectively mapping water amount monitoring data of each residential area combined drainage system pipe network, a cutoff well, a regulation and storage pool and a sewage plant to the unified grid R as output according to pipe network line information and point location geographic information, and constructing a city residential area combined drainage system model by using a deep learning mode;
s4, based on the constructed urban residential area combined flow system drainage system model, combining the latest multi-source satellite remote sensing data, rainfall forecast data and DEM data estimation results, predicting the water volume load conditions of each area pipe network, the intercepting well, the storage tank and the sewage plant in the potential rainfall period, and carrying out early warning work.
Further, the specific process of estimating the sewage discharge amount of the urban residential area in the step S1 is as follows:
the urban surface earth buildings are preliminarily divided through multispectral remote sensing data, the range of urban residential areas is determined by combining data refinement of a sky map and a Gaode map, the population density of each residential area of an urban is estimated by combining light intensity fed back by night light remote sensing data and the population number of area statistics, and the sewage discharge amount of the urban residential areas is indirectly estimated according to the per-person sewage discharge empirical value.
Further, the step S1 specifically includes the following steps:
s101, carrying out batch preprocessing on the remote sensing data by utilizing Envi, ArcGIS and Python, wherein the preprocessing comprises splicing, correcting, projection conversion and cloud removing;
s102, dividing each urban area based on multispectral remote sensing data, extracting urban ground building information, and further subdividing the extracted building information to obtain an urban residential area range based on urban residential area point location information marked by a sky map and a Gaode map data;
s103, obtaining light intensity values in all residential area ranges of the city based on night light remote sensing data, estimating population density of the residential area according to the population number counted by the residential area, and indirectly estimating sewage discharge, wherein the formula is as follows:
Pi＝Li/(L1+L2+......+Ln)×Dc×E
wherein Pi is the sewage discharge amount of the residential area i, Li is the light intensity value of the residential area i, (L1+ L2+ -. once. - + Ln) is the sum of the light intensity values of the parcel c, Dc is the total population of the parcel c, and E is the average sewage discharge amount of people.
Further, the step S2 is specifically: the method comprises the steps of judging a potential rainfall road surface catchment area of the city by utilizing DEM data, marking catchment area grids, evaluating the spatial distribution condition of the rainfall of the city by combining rainfall data of the city level per hour, and estimating the rainfall catchment area and the rainfall catchment amount of the potential catchment area.
Further, the specific process of constructing the urban residential area combined drainage system model in step S3 is as follows:
taking the estimated sewage discharge amount of each residential area of a city and the rainfall catchment area and catchment amount of a catchment area as model input quantities, and taking the integrated water quantity monitoring data of each district pipe network, the intercepting well, the storage tank and the sewage plant in the corresponding rainfall period as model output quantities; respectively mapping each input quantity and each output quantity to a unified geographic space grid R according to multi-source satellite remote sensing data, rainfall data, DEM data geographic information, pipe network line information of each block, intercepting well point location information, storage tank point location information and sewage plant point location information, and inputting the models; and establishing a potential relation between input quantity and output quantity by using a deep learning mode, and establishing a city residential area combined drainage system model.
Further, the step S3 specifically includes the following steps:
s301, taking sewage discharge amount, rainwater catchment areas, catchment areas and water catchment amount data of urban residential areas as model input amounts, taking water amount monitoring data of a combined drainage system pipe network, a cutoff well, a regulation and storage pool and a sewage plant of each area as model output amounts, and considering dimension difference of each variable, standardizing data dimensions by the model in a form of mapping to a unified geographic space grid;
s302, determining a unified geographic space grid (500 x 500 matrix dimensions, 30m spatial resolution scale) by using the DEM data and the urban rainfall data, and recording as a grid R;
s303, mapping the sewage discharge amount W of each residential area of the city estimated in the corresponding rainfall period to a grid R based on the position and range of each residential area extracted by the remote sensing data, and recording as an input dimensional layer MI _ 1;
s304, respectively mapping catchment area S and catchment quantity V data to a grid R based on the evaluated rainwater catchment area information, and respectively recording the catchment area S and the catchment quantity V data as an input dimension layer MI _2 and an input dimension layer MI _ 3;
s305, mapping corresponding monitoring water volume data to a grid R respectively based on the pipe network line information of each district and the information of the intercepting well, the storage regulation pool and the sewage plant point location, and recording the corresponding monitoring water volume data as an output dimension layer MO _1, an output dimension layer MO _2, an output dimension layer MO _3 and an output dimension layer MO _4 respectively;
s306, constructing a city residential area combined flow and drainage system model by taking the input dimension layers MI _1, MI _2 and MI _3 as model input data and the output dimension layers MO _1, MO _2, MO _3 and MO _4 as model output (target) data.
Further, the step S4 is a specific process for predicting the water volume load of each district pipe network, catch basin, storage tank and sewage plant in the potential rainfall period as follows:
estimating population density of urban residential areas according to updated multi-source satellite remote sensing data (multispectral remote sensing data and night light remote sensing data), indirectly estimating sewage discharge of the urban residential areas closest to a rainfall forecast period, mapping the sewage discharge to a uniform grid R and using the uniform grid R as input quantity; according to the DEM data and the rainfall forecast data, the rainfall catchment area and the catchment amount of the potential catchment area are estimated, and the area and the catchment amount are mapped to the unified grid R and serve as input quantities; based on the constructed urban residential area combined drainage system model, the forecasting conditions of water volume loads of each district pipe network, the intercepting well, the regulating and storing pool and the sewage plant in the potential rainfall period are obtained, and scheduling of water stored in drainage facilities and emergency preparation early warning work of a potential overflow pollution area are carried out.
Further, the step S4 specifically includes the following steps:
s401, acquiring night light remote sensing data closest to a rainfall forecast period, estimating the sewage discharge amount of each residential area of a city closest to the rainfall forecast period based on the position and range information of each residential area estimated before, mapping the data to a grid R, and recording the data as an input dimension layer PI _ 1;
s402, forecasting catchment area and catchment amount by utilizing rainfall forecast data and combining with a potential rainwater catchment area evaluated by DEM data, respectively mapping the forecasted catchment area and catchment amount data to a grid R based on the geographic information of the potential catchment area, and respectively recording the data as an input dimensional layer PI _2 and an input dimensional layer PI _ 3;
s403, based on the urban residential area combined drainage system model constructed in the step S3, taking input dimension layers PI _1, PI _2 and PI _3 as model input quantities to obtain water quantity prediction conditions of each district pipe network, the intercepting well, the storage tank and the sewage plant;
s404, judging whether the prediction result influences the normal operation of each drainage facility in the potential rainfall period according to the full-load water volume setting of a pipe network, an intercepting well, a regulation and storage tank and a sewage plant, and carrying out scheduling work of water stored in the drainage facility before rainfall according to the condition; for areas with serious overflow pollution, related facilities for storing water and draining water are erected on the ground in advance to deal with emergencies.
The invention has the beneficial effects that:
(1) the invention provides a method for remotely monitoring and predicting the water quantity of a combined drainage facility, which reduces the field work and the operation and maintenance cost;
(2) the method optimizes the monitoring of the traditional drainage facilities on single point positions, takes all the drainage facilities into consideration, and can analyze the water volume load of the whole combined drainage system through a model;
(3) according to the method, the water volume load of each facility of the combined drainage system is predicted through the model, and the water volume conditions of each district pipe network, the intercepting well, the storage tank and the sewage plant in the potential rainfall period can be estimated in advance; analyzing the normal operation condition of each drainage facility in the potential rainfall period, and carrying out early warning work such as water storage scheduling, potential overflow pollution area emergency preparation and the like in advance;
(4) the water quantity monitoring and predicting results of all drainage facilities can provide support for repairing and rebuilding the urban combined drainage system, and reference is not provided for urban drainage system planning, construction and urban rainwater and sewage diversion projects in the future.
Drawings
FIG. 1 is a flow diagram of an embodiment of the present invention;
FIG. 2 is an exemplary diagram of input dimension layers;
FIG. 3 is an exemplary diagram of various output dimension layers;
FIG. 4 is a frame diagram of a constructed model of a combined drainage system in urban residential areas;
FIG. 5 is a diagram of an example of a model window operation being constructed;
FIG. 6 is an exemplary graph of the number of failed tests of the constructed model;
FIG. 7 is an exemplary graph of the constructed model training error curve.
Detailed Description
The invention is described in further detail below with reference to the figures and specific embodiments.
As shown in fig. 1 to 7, a method for predicting water load of an urban combined drainage system based on remote sensing technology comprises the following steps:
s1, indirectly estimating the sewage discharge amount of the urban residential area by using multi-source satellite remote sensing data and combining a sky map and Gaode map data;
s2, estimating rainfall catchment area and catchment amount of the potential road surface catchment area by using DEM data and city-level rainfall data, and forming a unified mapping geographic space grid R according to the DEM data and the rainfall data;
s3, respectively mapping sewage discharge, rainfall catchment area and catchment amount of each residential area of a city to a unified grid R as input, respectively mapping water amount monitoring data of each residential area combined drainage system pipe network, a cutoff well, a regulation and storage pool and a sewage plant to the unified grid R as output according to pipe network line information and point location geographic information, and constructing a city residential area combined drainage system model by using a deep learning mode;
s4, based on the constructed urban residential area combined flow system drainage system model, combining the latest multi-source satellite remote sensing data, rainfall forecast data and DEM data estimation results, predicting the water volume load conditions of each area pipe network, the intercepting well, the storage tank and the sewage plant in the potential rainfall period, and carrying out early warning work.
Further, the specific process of estimating the sewage discharge amount of the urban residential area in the step S1 is as follows:
the urban surface buildings are preliminarily divided through multispectral remote sensing data, the range of urban residential areas is determined by combining data refinement of a sky map and a Gade map, the population density of each residential area of an urban is estimated by combining the light intensity fed back by night light remote sensing data and the population number of area statistics, and the sewage discharge amount of the urban residential areas is indirectly estimated according to the per-capita sewage discharge experience value.
Further, the step S1 specifically includes the following steps:
s101, carrying out batch preprocessing on the remote sensing data by utilizing Envi, ArcGIS and Python, wherein the preprocessing comprises splicing, correcting, projection conversion and cloud removing;
s102, dividing each urban area based on multispectral remote sensing data, extracting urban ground building information, and further subdividing the extracted building information to obtain an urban residential area range based on urban residential area point location information marked by a sky map and a Gaode map data;
s103, obtaining light intensity values in all residential area ranges of the city based on night light remote sensing data, estimating population density of the residential area according to the population number counted by the residential area, and indirectly estimating sewage discharge, wherein the formula is as follows:
Pi＝Li/(L1+L2+......+Ln)×Dc×E
wherein Pi is the sewage discharge amount of the residential area i, Li is the light intensity value of the residential area i, (L1+ L2+. multidot.. multidot. + Ln) is the sum of the light intensity values of the parcel c, Dc is the total population number of the parcel c, and E is the average sewage discharge amount of people.
Further, the step S2 is specifically: the method comprises the steps of judging a potential rainfall road surface catchment area of the city by utilizing DEM data, marking catchment area grids, evaluating the spatial distribution condition of the rainfall of the city by combining rainfall data of the city level per hour, and estimating the rainfall catchment area and the rainfall catchment amount of the potential catchment area.
Further, the specific process of constructing the urban residential area combined drainage system model in step S3 is as follows:
taking the estimated sewage discharge amount of each residential area of a city and the rainfall catchment area and catchment amount of a catchment area as model input quantities, and taking the integrated water quantity monitoring data of each district pipe network, the intercepting well, the storage tank and the sewage plant in the corresponding rainfall period as model output quantities; respectively mapping each input quantity and each output quantity to a unified geographic space grid R according to multi-source satellite remote sensing data, rainfall data, DEM data geographic information, pipe network line information of each block, intercepting well point location information, storage tank point location information and sewage plant point location information, and inputting the models; and establishing a potential relation between input quantity and output quantity by using a deep learning mode, and establishing a city residential area combined drainage system model.
Further, the step S3 specifically includes the following steps:
s301, taking sewage discharge amount, rainwater catchment areas, catchment areas and water catchment amount data of urban residential areas as model input amounts, taking water amount monitoring data of a combined drainage system pipe network, a cutoff well, a regulation and storage pool and a sewage plant of each area as model output amounts, and considering dimension difference of each variable, standardizing data dimensions by the model in a form of mapping to a unified geographic space grid;
s302, determining a unified geographic space grid (500 x 500 matrix dimensions, 30m spatial resolution scale) by using the DEM data and the urban rainfall data, and recording as a grid R;
s303, mapping the sewage discharge amount W of each residential area of the city estimated in the corresponding rainfall period to a grid R based on the position and range of each residential area extracted by the remote sensing data, and recording as an input dimensional layer MI _ 1;
s304, respectively mapping catchment area S and catchment quantity V data to a grid R based on the evaluated rainwater catchment area information, and respectively recording the catchment area S and the catchment quantity V data as an input dimension layer MI _2 and an input dimension layer MI _ 3;
s305, mapping corresponding monitoring water volume data to a grid R respectively based on the pipe network line information of each district and the information of the intercepting well, the storage regulation pool and the sewage plant point location, and recording the corresponding monitoring water volume data as an output dimension layer MO _1, an output dimension layer MO _2, an output dimension layer MO _3 and an output dimension layer MO _4 respectively;
s306, constructing a city residential area combined flow and drainage system model by taking the input dimension layers MI _1, MI _2 and MI _3 as model input data and the output dimension layers MO _1, MO _2, MO _3 and MO _4 as model output (target) data.
Further, the step S4 is a specific process for predicting the water volume load of each district pipe network, catch basin, storage tank and sewage plant in the potential rainfall period as follows:
estimating population density of urban residential areas according to updated multi-source satellite remote sensing data (multispectral remote sensing data and night light remote sensing data), indirectly estimating sewage discharge of the urban residential areas closest to a rainfall forecast period, mapping the sewage discharge to a uniform grid R and using the uniform grid R as input quantity; according to the DEM data and the rainfall forecast data, the rainfall catchment area and the catchment amount of the potential catchment area are estimated, and the area and the catchment amount are mapped to the unified grid R and serve as input quantities; based on the constructed urban residential area combined drainage system model, the forecasting conditions of water volume loads of pipe networks, intercepting wells, regulation and storage tanks and sewage plants in all areas in the potential rainfall period are obtained, and scheduling of water stored in drainage facilities and emergency preparation early warning work of potential overflow pollution areas are carried out.
Further, the step S4 specifically includes the following steps:
s401, acquiring night light remote sensing data closest to a rainfall forecast period, estimating the sewage discharge amount of each residential area of a city closest to the rainfall forecast period based on the position and range information of each residential area estimated before, mapping the data to a grid R, and recording the data as an input dimension layer PI _ 1;
s402, forecasting catchment area and catchment amount by utilizing rainfall forecast data and combining with a potential rainwater catchment area evaluated by DEM data, respectively mapping the forecasted catchment area and catchment amount data to a grid R based on the geographic information of the potential catchment area, and respectively recording the data as an input dimensional layer PI _2 and an input dimensional layer PI _ 3;
s403, based on the urban residential area combined drainage system model constructed in the step S3, taking input dimension layers PI _1, PI _2 and PI _3 as model input quantities to obtain water quantity prediction conditions of each district pipe network, an intercepting well, a regulation and storage tank and a sewage plant;
s404, judging whether the prediction result influences the normal operation of each drainage facility in the potential rainfall period according to the full-load water volume setting of a pipe network, an intercepting well, a regulation and storage tank and a sewage plant, and carrying out scheduling work of water stored in the drainage facility before rainfall according to the condition; for areas with serious overflow pollution, related facilities for storing water and draining water are erected on the ground in advance to deal with emergencies.
The embodiment is as follows:
fig. 1 is a flow chart framework of a method for predicting water load of an urban combined drainage system based on remote sensing technology, which is implemented by the invention, and comprises the following steps S1 to S4:
s1, the sewage discharge amount of urban residential areas is indirectly estimated by multi-source satellite remote sensing data, the range of the urban residential areas is determined by multi-spectral remote sensing data, a sky map and Gaode map information data, the population intensity of each residential area is estimated by night light remote sensing data, and the sewage discharge amount of each residential area in the city is estimated by combining the per-capita sewage discharge experience value, specifically:
s1-1, carrying out preprocessing operations such as splicing, correcting, projection conversion and cloud removal on the multispectral remote sensing data and the night light remote sensing data;
s1-2 multispectral remote sensing data can adopt data with resolution of meter level to meter level such as Landsat-8, high-resolution trains and the like, surface buildings are classified and extracted, roads, greenbelts, bare lands, vegetation, house buildings and the like are classified, grids related to the house buildings are marked, and positions and ranges of residential areas of the house buildings are further marked by combining residential area marking information such as a sky map and a Gaode map;
the remote sensing data of the lamplight at night of S1-3 can adopt DMSP OLS, NPP VIIRS and Lopa I data, the lamplight intensity value Li in each residential area range marked by S101 is counted and recorded in the corresponding grid;
s1-4, dividing each district boundary given by the relevant department, counting the sum of the light intensity values of each residential area in the district, estimating the population density of the residential area by combining the population number of the residential area and the light intensity value Li of each residential area, and estimating the sewage discharge amount of the residential area by combining the per-capita sewage discharge experience value, wherein the formula is as follows:
Pi＝Li/(L1+L2+......+Ln)×Dc×E
wherein Pi is the sewage discharge amount of a residential area i, Li is the light intensity value of the residential area i, (L1+ L2+. 9.. once. + Ln) is the sum of the light intensity values of a parcel c, Dc is the total population of the parcel c, and E is the average sewage discharge amount of people (which can be indirectly determined according to the ratio of the total daily average domestic sewage discharge amount of the city to the total population of the city in the last year);
s2, utilizing DEM data to judge the urban rainfall potential road surface catchment area, evaluating the urban rainfall spatial distribution condition by combining the urban rainfall data per hour, and estimating the rainfall catchment area and catchment quantity of the potential catchment area, specifically:
s2-1 DEM data can adopt GDEMV, SRTM and other series of digital elevation data, DEM data provided by provinces and cities are fused for correction, an ArcGIS Hydrology module is used for carrying out catchment analysis on the corrected DEM data, and potential road surface catchment grids are judged;
the rainfall data of S2-2 can adopt hourly observation data of a Chinese ground meteorological station, fusion analysis products (including rainfall data) of longitude and latitude grids such as CLDAS-V2.0 and the like, weather radar data and the like, and the rainfall data corresponding to the catchment grid of S201 is subjected to statistical analysis to obtain the rainfall catchment area and the catchment amount of a catchment area;
s2-3, according to the selected DEM data and the mesh and spatial resolution of the rainfall data, forming a uniform mapping mesh R, wherein the spatial resolution of the mesh R at least reaches meter level to decimeter level.
S3 model of urban residential area combined drainage system, which mainly comprises the steps of mapping the sewage discharge of urban residential areas, the rainfall catchment area of catchment areas and the catchment amount to a unified grid R, mapping the corresponding district pipe network, intercepting well, storage tank and sewage plant water amount monitoring data to the unified grid, setting model parameters, constructing the model, training and debugging the model and the like, and specifically comprises the following steps:
s3-1, as shown in figure 2, mapping sewage discharge W of each residential area of the city to a uniform grid R according to the extracted longitude and latitude information of the centers of the residential areas and the grid marks of the residential areas; according to the catchment area grid evaluated by DEM data, respectively mapping the estimated catchment area rainfall catchment area S and catchment amount V to a uniform grid R;
s3-2, as shown in FIG. 3, respectively mapping water volume monitoring data G, J, T, C corresponding to a pipe network, an intercepting well, a regulation and storage pool and a sewage plant in a rainfall period to a unified grid R according to pipe network line geographic information, intercepting well point location information, regulation and storage pool point location information and sewage plant point location information;
s3-3 performs normalization processing on the data mapped to the unified grid R. And recording the normalized data as an input layer MI _1 (sewage discharge amount of urban residential areas), MI _2 (water collection area of rainfall catchments on road surfaces), MI _3 (water collection amount of rainfall catchments on road surfaces), an output layer MO _1 (water amount monitored by a pipe network), MO _2 (water amount monitored by an intercepting well), MO _3 (water amount monitored by an adjusting and storing pool) and MO _4 (water amount monitored by the inflow of sewage plants). Normalization can avoid the situations of slow network convergence and low training efficiency caused by overlarge data range as much as possible; the normalization can make different data action effects tend to be consistent, the data with a larger numerical range generally has larger network action, and the normalization can reduce the system error; since the value range of the network output layer activation function is limited, the target (output) data of the network training needs to be mapped to the equivalent value range. The model respectively normalizes sewage discharge W, catchment area S, catchment volume V, pipe network monitoring water yield G, vatch basin monitoring water yield J, regulation and storage pool monitoring water yield T, sewage plant intake monitoring water yield C of each residential area in the city, and the concrete formula is as follows:
x'＝(y1-y2)×[(x-xmin)/(x-xmax)]+y2
wherein x' and x represent the normalized data, raw data, y1、y2Respectively, represent normalized interval ranges, y1＝1,y 20 represents the maximum value and the minimum value of the original data, respectively.
In the data normalization process, the model records mapping information in the form of a structural body, including the maximum value x of the original datamaxAnd minimum value xminDifference xrangeNormalized data interval, maximum value y1Minimum value y2The difference yrangeOriginal data x versus y2Offset value x ofoffsetAnd y israngeAnd xrangeThe ratio gain. According to the mapping information recorded by the structure body, the output data of the model can be reversely normalized to the original data.
S3-4, as shown in Table 1, relevant training parameters of the deep learning-based urban residential area flow control drainage system model are set, wherein the relevant training parameters comprise a data distribution mode, a training function, performance evaluation, iteration times, a performance target, a minimum performance gradient, a maximum adaptation factor, validation failure times, an initial learning rate, a hidden layer activation function and an output layer activation function.
TABLE 1 model training parameter examples
| Parameter name | Parameter setting |
| Data distribution mode | Random |
| Training function | Levenberg-Marquardt algorithm |
| Evaluation of Properties | Mean square error |
| Number of |
5000 |
| Performance objectives | 0.01 |
| |
1×10-5 |
| |
1×1010 |
| Number of failures of |
10 |
| Initial learning rate | 0.01 |
| Hidden layer activation function | Tan-Sigmoid |
| Output layer activation function | Log-Sigmoid |
S3-5 is a frame diagram of the model as shown in FIG. 4, the input layer is sewage discharge W (MI _1), catchment area S (MI _2) and catchment V (MI _3) of each residential area of the city after being mapped to the unified grid and normalized, and the output layer (namely the target layer) is pipe network detection water G (MO _1), catch basin monitoring water J (MO _2), storage tank monitoring water T (MO _3) and sewage plant inlet monitoring water C (MO _4) after being mapped to the unified grid and normalized; based on a deep learning mode, the model comprises a plurality of hidden layers (3 layers and more), wherein each hidden layer comprises a plurality of neurons; according to the parameter example of the step S304, carrying out model construction;
s3-6 is an exemplary diagram of a model running window as shown in fig. 5, where as shown in the diagram, when a Progress bar arrives at any Progress bar in a Progress bar (Progress), it indicates that the training is finished, it needs to be noted that the training is finished, and it does not indicate that the model has completed the best fitting, and if the training is abnormally finished, it indicates that the model has not completely fitted or has been involved in fitting. The model is normally constructed according to the standard that the number of Validation failures (Validation Checks) reaches a set value and training is finished, and the model under the condition has a good training effect. If the validation failure times are set to 10 times in this example, the mean square error representing the model calculation needs to be checked for at least 10 times continuously and then does not decrease, and if the mean square error remains unchanged or does not decrease, it indicates that the model fitting error is not reduced, that is, the best training effect is achieved, the iteration should be stopped, and if the iteration is continued, the model will fall into an overfitting state.
As shown in fig. 6, in the example, the model training is finished after the 52 th iteration, and the reason for finishing is that the requirement that the number of times of the validation failures is 10 is met, that is, the green progress bar in fig. 5 is finished, which indicates that the model training is normally finished. Figure 7 is an example of the number of mean square error checks in training. As illustrated in the example of FIG. 7, the model begins the test at iteration 43 and completes the test at iteration 52. The result shows that the model meets the condition that the mean square error of continuous 10 iterations is kept unchanged or does not decline any more, and the model training is completed normally. It should be noted that the initial learning rate setting of the model construction is important, and if the initial learning rate setting is proper, the mean square error will rapidly decrease and no shock will occur in the initial stage of iteration, as shown in the example of fig. 7, which indicates that the initial learning rate setting of the model is proper.
S3-7, because of randomness existing in single model training, the model of the urban residential area combined drainage system can be constructed by taking the ensemble average of multiple times of model training as a final result.
S4 forecasting water quantity load of the combined system drainage system in the urban residential area, wherein the forecasting contents are the water quantity of a corresponding district pipe network, the water quantity of a intercepting well, the water quantity of a regulating storage tank and the water inlet quantity of a sewage plant, and the forecasting contents specifically comprise the following steps:
s4-1, acquiring sewage discharge amount of each residential area of a city in a corresponding period according to related operations of S1 by adopting city light remote sensing data closest to a rainfall forecast period, mapping the sewage discharge amount to a unified grid R, and performing normalization processing to record the sewage discharge amount as an input layer PI _ 1;
s4-2, rainfall forecast data such as GRAPES _ MESO China and peripheral area numerical forecast products are adopted, a city rainfall potential road surface catchment area evaluated by combining DEM data is combined, rainfall catchment area and catchment amount of the catchment area are estimated, and are respectively mapped to a unified grid R for normalization treatment and are respectively marked as an input layer PI _2 and a PI _ 3;
s4-3, based on the urban residential area combined flow system drainage system model constructed by S3, obtaining prediction data (PO _1, PO _2, PO _3 and PO _4) of the inflow water quantity of the pipe network, the intercepting well, the storage tank and the sewage plant in the grid R by taking PI _1, PI _2 and PI _3 as input layer input models, and performing inverse normalization on the prediction data of the inflow water quantity to original data according to mapping information recorded by an S3 structural body to obtain the prediction conditions of the inflow water quantity load of the pipe network, the intercepting well, the storage tank and the sewage plant corresponding to the potential rainfall period of the segment;
s4-4, according to the setting of full-load water quantity of a pipe network, an intercepting well, a regulation and storage pool, a sewage plant and the like, judging whether the prediction result influences the normal operation of each drainage facility in the potential rainfall period, and carrying out scheduling work of water storage in the drainage facility before rainfall according to the situation; for areas with serious overflow pollution, related facilities for storing water and draining water are erected on the ground in advance to deal with emergencies.
The above-described embodiments are merely preferred embodiments of the present invention, and should not be construed as limiting the present invention, and features in the embodiments and examples in the present application may be arbitrarily combined with each other without conflict. The protection scope of the present invention is defined by the claims, and includes equivalents of technical features of the claims. I.e., equivalent alterations and modifications within the scope hereof, are also intended to be within the scope of this invention.
Claims (8)
1. A method for predicting water load of an urban combined drainage system based on a remote sensing technology is characterized by comprising the following steps: the method comprises the following steps:
s1, indirectly estimating the sewage discharge amount of the urban residential area by using multi-source satellite remote sensing data and combining the data of the sky map and the Gaode map;
s2, estimating rainfall catchment area and catchment amount of the potential road surface catchment area by using DEM data and city-level rainfall data, and forming a unified mapping geographic space grid R according to the DEM data and the rainfall data;
s3, respectively mapping sewage discharge, rainfall catchment area and catchment amount of each residential area of a city to a unified grid R as input, respectively mapping water amount monitoring data of each residential area combined drainage system pipe network, a cutoff well, a regulation and storage pool and a sewage plant to the unified grid R as output according to pipe network line information and point location geographic information, and constructing a city residential area combined drainage system model by using a deep learning mode;
s4, based on the constructed urban residential area combined flow system drainage system model, combining the latest multi-source satellite remote sensing data, rainfall forecast data and DEM data estimation results, predicting the water volume load conditions of each area pipe network, the intercepting well, the storage tank and the sewage plant in the potential rainfall period, and carrying out early warning work.
2. The method for predicting the water load of the urban combined drainage system based on the remote sensing technology according to claim 1, wherein the method comprises the following steps: the specific process of estimating the sewage discharge amount of the urban residential area in the step S1 is as follows:
the urban surface earth buildings are preliminarily divided through multispectral remote sensing data, the range of urban residential areas is determined by combining data refinement of a sky map and a Gaode map, the population density of each residential area of an urban is estimated by combining light intensity fed back by night light remote sensing data and the population number of area statistics, and the sewage discharge amount of the urban residential areas is indirectly estimated according to the per-person sewage discharge empirical value.
3. The method for predicting the water load of the urban combined drainage system based on the remote sensing technology according to claim 2, characterized by comprising the following steps: the step S1 specifically includes the following steps:
s101, carrying out batch preprocessing on the remote sensing data by utilizing Envi, ArcGIS and Python, wherein the batch preprocessing comprises splicing, correcting, projection conversion and cloud removing;
s102, dividing each urban area based on multispectral remote sensing data, extracting urban ground building information, and further subdividing the extracted building information to obtain an urban residential area range based on urban residential area point location information marked by a sky map and a Gaode map;
s103, obtaining light intensity values in all residential area ranges of the city based on night light remote sensing data, estimating population density of the residential area according to the population number counted by the residential area, and indirectly estimating sewage discharge, wherein the formula is as follows:
Pi＝Li/(L1+L2+......+Ln)×Dc×E
wherein Pi is the sewage discharge amount of the residential area i, Li is the light intensity value of the residential area i, (L1+ L2+ -. once. - + Ln) is the sum of the light intensity values of the parcel c, Dc is the total population of the parcel c, and E is the average sewage discharge amount of people.
4. The method for predicting the water load of the urban combined drainage system based on the remote sensing technology according to claim 1, wherein the method comprises the following steps: the step S2 specifically includes: the method comprises the steps of judging a potential rainfall road surface catchment area of the city by utilizing DEM data, marking catchment area grids, evaluating the spatial distribution condition of the rainfall of the city by combining rainfall data of the city level per hour, and estimating the rainfall catchment area and the rainfall catchment amount of the potential catchment area.
5. The method for predicting the water load of the urban combined drainage system based on the remote sensing technology according to claim 1, wherein the method comprises the following steps: the specific process of constructing the urban residential district combined drainage system model in the step S3 is as follows:
taking the estimated sewage discharge amount of each residential area of a city and the rainfall catchment area and catchment amount of a catchment area as model input quantities, and taking the integrated water quantity monitoring data of each district pipe network, the intercepting well, the storage tank and the sewage plant in the corresponding rainfall period as model output quantities; respectively mapping each input quantity and each output quantity to a unified geographic space grid R according to multi-source satellite remote sensing data, rainfall data, DEM data geographic information, pipe network line information of each block, intercepting well point location information, storage tank point location information and sewage plant point location information, and inputting the models; and establishing a potential relation between input quantity and output quantity by using a deep learning mode, and establishing a city residential area combined drainage system model.
6. The method for predicting the water load of the urban combined drainage system based on the remote sensing technology according to claim 5, wherein the method comprises the following steps: the step S3 specifically includes the following steps:
s301, taking sewage discharge amount, rainwater catchment areas, catchment areas and water catchment amount data of urban residential areas as model input amounts, taking water amount monitoring data of a combined drainage system pipe network, a cutoff well, a regulation and storage pool and a sewage plant of each area as model output amounts, and considering dimension difference of each variable, standardizing data dimensions by the model in a form of mapping to a unified geographic space grid;
s302, determining a unified geographic space grid (500 x 500 matrix dimensions, 30m spatial resolution scale) by using the DEM data and the urban rainfall data, and recording as a grid R;
s303, mapping the sewage discharge amount W of each residential area of the city estimated in the corresponding rainfall period to a grid R based on the position and range of each residential area extracted by the remote sensing data, and recording as an input dimensional layer MI _ 1;
s304, respectively mapping catchment area S and catchment quantity V data to a grid R based on the evaluated rainwater catchment area information, and respectively recording the catchment area S and the catchment quantity V data as an input dimension layer MI _2 and an input dimension layer MI _ 3;
s305, mapping corresponding monitoring water volume data to a grid R respectively based on the pipe network line information of each district and the information of the intercepting well, the storage regulation pool and the sewage plant point location, and recording the corresponding monitoring water volume data as an output dimension layer MO _1, an output dimension layer MO _2, an output dimension layer MO _3 and an output dimension layer MO _4 respectively;
s306, constructing a city residential area combined flow and drainage system model by taking the input dimension layers MI _1, MI _2 and MI _3 as model input data and the output dimension layers MO _1, MO _2, MO _3 and MO _4 as model output (target) data.
7. The method for predicting the water load of the urban combined drainage system based on the remote sensing technology according to claim 1, wherein the method comprises the following steps: the specific process of predicting the water volume load of each district pipe network, the intercepting well, the storage tank and the sewage plant in the potential rainfall period in the step S4 is as follows:
estimating population density of urban residential areas according to updated multi-source satellite remote sensing data (multispectral remote sensing data and night light remote sensing data), indirectly estimating sewage discharge of the urban residential areas closest to a rainfall forecast period, mapping the sewage discharge to a uniform grid R and using the uniform grid R as input quantity; according to the DEM data and the rainfall forecast data, the rainfall catchment area and the catchment amount of the potential catchment area are estimated, and the area and the catchment amount are mapped to the unified grid R and serve as input quantities; based on the constructed urban residential area combined drainage system model, the forecasting conditions of water volume loads of each district pipe network, the intercepting well, the regulating and storing pool and the sewage plant in the potential rainfall period are obtained, and scheduling of water stored in drainage facilities and emergency preparation early warning work of a potential overflow pollution area are carried out.
8. The method for predicting the water load of the urban combined drainage system based on the remote sensing technology according to claim 7, wherein the method comprises the following steps: the step S4 specifically includes the following steps:
s401, acquiring night light remote sensing data closest to a rainfall forecast period, estimating the sewage discharge amount of each residential area of a city closest to the rainfall forecast period based on the position and range information of each residential area estimated before, mapping the data to a grid R, and recording the data as an input dimension layer PI _ 1;
s402, forecasting catchment area and catchment amount by utilizing rainfall forecast data and combining with a potential rainwater catchment area evaluated by DEM data, respectively mapping the forecasted catchment area and catchment amount data to a grid R based on the geographic information of the potential catchment area, and respectively recording the data as an input dimensional layer PI _2 and an input dimensional layer PI _ 3;
s403, based on the urban residential area combined drainage system model constructed in the step S3, taking input dimension layers PI _1, PI _2 and PI _3 as model input quantities to obtain water quantity prediction conditions of each district pipe network, the intercepting well, the storage tank and the sewage plant;
s404, judging whether the prediction result influences the normal operation of each drainage facility in the potential rainfall period according to the full-load water volume setting of a pipe network, an intercepting well, a regulation and storage tank and a sewage plant, and carrying out scheduling work of water stored in the drainage facility before rainfall according to the condition; for areas with serious overflow pollution, related facilities for storing water and draining water are erected on the ground in advance to deal with emergencies.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210129309.5A CN114611756A (en) | 2022-02-11 | 2022-02-11 | Urban combined drainage system water quantity load prediction method based on remote sensing technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210129309.5A CN114611756A (en) | 2022-02-11 | 2022-02-11 | Urban combined drainage system water quantity load prediction method based on remote sensing technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114611756A true CN114611756A (en) | 2022-06-10 |
Family
ID=81859928
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210129309.5A Pending CN114611756A (en) | 2022-02-11 | 2022-02-11 | Urban combined drainage system water quantity load prediction method based on remote sensing technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114611756A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115577506A (en) * | 2022-09-22 | 2023-01-06 | 长江生态环保集团有限公司 | Method for pre-diagnosing and accurately troubleshooting problems of sewage pipe network |
| CN116091941A (en) * | 2023-01-18 | 2023-05-09 | 生态环境部卫星环境应用中心 | Method and device for rapidly checking life non-point source pollution load of drinking water source protection area |
| CN116084529A (en) * | 2022-11-30 | 2023-05-09 | 广东省建筑设计研究院有限公司 | Sponge airport structure for summer-heat winter-heat weather area |
| CN116402291A (en) * | 2023-03-22 | 2023-07-07 | 深圳市深圳河湾流域管理中心 | Method and system for overall scheduling of sewage in river basin of river |
-
2022
- 2022-02-11 CN CN202210129309.5A patent/CN114611756A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115577506A (en) * | 2022-09-22 | 2023-01-06 | 长江生态环保集团有限公司 | Method for pre-diagnosing and accurately troubleshooting problems of sewage pipe network |
| CN115577506B (en) * | 2022-09-22 | 2023-08-25 | 长江生态环保集团有限公司 | Method for pre-diagnosing and accurately checking problems of sewage pipe network |
| CN116084529A (en) * | 2022-11-30 | 2023-05-09 | 广东省建筑设计研究院有限公司 | Sponge airport structure for summer-heat winter-heat weather area |
| CN116084529B (en) * | 2022-11-30 | 2023-10-27 | 广东省建筑设计研究院有限公司 | Sponge airport structure for summer-heat winter-heat weather area |
| CN116091941A (en) * | 2023-01-18 | 2023-05-09 | 生态环境部卫星环境应用中心 | Method and device for rapidly checking life non-point source pollution load of drinking water source protection area |
| CN116091941B (en) * | 2023-01-18 | 2023-10-27 | 生态环境部卫星环境应用中心 | Method and device for rapidly checking life non-point source pollution load of drinking water source protection area |
| CN116402291A (en) * | 2023-03-22 | 2023-07-07 | 深圳市深圳河湾流域管理中心 | Method and system for overall scheduling of sewage in river basin of river |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Apreda et al. | A climate vulnerability and impact assessment model for complex urban systems | |
| CN114611756A (en) | Urban combined drainage system water quantity load prediction method based on remote sensing technology | |
| Yang et al. | Understanding land surface temperature impact factors based on local climate zones | |
| CN110852577B (en) | Urban flood assessment method based on urban toughness and urban watershed hydrologic model | |
| CN110633865A (en) | Urban ponding prediction and safety early warning system based on drainage model | |
| Campisano et al. | Selecting time scale resolution to evaluate water saving and retention potential of rainwater harvesting tanks | |
| KR102073768B1 (en) | Drought information supply system based on portal | |
| CN114240119A (en) | Digital twin-based flood control and waterlogging prevention system and early warning method for whole elements of territorial universe | |
| CN110276145A (en) | Sewerage system simulation modeling and dispatching method | |
| CN105046445A (en) | Flood prevention dispatching decision support system | |
| CN107316095A (en) | A kind of region meteorological drought grade prediction technique for coupling multi-source data | |
| CN112506994B (en) | Power equipment flood hidden danger point monitoring and early warning method and related device | |
| KR101383617B1 (en) | Method and apparatus for predicting daily solar radiation level | |
| CN110274656B (en) | Urban inland river water level forecasting and early warning method | |
| CN116611333B (en) | Urban flood risk point prediction method | |
| CN112052561A (en) | Method for formulating waterlogging prevention emergency plan of drainage system | |
| Zheng et al. | Mapping the spatial distribution of nocturnal urban heat island based on Local Climate Zone framework | |
| CN116227362A (en) | Municipal drainage pipe network state prediction method based on graph and deep learning | |
| CN115689168A (en) | Accumulated water emergency scheduling method based on accumulated water prediction | |
| CN116029460A (en) | Municipal construction engineering water conservation management platform based on big data | |
| CN113222368B (en) | Rainfall flood early warning method based on rainwater garden monitoring data | |
| CN106651040A (en) | Optimal layout method of urban waterlogging monitoring points | |
| CN110633674A (en) | Rainwater heading uncertainty analysis method and system based on remote sensing image and rainfall monitoring data | |
| Hamidi et al. | Uncertainty analysis of urban sewer system using spatial simulation of radar rainfall fields: New York City case study | |
| CN110414027A (en) | A kind of data processing method suitable for flood forecasting system |
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 |