CN117010726B - Intelligent early warning method and system for urban flood control - Google Patents
Intelligent early warning method and system for urban flood control Download PDFInfo
- Publication number
- CN117010726B CN117010726B CN202311276139.4A CN202311276139A CN117010726B CN 117010726 B CN117010726 B CN 117010726B CN 202311276139 A CN202311276139 A CN 202311276139A CN 117010726 B CN117010726 B CN 117010726B
- Authority
- CN
- China
- Prior art keywords
- rainfall
- flood
- data
- urban
- urban flood
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 98
- 238000011160 research Methods 0.000 claims abstract description 73
- 238000004458 analytical method Methods 0.000 claims abstract description 55
- 238000013507 mapping Methods 0.000 claims abstract description 34
- 238000004088 simulation Methods 0.000 claims abstract description 15
- 238000010219 correlation analysis Methods 0.000 claims abstract description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 41
- 230000008859 change Effects 0.000 claims description 30
- 230000035772 mutation Effects 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 20
- 238000009826 distribution Methods 0.000 claims description 16
- 230000001186 cumulative effect Effects 0.000 claims description 8
- 230000000630 rising effect Effects 0.000 claims description 7
- 239000002689 soil Substances 0.000 claims description 7
- 239000003550 marker Substances 0.000 claims description 6
- 238000010998 test method Methods 0.000 claims description 6
- 238000003556 assay Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 5
- 238000012300 Sequence Analysis Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000012098 association analyses Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 11
- 230000000875 corresponding effect Effects 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 8
- 230000007246 mechanism Effects 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 5
- 238000013499 data model Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000002265 prevention Effects 0.000 description 4
- 238000013179 statistical model Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000006424 Flood reaction Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000000692 Student's t-test Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000005293 physical law Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000008566 social perception Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012353 t test Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent early warning method and system for urban flood control, comprising the following steps: determining a research area range and acquiring research data; extracting historical rainfall data to obtain rainfall characteristics to form a rainfall characteristic set; analyzing rainfall data by adopting a trend analysis method, and dividing the rainfall data into at least two time periods; extracting urban flood data and urban flood features to form an urban flood feature set; building a correlation analysis model of rainfall and urban flood, calculating the correlation of the rainfall and the urban flood, and arranging the rainfall and the urban flood in a descending order; constructing an early warning measure set aiming at each urban flood to form a rainfall and early warning measure mapping relation of a research area; and constructing a hydrologic hydrodynamic model, calibrating based on research data, taking current actually measured rainfall and urban flood data as input data, performing simulation and prediction, giving intelligent early warning information and early warning measures, and pushing to each terminal. The invention greatly improves the forecasting precision and sensitivity.
Description
Technical Field
The invention belongs to flood forecasting technology, and particularly relates to an intelligent early warning method and system for urban flood control.
Background
The flood forecasting and early warning refers to a process of forecasting hydrologic elements (such as river water level, flow, flood peak arrival time and the like) of a certain place or area in a certain future time by utilizing a mathematical model or a statistical method according to known or forecasted hydrologic weather conditions such as rainfall, snow melting, soil humidity and the like. Flood forecast is an important basis for flood prevention and drought resistance work, and is also a basic technology in the fields of water resource management, hydraulic engineering operation, ecological environment protection and the like. At present, flood forecasting mainly comprises two types of methods: a deterministic model based on physical mechanisms and an empirical statistical model based on data relationships.
Firstly, a deterministic model based on a physical mechanism is a mathematical model established according to the physical laws of a river basin confluence process and a river channel fluctuation process, and the processes of flood occurrence, flood development and flood regression are simulated by solving a control equation and boundary conditions. The model can reflect the influence of various factors in a flow field on the flood process, has strong physical significance and adaptability, but also has some problems such as more parameters, difficult determination, larger calculated amount, difficult real-time application, higher data requirement, difficult satisfaction and the like. And secondly, an empirical statistical model based on the data relationship is used for analyzing the statistical relationship between the flood process and various factors according to historical observation data and establishing a corresponding mathematical expression or probability distribution function for predicting the flood situation possibly happening in the future. The model can fully utilize the existing data, simplify the calculation process and improve the forecasting efficiency, but has problems such as lack of generality and stability, high requirements on data quality and quantity and the like, and cannot reflect the physical mechanism of various factors in the flow domain to the flood process. And along with the development and application of new technologies such as big data, artificial intelligence and the like, new ideas and means are provided for flood forecasting. Artificial intelligence is a technology for making a machine have intelligent behaviors, wherein machine learning is one of core technologies of artificial intelligence, and mainly performs tasks such as classification, regression, clustering and the like by making the machine autonomously learn rules contained in data and utilizing the rules. The machine learning can process massive, complex and nonlinear data, and has the advantages of high efficiency, stability, objectivity and the like. At present, good application effects are obtained in aspects of weather disaster identification prediction, weather index classification, weather forecast prediction and the like. The machine learning is applied to flood forecasting and early warning, so that the limitation of the traditional method can be overcome, and the forecasting precision and sensitivity can be improved. However, machine learning lacks sufficient interpretability and cannot reflect the actual physical mechanism and principle, and meanwhile, has high requirements on data quality and quantity, and has problems on data quality, so that reliability and robustness are reduced.
Finally, for urban flood control, the prediction in time and space is higher in precision and speed, and the current prediction method is difficult to meet the requirements. There is therefore a need to develop innovations providing new solutions.
Disclosure of Invention
The application aims to: an intelligent early warning method for urban flood control is provided to solve the above problems in the prior art. And further provides an intelligent early warning system for urban flood control so as to realize the method.
Technical proposal
According to one aspect of the application, an intelligent early warning method for urban flood control comprises the following steps:
s1, determining a range of a research area, and acquiring research data;
s2, extracting historical rainfall data from the research data to obtain rainfall characteristics to form a rainfall characteristic set; analyzing rainfall data by adopting a trend analysis method, and dividing the rainfall data into at least two time periods;
step S3, urban flood data are extracted from the research data, and urban flood features are extracted to form an urban flood feature set; analyzing urban flood by adopting a trend analysis method;
s4, constructing a correlation analysis model of rainfall and urban flood, calculating the correlation of the rainfall and the urban flood according to each rainfall and urban flood based on the rainfall data and the urban flood data, and arranging the rainfall and the urban flood in a descending order;
Step S5, constructing an early warning measure set aiming at each urban flood to form a rainfall and early warning measure mapping relation of a research area;
and S6, constructing a hydrologic hydrodynamic model, calibrating based on research data, taking current actually measured rainfall and urban flood data as input data, performing simulation and prediction, giving intelligent early warning information and early warning measures, and pushing to each terminal.
According to one aspect of the present application, the step S1 is further:
s11, acquiring research data of a river basin where a city is located, wherein the research data at least comprises a digital elevation model, gradient, flow direction, flow, drainage pipe network parameters, rainfall data and urban flood data;
step S12, acquiring a first boundary and a second boundary based on a digital elevation model, wherein the first boundary is a river basin boundary of a river basin where the city is located; the second boundary is a city flood control area boundary; the second boundary is included in the first boundary;
step S13, rasterizing the research area, extracting key areas in the second boundary based on the flood control target, searching grids corresponding to the key areas for each key area, and constructing a key grid set;
and S14, extracting urban water network structures based on the digital elevation model, and extracting water network and confluence data of key areas one by one.
According to one aspect of the present application, the step S2 further includes:
s21, extracting historical rainfall data from the research data, and obtaining rainfall characteristics including a rainfall center, a rainfall radius, a maximum N-day rainfall, a rainfall days and an accumulated rainfall from the rainfall data; wherein N is 1, 3, 5, 7;
s22, constructing a trend analysis method set, wherein the trend analysis method at least comprises an MK test method and a Sen' S slope method;
s23, trend detection is carried out one by adopting a trend analysis method;
the MK assay process includes: firstly, calculating the difference value of the rainfall of each pair of years, and endowing a sign value with a sign; calculating the cumulative symbol value of each year and calculating the sum, variance, standard deviation and standardized statistic; judging whether a significant trend exists or not based on a comparison result of the standardized statistic and the threshold value; searching rainfall mutation points by adopting a dichotomy method,
and step S24, dividing rainfall data into at least two time periods based on the rainfall abrupt change points.
According to one aspect of the present application, the step S3 is further:
step S31, urban flood data are extracted from research data, urban flood characteristics are collected and form an urban flood characteristic set, wherein the urban flood characteristics at least comprise a flooding range, a flooding time, a flooding depth, a total flood amount, a flood duration, a flood peak flow, a peak time, a rising flow and a peak section flood;
S32, constructing a trend analysis method set, wherein the trend analysis method at least comprises an MK (marker for marker) test method and a moving average method;
the trend analysis process by using the moving average method comprises the following steps: obtaining urban flood data, constructing a flood time sequence, selecting a proper time window length, and calculating a moving average value of each period according to the time window length; drawing a smooth curve according to the moving average value, observing the change trend of the curve, and judging whether a significant rising or falling trend exists or not; calculating residual errors according to the moving average value and the original data, namely, the difference value between the moving average value and the original data, judging whether flood mutation points exist or not according to the absolute value or standard deviation of the residual errors, and determining the positions of the flood mutation points;
the moving average value comprises a simple moving average value SMA and an exponential moving average value EMA, wherein the simple moving average value SMA refers to the arithmetic average value of data in each period in a time window; the index moving average EMA refers to that the data in each period in a time window are weighted and averaged according to the index weight;
and step S33, urban flood is staged based on the condition of the flood mutation points.
According to one aspect of the present application, the step S4 is further:
s41, constructing a correlation analysis model of rainfall and urban flood, wherein the correlation analysis model at least comprises a rainfall distribution analysis unit;
Step S42, aiming at each rainfall in each period, searching an affected key area according to the track of a rainfall center and the rainfall radius; establishing a mapping relation between rainfall and key areas;
step S43, aiming at each flood in each period, searching the association relation between the flood in each key area and each rainfall in the preset time, establishing a mapping set between the urban flood in each key area and the associated rainfall, calculating the contribution degree of each rainfall to the urban flood in the key area, and arranging in descending order; obtaining the correlation between each city flood and each rainfall;
and S44, carrying out association analysis on the correlation of urban flood and rainfall based on the water network structural relationship among key areas.
According to one aspect of the present application, the step S5 is further:
s51, constructing an early warning measure total set;
step S52, establishing flood classification standards, and classifying each flood;
and step S53, forming a pre-warning measure set corresponding to the type of flood according to the type of flood, and forming a mapping relation between each type of flood and pre-warning measures in the research area.
According to one aspect of the present application, the step S6 is further:
Step S61, acquiring research data and preprocessing to enable the research data to meet the requirements of a hydrographic hydrodynamic model;
step S62, constructing a hydrological hydrodynamic model, and generalizing a water network and a pipe network of a research area by adopting a GIS module; simplifying the pipe network structure and the topological relation;
step S63, dividing the sub-water areas of the research area by using DEM data, and determining parameters of each sub-water area, including area, gradient, soil type, building condition and vegetation coverage;
step S64, carrying out two-dimensional grid division on the research area by adopting a limited volume method, and endowing grid parameters of each grid, including elevation, roughness and boundary conditions;
s65, constructing training input data by adopting a rainfall design method including a same-frequency analysis method, a Chicago method and a heavy rainfall time face depth relation method, and calibrating a hydrological hydrodynamic model;
and step S66, acquiring current actually measured rainfall and urban flood data, performing simulation and prediction as input data, giving intelligent early warning information and early warning measures, and pushing the intelligent early warning information and the early warning measures to each preset terminal.
According to one aspect of the present application, the step S4 further includes:
step S40, labeling flood in the heavy point area based on rainfall abrupt points and flood abrupt points:
Judging whether the number of rainfall abrupt change points and flood abrupt change points exceeds respective threshold values or not respectively;
if yes, clustering is carried out respectively until the number of the rainfall breaking mutation points and the flood mutation points is not higher than a preset threshold value;
if not, acquiring rainfall data and flood data in the latest period;
establishing a mapping relation according to rainfall and flood in the last period, and obtaining a first mapping weight;
and resetting the mapping relation between rainfall and flood in other periods according to the first mapping weight, updating the mapping weight, and checking.
According to an aspect of the present application, the step S42 further includes:
acquiring rainfall data and generating a rasterized rainfall distribution map;
dividing, identifying and positioning rainfall data, extracting a rainfall center, average rainfall and rainfall radius, and converting the rainfall center, the average rainfall and the rainfall radius into position information under a coordinate system;
fitting, predicting and smoothing the position information by using a time sequence analysis method to obtain a movement track of a rainfall center, and judging whether the rainfall intensity changes according to the change condition of the rainfall radius;
and superposing the movement track and the map of the key area by using a Geographic Information System (GIS), analyzing the movement direction, speed and range of the rainfall center, and calculating and evaluating the influence degree of the rainfall center on the heavy flood control area.
According to another aspect of the present application, an intelligent pre-warning system for urban flood control, comprises:
at least one processor; and
a memory communicatively coupled to at least one of the processors; wherein,
the memory stores instructions executable by the processor for execution by the processor to implement the intelligent pre-warning method for urban flood control of any one of the above-described technical schemes.
The beneficial effects are that: the application overcomes the defects existing in the prior art, improves the interpretability and the robustness of machine learning, and simultaneously greatly improves the speed and the accuracy of forecasting and early warning according to the test result of an actual project. Some of the advantages will be described below in connection with specific embodiments.
Drawings
Fig. 1 is a flow chart of the present application.
Fig. 2 is a flowchart of step S1 of the present application.
Fig. 3 is a flow chart of step S2 of the present application.
Fig. 4 is a flowchart of step S3 of the present application.
Fig. 5 is a flowchart of step S4 of the present application.
Fig. 6 is a flowchart of step S5 of the present application.
Fig. 7 is a flowchart of step S6 of the present application.
Detailed Description
As shown in fig. 1, an intelligent early warning method for urban flood control is provided, which comprises the following steps:
S1, determining a range of a research area, and acquiring research data;
s2, extracting historical rainfall data from the research data to obtain rainfall characteristics to form a rainfall characteristic set; analyzing rainfall data by adopting a trend analysis method, and dividing the rainfall data into at least two time periods;
step S3, urban flood data are extracted from the research data, and urban flood features are extracted to form an urban flood feature set; analyzing urban flood by adopting a trend analysis method;
s4, constructing a correlation analysis model of rainfall and urban flood, calculating the correlation of the rainfall and the urban flood according to each rainfall and urban flood based on the rainfall data and the urban flood data, and arranging the rainfall and the urban flood in a descending order;
step S5, constructing an early warning measure set aiming at each urban flood to form a rainfall and early warning measure mapping relation of a research area;
and S6, constructing a hydrologic hydrodynamic model, calibrating based on research data, taking current actually measured rainfall and urban flood data as input data, performing simulation and prediction, giving intelligent early warning information and early warning measures, and pushing to each terminal.
In the embodiment, the relation and the rule between the urban rainfall and the flood are revealed by analyzing the historical change trend of the urban rainfall and the flood, and a reference basis is provided for urban flood control and drainage. By extracting historical rainfall data and urban flood data from the research data and analyzing the historical rainfall data and the urban flood data by adopting a trend analysis method, the change characteristics, space-time distribution, frequency intensity and the like of urban rainfall and flood can be found, and whether a significant rising or falling trend exists or not and whether a mutation point or an abnormal event exists or not can be judged. By calculating the correlation of rainfall and urban flood for each rainfall and urban flood based on the rainfall data and the urban flood data and arranging the rainfall and urban flood in descending order, the rainfall factors affecting the maximum urban flood, such as rainfall intensity, duration time, distribution range and the like, can be found, and the urban flood risks of different degrees can be estimated according to rainfall scenes of different reproduction periods. By constructing an early warning measure set for each city flood, such as cutting off the power supply of low-lying zones, transferring dangerous zone personnel, checking a drainage system, implementing joint arrangement and joint adjustment, and selecting proper early warning measures according to city flood risks of different degrees, casualties and property loss caused by city waterlogging can be effectively reduced. The flow state of rainwater in a pipe network and the surface overflow and ponding forming process can be described by constructing a hydrologic hydrodynamic model and calibrating based on research data, simulation and prediction are carried out according to the current actually measured rainfall and urban flood data as input data, the occurrence, development, fading and other processes of urban waterlogging can be monitored and predicted in real time, intelligent early warning information and early warning measures are given, and the intelligent early warning information and early warning measures are pushed to all terminals.
The scientificity and the accuracy of urban flood control and drainage can be improved, and support is provided for urban planning, construction and management. By utilizing the data analysis and model simulation method, the characteristics, rules, risks and the like of urban rainfall and flood can be more comprehensively and deeply known, scientific basis and accurate information are provided for urban flood control and drainage, so that support is provided for urban planning, construction and management, and the disaster prevention and reduction capability of the city is improved. The real-time performance and the intelligence of urban flood control and drainage are improved, and a guarantee is provided for urban emergency response. By utilizing the data analysis and model simulation method, the urban waterlogging condition can be monitored and predicted more timely and intelligently, and a guarantee is provided for urban emergency response, so that the loss caused by urban waterlogging is reduced, and the urban emergency response capability is improved.
As shown in fig. 2, according to an aspect of the present application, the step S1 is further:
s11, acquiring research data of a river basin where a city is located, wherein the research data at least comprises a digital elevation model, gradient, flow direction, flow, drainage pipe network parameters, rainfall data and urban flood data; research data may be obtained from public data sources such as chinese weather datasets, global precipitation measurement tasks, national geographic information public service platforms, and the like. The data can help analyze the topography, hydrologic hydraulic characteristics, rainfall flood conditions and the like of the basin where the city is located.
Step S12, acquiring a first boundary and a second boundary based on a digital elevation model, wherein the first boundary is a river basin boundary of a river basin where the city is located; the second boundary is a city flood control area boundary; the second boundary is included in the first boundary;
step S13, rasterizing the research area, extracting key areas in the second boundary based on the flood control target, searching grids corresponding to the key areas for each key area, and constructing a key grid set; important areas in the second boundary, such as low-lying zones, water-prone road sections and important facility equipment, can be extracted based on flood control targets; the key grid set can help analyze drainage risks and prevention measures of key areas.
And S14, extracting urban water network structures based on the digital elevation model, and extracting water network and confluence data of key areas one by one. The urban water network structure, including river channels, lakes, drainage pipes and the like, can be extracted based on a digital elevation model by utilizing tools such as GIS and the like, and parameters such as length, width, depth, section shape and the like of each water network element are endowed. The water network and confluence data can help analyze drainage capacity and influencing factors of key areas.
In the present embodiment of the present invention, in the present embodiment,
As shown in fig. 3, according to an aspect of the present application, the step S2 further includes:
s21, extracting historical rainfall data from the research data, and obtaining rainfall characteristics including a rainfall center, a rainfall radius, a maximum N-day rainfall, a rainfall days and an accumulated rainfall from the rainfall data; wherein N is 1, 3, 5, 7;
the rainfall center refers to the area with the largest average rainfall in a certain period. The average rainfall in each period can be calculated by using tools such as GIS and the like according to daily space distribution data, and the area where the maximum value is located is found out.
Radius of rainfall: refers to a circular area with a rainfall center as a center and average rainfall as a radius. The average rainfall of each period can be calculated by using tools such as GIS and the like according to daily space distribution data, and a circular area is drawn by taking the average rainfall as a radius.
The maximum N days of rainfall refers to the maximum value of the accumulated rainfall for N consecutive days in a certain period. The accumulated rainfall for N consecutive days in each period can be calculated according to the accumulated rainfall data per day by using Excel and other tools, and the maximum value is found. Wherein N is 1, 3, 5 or 7.
The number of days of rainfall refers to the number of days in which the daily rainfall is greater than or equal to 0.1 mm in a certain period. The days satisfying the condition in each period can be counted according to daily rainfall data by using an Excel or other tool.
The accumulated rainfall refers to the sum of all daily rainfall in a certain period. The accumulated rainfall for each period can be summed up from daily rainfall data for each day using Excel or other tools.
S22, constructing a trend analysis method set, wherein the trend analysis method at least comprises an MK test method and a Sen' S slope method;
MK assays are methods used to detect whether a time series has a significant trend. The basic idea is to time sequence in time sequence and compare the difference between any two periods and assign sign values according to signs. The cumulative symbol values are then calculated and the sum, variance, standard deviation, and normalized statistic are found. Based on the comparison of the normalized statistics to a threshold (e.g., 1.96), a determination is made as to whether there is a significant trend. If the absolute value of the normalized statistic is greater than the threshold, then a significant trend is considered to exist; if less than the threshold, no significant trend is considered to exist; if equal to the threshold, the trend is considered uncertain. In addition, a dichotomy method can be adopted to find rainfall mutation points, namely, the division point which maximizes the absolute value of the standardized statistic is found out in the time sequence and used as the rainfall mutation time.
The Sen's slope method is a method for estimating the median slope of a time series. The basic idea is to arrange the time series in time sequence, calculate the slope between any two periods, and find the median of all slopes as the median slope of the whole time series. The median slope may reflect an average rate of change of the time series, and if the median slope is greater than zero, then a forward trend is considered to exist; if less than zero, then a negative trend is considered to exist; if equal to zero, the trend is considered unchanged.
S23, trend detection is carried out one by adopting a trend analysis method;
the MK assay process includes: firstly, calculating the difference value of the rainfall of each pair of years, and endowing a sign value with a sign; calculating the cumulative symbol value of each year and calculating the sum, variance, standard deviation and standardized statistic; judging whether a significant trend exists or not based on a comparison result of the standardized statistic and the threshold value; and searching rainfall mutation points by adopting a dichotomy method.
For example, the difference between 2001 and 2000 is-5.6, and the sign value is-1; the difference between 2002 and 2000 is-3.2, and the sign value is-1; and so on, all symbol values are obtained.
The cumulative symbol value in year 2000 is 0; the cumulative sign value in 2001 was-1; the cumulative symbol value in 2002 was-2; and so on, all accumulated symbol values are obtained. The sum was-21, the variance was 105, the standard deviation was 10.25, and the normalized statistic was-2.05. Based on the comparison of the normalized statistics to a threshold (e.g., 1.96), a determination is made as to whether there is a significant trend. Since the absolute value of the normalized statistic is greater than the threshold, there is considered to be a significant negative trend, i.e., the amount of rainfall shows a decreasing trend. And searching rainfall abrupt change points by adopting a dichotomy, namely, searching a dividing point with the maximum absolute value of the standardized statistic in the time sequence, and taking the dividing point as rainfall abrupt change time. For example, the time series is divided into two parts, namely, 2000 to 2010 and 2011 to 2020, and the two parts of the standardized statistics are calculated respectively, and the former half is found to be-2.58 and the latter half is found to be-1.41, so that 2010 is considered as a rainfall mutation point.
And searching rainfall abrupt change points by adopting a dichotomy, namely, searching a dividing point with the maximum absolute value of the standardized statistic in the time sequence, and taking the dividing point as rainfall abrupt change time. For example, the time series is divided into two parts, namely, 2000 to 2010 and 2011 to 2020, and the two parts of the standardized statistics are calculated respectively, and the former half is found to be-2.58 and the latter half is found to be-1.41, so that 2010 is considered as a rainfall mutation point. Since the median slope is less than zero, it is considered that there is a negative trend, i.e., the rainfall shows a decreasing trend.
And step S24, dividing rainfall data into at least two time periods based on the rainfall abrupt change points.
As shown in fig. 4, according to an aspect of the present application, the step S3 is further:
step S31, urban flood data are extracted from the research data, urban flood characteristics are collected and form an urban flood characteristic set, and the urban flood characteristics at least comprise a flooding range, a flooding time, a flooding depth, a total flood amount, a flood duration, a flood peak flow, a peak time, a rising flow and a peak section flood.
To obtain urban flood data, a remote sensing technique or a social sensing technique may be used to monitor and extract flood coverage. The remote sensing technology utilizes images shot by satellites or unmanned aerial vehicles, and identifies water and non-water areas through image processing and analysis methods, so that submerged range and submerged depth are obtained. The social perception technology utilizes information issued by users on social media or other network platforms, and extracts texts or pictures containing flood places through natural language processing and a geographic information system method, so that a flooding range is obtained. Suitable techniques may be selected or used in combination with a variety of techniques to obtain more accurate results, depending on the availability and quality of the data.
To collect urban flood characteristics, a hydrologic site or sensor network may be used to monitor and record parameters such as flow, water level, rainfall, etc. during the flood. These parameters may be estimated or inferred using historical data or statistical models. Depending on the availability and accuracy of the data, a suitable method may be selected or a combination of methods may be used to obtain more complete data.
In order to form the urban flood feature set, the extracted or collected data can be sorted and summarized according to different time scales (such as years, months, days and the like) or space scales (such as drainage basins, areas, streets and the like), so that the urban flood features of different levels are obtained. Suitable dimensions may be selected or a combination of dimensions may be used to obtain more meaningful features, depending on the purpose and requirements of the analysis.
S32, constructing a trend analysis method set, wherein the trend analysis method at least comprises an MK (marker for marker) test method and a moving average method;
the trend analysis process by using the moving average method comprises the following steps: obtaining urban flood data, constructing a flood time sequence, selecting a proper time window length, and calculating a moving average value of each period according to the time window length; drawing a smooth curve according to the moving average value, observing the change trend of the curve, and judging whether a significant rising or falling trend exists or not; calculating residual errors according to the moving average value and the original data, namely, the difference value between the moving average value and the original data, judging whether flood mutation points exist or not according to the absolute value or standard deviation of the residual errors, and determining the positions of the flood mutation points;
The moving average value comprises a simple moving average value SMA and an exponential moving average value EMA, wherein the simple moving average value SMA refers to the arithmetic average value of data in each period in a time window; the index moving average EMA refers to that the data in each period in a time window are weighted and averaged according to the index weight;
in a certain embodiment, firstly, one or more urban flood characteristics are selected as analysis objects, such as annual maximum daily rainfall, annual maximum peak flow and the like; secondly, one or more time scales are selected as analysis units, such as years, seasons, months and the like; then, one or more trend analysis methods such as MK assay and moving average method are selected as the analysis methods; and finally, applying each analysis method on each time scale to each analysis object to obtain a trend analysis result, and comprehensively comparing and evaluating.
And step S33, urban flood is staged based on the condition of the flood mutation points.
In a certain embodiment, one or more mutation detection methods are selected as the analysis methods, such as a cumulative sum method, a sliding t-test method, a Mann-Kendall-Sneyers method, etc.; and applying each analysis method to each analysis object on each time scale to obtain a mutation detection result, and dividing urban flood into different stages according to the positions and the number of mutation points.
As shown in fig. 5, according to an aspect of the present application, the step S4 is further:
s41, constructing a correlation analysis model of rainfall and urban flood, wherein the correlation analysis model at least comprises a rainfall distribution analysis unit; the method can divide a research area into a plurality of grid units according to the space distribution of rainfall data by utilizing tools such as GIS and the like, and calculate the average rainfall, the maximum rainfall, the rainfall frequency and other parameters of each unit to form a rainfall distribution analysis unit. These units can help describe the spatial heterogeneity and law of variation of rainfall.
Step S42, aiming at each rainfall in each period, searching an affected key area according to the track of a rainfall center and the rainfall radius; establishing a mapping relation between rainfall and key areas;
the method can draw the track of each rainfall according to the central position, the moving direction, the moving speed and the radius of each rainfall by utilizing tools such as GIS and the like, superimpose the track with the boundary of the key region, find out the affected key region, record the influence time and the influence degree of each rainfall on each key region and form the mapping relation of each rainfall and the key region. These relationships can help identify the extent and intensity of the impact of different rainfall on different accent areas.
Step S43, aiming at each flood in each period, searching the association relation between the flood in each key area and each rainfall in the preset time, establishing a mapping set between the urban flood in each key area and the associated rainfall, calculating the contribution degree of each rainfall to the urban flood in the key area, and arranging in descending order; obtaining the correlation between each city flood and each rainfall;
and determining all rainfall in a preset time (such as 24 hours before and after) associated with each key area according to the time and duration of the flood generated by each key area by using Excel and other tools, and recording the time difference and the space distance between each flood and each rainfall to form a mapping set between the urban flood of each key area and the associated rainfall. Then, the contribution degree of each rainfall to the urban flood in the key area can be calculated by using correlation analysis or regression analysis and other methods, and the urban flood and each rainfall are ranked according to the contribution degree, so that the correlation between each urban flood and each rainfall is obtained. These correlations can help assess the size and sensitivity of different rainfall to urban flood risks in different key areas.
And S44, carrying out association analysis on the correlation of urban flood and rainfall based on the water network structural relationship among key areas.
And determining the water flow direction and the water flow between the key areas according to the water network structural relations between the key areas, such as river channels, drainage pipe networks, culverts and the like by utilizing tools such as GIS and the like, recording the inflow and the outflow of each key area, and forming a water network structural relation matrix between the key areas. Then, the influence of the water network structure relation between key areas on the correlation of urban flood and rainfall can be analyzed by utilizing methods such as network analysis or system dynamics, and the like, and the correlation of the urban flood and rainfall between the key areas is obtained. These associations may help understand urban flood propagation and diffusion mechanisms and paths between different accent areas.
As shown in fig. 6, according to an aspect of the present application, the step S5 is further:
s51, constructing an early warning measure total set;
analyzing flood characteristics, flood control responsibility, flood control capacity and flood control requirements of a research area, and determining a flood control target and an early warning target; determining the division basis and standard of flood level and early warning level by referring to the related standards and specifications of the country and the place; different early warning information contents, release channels, release opportunities and release frequencies are designed according to flood grades and early warning grades; according to flood level and early warning level, different flood control organization command systems, responsibility division, coordination mechanisms and information communication modes are formulated; according to flood level and early warning level, different personnel transfer evacuation plans, arrangement point setting, material preparation and traffic guarantee measures are formulated; according to the flood level and the early warning level, different engineering facility operation scheduling schemes, operation parameters, operation modes and operation effect evaluation methods are formulated; according to the flood level and the early warning level, different emergency rescue team configuration, rescue material reserve, rescue scheme formulation and rescue effect evaluation methods are formulated.
Step S52, establishing flood classification standards, and classifying each flood;
collecting historical or simulated flood element data of a research area, performing frequency analysis or extremum analysis, and calculating flood element values corresponding to different reproduction periods or possible maximum values; determining a recurring period or a possible maximum range applicable to the study area, and a corresponding flood ranking criterion, with reference to relevant specifications of the country or place; and classifying each field of historic or simulated flood according to flood class classification standards, and counting the occurrence frequency and the duty ratio of each class.
And step S53, forming a pre-warning measure set corresponding to the type of flood according to the type of flood, and forming a mapping relation between each type of flood and pre-warning measures in the research area.
The step of forming the set of pre-warning measures corresponding to the type of flood comprises: analyzing flood type characteristics of a research area, such as occurrence conditions, development rules, influence degree, duration time and the like; according to flood type characteristics, selecting proper early warning measures from the early warning measure total set, such as early warning information content, release time, personnel transfer routes, engineering facility operation modes and the like; and determining the priority and execution sequence of the early warning measures of different types of floods according to the matching degree of the floods and the early warning measures.
The step of forming the mapping relation between each type of flood and the pre-warning measures in the research area comprises the following steps: establishing a two-dimensional table, wherein the horizontal axis is flood type, and the vertical axis is early warning measure; filling in the form a corresponding early warning measure set of each flood type, and a priority and an execution sequence; the form is converted into a graphical or symbolic representation, such as a flow chart, tree diagram, matrix diagram, etc., that is convenient to understand and use.
As shown in fig. 7, according to an aspect of the present application, the step S6 is further:
step S61, acquiring research data and preprocessing to enable the research data to meet the requirements of a hydrographic hydrodynamic model;
the method can be used for collecting rainfall data, flow data, water level data, water quality data, topography data, soil data, vegetation data and the like of a research area by using a remote sensing technology, a hydrological site, a sensor network, a social sensing technology and the like. Historical data or statistical models may also be utilized to estimate or infer such data.
Step S62, constructing a hydrological hydrodynamic model, and generalizing a water network and a pipe network of a research area by adopting a GIS module; simplifying the pipe network structure and the topological relation;
the collected data can be subjected to operations such as cleaning, correction, interpolation, conversion, sampling and the like by using Excel, arcGIS, MATLAB and other tools, so that the collected data meets the requirements of a hydrographic hydrodynamic model.
Professional software such as SWMM, HEC-HMS and the like can be used, or a numerical simulation program based on a finite volume method can be compiled by oneself, so that simulation calculation of surface runoff of a research area and a pipe network drainage process can be realized.
The method can use ArcGIS and other tools to draw the spatial distribution of the water network and the pipe network according to the geographical information and engineering information of the research area, and endow each element (such as river channels, drainage pipelines, culverts, pump stations and the like) with corresponding properties (such as length, width, depth, roughness, capacity and the like).
In order to simplify the pipe network structure and the topological relation, software such as SWMM can be used, redundant elements (such as pipelines without flow or pressure change) in the pipe network are removed or combined according to the flow distribution rule and the pressure balance principle in the pipe network drainage process, and the connection relation between adjacent elements is adjusted. Suitable software can be selected or combined with various software for more reasonable and concise simplification according to the calculation efficiency and stability of the model.
Step S63, dividing the sub-water areas of the research area by using DEM data, and determining parameters of each sub-water area, including area, gradient, soil type, building condition and vegetation coverage;
And using ArcGIS and other tools, identifying the water collecting boundary of the research area by using methods such as flow direction analysis, flow accumulation analysis and the like according to elevation information of DEM data, and dividing the research area into a plurality of sub-water collecting areas according to certain standards (such as area, shape, position and the like). Parameters such as the area, gradient, soil type, building condition and vegetation coverage of each subset water area are calculated by using tools such as ArcGIS according to DEM data, soil data, building data, vegetation data and the like through methods such as statistical analysis and space analysis.
Step S64, carrying out two-dimensional grid division on the research area by adopting a limited volume method, and endowing grid parameters of each grid, including elevation, roughness and boundary conditions;
and dividing the research area into a plurality of finite volume units by using MATLAB and other tools according to the topographic features and calculation requirements of the research area and using triangulation or quadrilateral subdivision and other methods, and recording vertex coordinates, adjacent relations and control surface information of each unit. Parameters such as elevation, roughness, boundary conditions and the like of each unit are calculated by using a tool such as ArcGIS according to DEM data, roughness data, boundary condition data and the like through methods such as interpolation analysis, space analysis and the like, and are led into a tool such as MATLAB.
S65, constructing training input data by adopting a rainfall design method including a same-frequency analysis method, a Chicago method and a heavy rainfall time face depth relation method, and calibrating a hydrological hydrodynamic model;
parameters such as elevation, roughness, boundary conditions and the like of each unit are calculated by using a tool such as ArcGIS according to DEM data, roughness data, boundary condition data and the like through methods such as interpolation analysis, space analysis and the like, and are led into a tool such as MATLAB. And using SWMM and other software to perform simulation calculation according to the constructed model and the generated training input data, comparing and evaluating the calculation result with the actual measurement result, and adjusting parameters or structures in the model by using an optimization algorithm or manual adjustment and other methods to enable the simulation result to be as close as possible to the actual measurement result and achieve preset precision and stability.
And step S66, acquiring current actually measured rainfall and urban flood data, performing simulation and prediction as input data, giving intelligent early warning information and early warning measures, and pushing the intelligent early warning information and the early warning measures to each preset terminal.
The method comprises the steps of collecting rainfall data, flow data, water level data, water quality data and the like of a research area in real time or at fixed time by using a remote sensing technology, a hydrological site, a sensor network, a social sensing technology and the like, and converting the rainfall data, the flow data, the water level data, the water quality data and the like into a format suitable for model input. And using SWMM and other software, performing simulation calculation according to the calibrated model and the acquired input data, and giving out urban flood conditions and risk grades of various key areas in the research area in the current or future period according to a certain rule or algorithm. And determining the content, the release channel, the release time and the release frequency of the early warning information, the content, the execution main body, the execution time and the execution sequence of the early warning measures, which are applicable to the urban flood condition and the risk level of each key area in the research area in the current or future period, according to the simulation and prediction results and the mapping relation in the total set of the early warning measures by using Excel and other tools. And sending the early warning information to each preset terminal, such as government departments, flood control units, media institutions, public and the like according to the early warning information content, the release channels, the release time and the release frequency by using tools such as WeChat, short message, broadcast and the like, and adjusting and optimizing according to the feedback information.
According to one aspect of the present application, the step S4 further includes:
step S40, labeling flood in the heavy point area based on rainfall abrupt points and flood abrupt points:
judging whether the number of rainfall abrupt change points and flood abrupt change points exceeds respective threshold values or not respectively;
if yes, clustering is carried out respectively until the number of the rainfall breaking mutation points and the flood mutation points is not higher than a preset threshold value;
if not, acquiring rainfall data and flood data in the latest period;
establishing a mapping relation according to rainfall and flood in the last period, and obtaining a first mapping weight;
and resetting the mapping relation between rainfall and flood in other periods according to the first mapping weight, updating the mapping weight, and checking.
According to the embodiment, through the scheme, the time and the range of flood occurrence of the key area can be effectively identified, and basis is provided for flood early warning and prevention and control; the rainfall conditions in different periods are reversely pushed out by utilizing the mapping relation between rainfall and flood, and data support is provided for rainfall monitoring and analysis; according to rainfall and flood data in different periods, mapping weights are dynamically updated, and the accuracy and adaptability of the model are improved; through clustering, the number of rainfall abrupt change points and flood abrupt change points can be reduced, and the calculation complexity and the storage space are reduced. The method solves the problem that rainfall and flood sequences change due to climate change and underlying surface change, so that the forecasting is carried out according to the current parameters, and the forecasting accuracy is greatly improved.
According to an aspect of the present application, the step S42 further includes:
acquiring rainfall data and generating a rasterized rainfall distribution map;
dividing, identifying and positioning rainfall data, extracting a rainfall center, average rainfall and rainfall radius, and converting the rainfall center, the average rainfall and the rainfall radius into position information under a coordinate system;
fitting, predicting and smoothing the position information by using a time sequence analysis method to obtain a movement track of a rainfall center, and judging whether the rainfall intensity changes according to the change condition of the rainfall radius;
and superposing the movement track and the map of the key area by using a Geographic Information System (GIS), analyzing the movement direction, speed and range of the rainfall center, and calculating and evaluating the influence degree of the rainfall center on the heavy flood control area.
In the embodiment, the space distribution and the change of rainfall are more accurately described by utilizing a grid rainfall distribution map, and a finer data base is provided for flood marking; key parameters such as a rainfall center, average rainfall capacity, rainfall radius and the like are extracted through dividing, identifying and positioning rainfall data, so that more effective characteristic information is provided for flood marking; fitting, predicting and smoothing the position information of the rainfall center by using a time sequence analysis method to obtain a movement track of the rainfall center, judging whether the rainfall intensity changes according to the change condition of the rainfall radius, and providing more dynamic process information for flood marking; and superposing the movement track of the rainfall center with a map of the key area by using a Geographic Information System (GIS), analyzing the movement direction, speed and range of the rainfall center, calculating and evaluating the influence degree of the rainfall center on the heavy flood control area, and providing more comprehensive influence information for flood marking.
According to another aspect of the present application, an intelligent pre-warning system for urban flood control, comprises:
at least one processor; and
a memory communicatively coupled to at least one of the processors; wherein,
the memory stores instructions executable by the processor for execution by the processor to implement the intelligent pre-warning method for urban flood control of any one of the above-described technical schemes.
The preferred embodiments of the present application have been described in detail above, but the present application is not limited to the specific details of the above embodiments, and various equivalent changes can be made to the technical solution of the present application within the scope of the technical concept of the present application, and all the equivalent changes belong to the protection scope of the present application.
Claims (5)
1. The intelligent early warning method for urban flood control is characterized by comprising the following steps of:
s1, determining a range of a research area, and acquiring research data;
s2, extracting historical rainfall data from the research data to obtain rainfall characteristics to form a rainfall characteristic set; analyzing rainfall data by adopting a trend analysis method, and dividing the rainfall data into at least two time periods;
step S3, urban flood data are extracted from the research data, and urban flood features are extracted to form an urban flood feature set; analyzing urban flood by adopting a trend analysis method;
S4, constructing a correlation analysis model of rainfall and urban flood, calculating the correlation of the rainfall and the urban flood according to each rainfall and urban flood based on the rainfall data and the urban flood data, and arranging the rainfall and the urban flood in a descending order;
step S5, constructing an early warning measure set aiming at each urban flood to form a rainfall and early warning measure mapping relation of a research area;
s6, constructing a hydrologic hydrodynamic model, calibrating based on research data, taking current actually measured rainfall and urban flood data as input data, performing simulation and prediction, giving intelligent early warning information and early warning measures, and pushing to each terminal;
the step S1 is further:
s11, acquiring research data of a river basin where a city is located, wherein the research data at least comprises a digital elevation model, gradient, flow direction, flow, drainage pipe network parameters, rainfall data and urban flood data;
step S12, acquiring a first boundary and a second boundary based on a digital elevation model, wherein the first boundary is a river basin boundary of a river basin where the city is located; the second boundary is a city flood control area boundary; the second boundary is included in the first boundary;
step S13, rasterizing the research area, extracting key areas in the second boundary based on the flood control target, searching grids corresponding to the key areas for each key area, and constructing a key grid set;
Step S14, extracting urban water network structures based on a digital elevation model, and extracting water network and confluence data of key areas one by one;
the step S2 further includes:
s21, extracting historical rainfall data from the research data, and obtaining rainfall characteristics including a rainfall center, a rainfall radius, a maximum N-day rainfall, a rainfall days and an accumulated rainfall from the rainfall data; wherein N is 1, 3, 5, 7;
s22, constructing a trend analysis method set, wherein the trend analysis method at least comprises an MK test method and a Sen' S slope method;
s23, trend detection is carried out one by adopting a trend analysis method;
the MK assay process includes: firstly, calculating the difference value of the rainfall of each pair of years, and endowing a sign value with a sign; calculating the cumulative symbol value of each year and calculating the sum, variance, standard deviation and standardized statistic; judging whether a significant trend exists or not based on a comparison result of the standardized statistic and the threshold value; searching rainfall mutation points by adopting a dichotomy method,
step S24, dividing rainfall data into at least two time periods based on rainfall abrupt change points;
the step S3 is further:
step S31, urban flood data are extracted from research data, urban flood characteristics are collected and form an urban flood characteristic set, wherein the urban flood characteristics at least comprise a flooding range, a flooding time, a flooding depth, a total flood amount, a flood duration, a flood peak flow, a peak time, a rising flow and a peak section flood;
S32, constructing a trend analysis method set, wherein the trend analysis method at least comprises an MK (marker for marker) test method and a moving average method;
the trend analysis process by using the moving average method comprises the following steps: obtaining urban flood data, constructing a flood time sequence, selecting a proper time window length, and calculating a moving average value of each period according to the time window length; drawing a smooth curve according to the moving average value, observing the change trend of the curve, and judging whether a significant rising or falling trend exists or not; calculating residual errors according to the moving average value and the original data, namely, the difference value between the moving average value and the original data, judging whether flood mutation points exist or not according to the absolute value or standard deviation of the residual errors, and determining the positions of the flood mutation points;
the moving average value comprises a simple moving average value SMA and an exponential moving average value EMA, wherein the simple moving average value SMA refers to the arithmetic average value of data in each period in a time window; the index moving average EMA refers to that the data in each period in a time window are weighted and averaged according to the index weight;
step S33, urban flood is staged based on the condition of the flood mutation points;
the step S4 further includes:
step S40, labeling flood in the heavy point area based on rainfall abrupt points and flood abrupt points:
Judging whether the number of rainfall abrupt change points and flood abrupt change points exceeds respective threshold values or not respectively;
if yes, clustering is carried out respectively until the number of the rainfall breaking mutation points and the flood mutation points is not higher than a preset threshold value;
if not, acquiring rainfall data and flood data in the latest period;
establishing a mapping relation according to rainfall and flood in the last period, and obtaining a first mapping weight;
resetting the mapping relation between rainfall and flood in other periods by using the first mapping weight, updating the mapping weight, and checking;
s41, constructing a correlation analysis model of rainfall and urban flood, wherein the correlation analysis model at least comprises a rainfall distribution analysis unit;
step S42, aiming at each rainfall in each period, searching an affected key area according to the track of a rainfall center and the rainfall radius; establishing a mapping relation between rainfall and key areas;
step S43, aiming at each flood in each period, searching the association relation between the flood in each key area and each rainfall in the preset time, establishing a mapping set between the urban flood in each key area and the associated rainfall, calculating the contribution degree of each rainfall to the urban flood in the key area, and arranging in descending order; obtaining the correlation between each city flood and each rainfall;
And S44, carrying out association analysis on the correlation of urban flood and rainfall based on the water network structural relationship among key areas.
2. The intelligent pre-warning method for urban flood control according to claim 1, wherein said step S5 is further:
s51, constructing an early warning measure total set;
step S52, establishing flood classification standards, and classifying each flood;
and step S53, forming a pre-warning measure set corresponding to the type of flood according to the type of flood, and forming a mapping relation between each type of flood and pre-warning measures in the research area.
3. The intelligent pre-warning method for urban flood control according to claim 2, wherein said step S6 is further:
step S61, acquiring research data and preprocessing to enable the research data to meet the requirements of a hydrographic hydrodynamic model;
step S62, constructing a hydrological hydrodynamic model, and generalizing a water network and a pipe network of a research area by adopting a GIS module; simplifying the pipe network structure and the topological relation;
step S63, dividing the sub-water areas of the research area by using DEM data, and determining parameters of each sub-water area, including area, gradient, soil type, building condition and vegetation coverage;
Step S64, carrying out two-dimensional grid division on the research area by adopting a limited volume method, and endowing grid parameters of each grid, including elevation, roughness and boundary conditions;
s65, constructing training input data by adopting a rainfall design method including a same-frequency analysis method, a Chicago method and a heavy rainfall time face depth relation method, and calibrating a hydrological hydrodynamic model;
and step S66, acquiring current actually measured rainfall and urban flood data, performing simulation and prediction as input data, giving intelligent early warning information and early warning measures, and pushing the intelligent early warning information and the early warning measures to each preset terminal.
4. The intelligent pre-warning method for urban flood control according to claim 1, wherein said step S42 further comprises:
acquiring rainfall data and generating a rasterized rainfall distribution map;
dividing, identifying and positioning rainfall data, extracting a rainfall center, average rainfall and rainfall radius, and converting the rainfall center, the average rainfall and the rainfall radius into position information under a coordinate system;
fitting, predicting and smoothing the position information by using a time sequence analysis method to obtain a movement track of a rainfall center, and judging whether the rainfall intensity changes according to the change condition of the rainfall radius;
And superposing the movement track and the map of the key area by using a Geographic Information System (GIS), analyzing the movement direction, speed and range of the rainfall center, and calculating and evaluating the influence degree of the rainfall center on the heavy flood control area.
5. An intelligent early warning system for urban flood control, comprising:
at least one processor; and
a memory communicatively coupled to at least one of the processors; wherein,
the memory stores instructions executable by the processor for execution by the processor to implement the intelligent pre-warning method for urban flood control of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311276139.4A CN117010726B (en) | 2023-09-29 | 2023-09-29 | Intelligent early warning method and system for urban flood control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311276139.4A CN117010726B (en) | 2023-09-29 | 2023-09-29 | Intelligent early warning method and system for urban flood control |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117010726A CN117010726A (en) | 2023-11-07 |
| CN117010726B true CN117010726B (en) | 2023-12-08 |
Family
ID=88562174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311276139.4A Active CN117010726B (en) | 2023-09-29 | 2023-09-29 | Intelligent early warning method and system for urban flood control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117010726B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236673B (en) * | 2023-11-16 | 2024-01-26 | 水利部交通运输部国家能源局南京水利科学研究院 | Urban water network multi-scale flood control and drainage combined optimization scheduling method and system |
| CN117745095B (en) * | 2023-12-21 | 2024-07-19 | 山东融信数科信息科技有限公司 | Urban flood prevention decision method, system and storage medium based on big data |
| CN117875216B (en) * | 2024-02-04 | 2024-07-19 | 珠海市规划设计研究院 | Rain and flood regulation and storage rate determining method, device and medium based on elastic coefficient method |
| CN118134729B (en) * | 2024-05-08 | 2024-07-05 | 水利部交通运输部国家能源局南京水利科学研究院 | Intelligent forecasting method and system for urban flood control |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102610059A (en) * | 2012-03-01 | 2012-07-25 | 河海大学 | Monitoring and prewarning system for sudden flood in mountainous area and establishing method thereof |
| CN106844531A (en) * | 2016-12-29 | 2017-06-13 | 福建四创软件有限公司 | A kind of flood control command based on grid studies and judges system |
| CN108460510A (en) * | 2017-12-28 | 2018-08-28 | 中国水利水电科学研究院 | The determination method, apparatus and storage medium of Flood Dispatching On Reservoirs scheme |
| CN111027763A (en) * | 2019-12-06 | 2020-04-17 | 中国水利水电科学研究院 | Basin flood response similarity analysis method based on machine learning |
| CN111651885A (en) * | 2020-06-03 | 2020-09-11 | 南昌工程学院 | Intelligent sponge urban flood forecasting method |
| CN112785053A (en) * | 2021-01-15 | 2021-05-11 | 北京市水科学技术研究院 | Method and system for forecasting urban drainage basin flood |
| CN115186858A (en) * | 2022-03-29 | 2022-10-14 | 南京南瑞水利水电科技有限公司 | Transformer substation flood inundation risk early warning method and system based on different influence types |
| CN115271255A (en) * | 2022-09-19 | 2022-11-01 | 长江水利委员会水文局 | Rainfall flood similarity analysis method and system based on knowledge graph and machine learning |
| CN115829163A (en) * | 2023-01-16 | 2023-03-21 | 河海大学 | Multi-mode integration-based runoff prediction method and system for middle and lower reaches of Yangtze river |
| CN116611333A (en) * | 2023-05-23 | 2023-08-18 | 中国水利水电科学研究院 | Urban flood risk point prediction method |
-
2023
- 2023-09-29 CN CN202311276139.4A patent/CN117010726B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102610059A (en) * | 2012-03-01 | 2012-07-25 | 河海大学 | Monitoring and prewarning system for sudden flood in mountainous area and establishing method thereof |
| CN106844531A (en) * | 2016-12-29 | 2017-06-13 | 福建四创软件有限公司 | A kind of flood control command based on grid studies and judges system |
| CN108460510A (en) * | 2017-12-28 | 2018-08-28 | 中国水利水电科学研究院 | The determination method, apparatus and storage medium of Flood Dispatching On Reservoirs scheme |
| CN111027763A (en) * | 2019-12-06 | 2020-04-17 | 中国水利水电科学研究院 | Basin flood response similarity analysis method based on machine learning |
| CN111651885A (en) * | 2020-06-03 | 2020-09-11 | 南昌工程学院 | Intelligent sponge urban flood forecasting method |
| CN112785053A (en) * | 2021-01-15 | 2021-05-11 | 北京市水科学技术研究院 | Method and system for forecasting urban drainage basin flood |
| CN115186858A (en) * | 2022-03-29 | 2022-10-14 | 南京南瑞水利水电科技有限公司 | Transformer substation flood inundation risk early warning method and system based on different influence types |
| CN115271255A (en) * | 2022-09-19 | 2022-11-01 | 长江水利委员会水文局 | Rainfall flood similarity analysis method and system based on knowledge graph and machine learning |
| CN115829163A (en) * | 2023-01-16 | 2023-03-21 | 河海大学 | Multi-mode integration-based runoff prediction method and system for middle and lower reaches of Yangtze river |
| CN116611333A (en) * | 2023-05-23 | 2023-08-18 | 中国水利水电科学研究院 | Urban flood risk point prediction method |
Non-Patent Citations (6)
| Title |
|---|
| 基于信息熵的洪水过程均匀度变异分析方法――以东江流域龙川站洪水过程为例;陈海健;谢平;谢静红;李彬彬;雷旭;张波;;水利学报(10);第1233-1239页 * |
| 大数据在洪水分析中的应用前景探究;吴美玲;杨侃;杨哲;;江苏水利(06);第13-24页 * |
| 武汉地铁黄浦路站防洪涝水位及预警研究;谢桥军;罗伟;欧阳院平;周丹;李肖男;;现代城市轨道交通(04);第71-75页 * |
| 流域降雨径流关系的变化现状及其原因分析;刘涓;聂川翔;谢谦;冯欢;苏成林;靳军英;;安徽农业科学(10);第2110页 * |
| 淮河上游典型流域径流演变过程影响因素分析――以白莲崖流域为例;杨传清;陈杭;顾哲衍;王蔚;鞠靖;陈立冬;朱华刚;;中国水土保持科学(01);第110-116页 * |
| 闹德海水库库区降水径流变化趋势及突变分析;尹璐璐;《水土保持应用技术》(05);第28-29页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117010726A (en) | 2023-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117010726B (en) | Intelligent early warning method and system for urban flood control | |
| CN116070918B (en) | Urban flood safety assessment and flood disaster prevention and control method | |
| US10664937B2 (en) | Flood risk analysis and mapping | |
| US20190316309A1 (en) | Flood monitoring and management system | |
| CN110852577A (en) | Urban flood assessment method based on urban toughness and urban drainage basin hydrological model | |
| CN113434565A (en) | Water conservancy flood control drought and waterlogging prevention comprehensive disaster reduction platform system based on CIM platform | |
| CN111507375B (en) | Urban waterlogging risk rapid assessment method and system | |
| CN116911699B (en) | Method and system for fine dynamic evaluation of toughness of urban flood disaster response | |
| US10762588B2 (en) | Flood-recovery options tool | |
| Yan et al. | A rapid prediction model of urban flood inundation in a high-risk area coupling machine learning and numerical simulation approaches | |
| CN110837925B (en) | Urban waterlogging prediction method and device | |
| Sebastian et al. | Hindcast of pluvial, fluvial, and coastal flood damage in Houston, Texas during Hurricane Harvey (2017) using SFINCS | |
| CN106373070A (en) | Four-prevention method for responding to city rainstorm waterlogging | |
| CN117408173B (en) | Hydrologic flow recompilation intelligent model construction method based on machine learning | |
| CN117275188A (en) | Mountain torrent disaster monitoring and early warning system and mountain torrent disaster monitoring and early warning method | |
| CN117332909B (en) | Multi-scale urban waterlogging road traffic exposure prediction method based on intelligent agent | |
| Li et al. | Urban flood risk assessment based on DBSCAN and K-means clustering algorithm | |
| Tu et al. | Flood risk assessment of metro stations based on the SMAA-2-FFS-H method: A case study of the “7· 20” rainstorm in Zhengzhou, China | |
| CN117113038B (en) | Urban water and soil loss Huang Nishui event tracing method and system | |
| Wang et al. | Evaluation of urban flooding and potential exposure risk in central and southern Liaoning urban agglomeration, China | |
| Surwase et al. | Urban flood simulation-A case study of Hyderabad city | |
| Li et al. | High-Resolution Flood Numerical Model and Dijkstra Algorithm Based Risk Avoidance Routes Planning | |
| Yan et al. | A novel integrated urban flood risk assessment approach based on one-two dimensional coupled hydrodynamic model and improved projection pursuit method | |
| Kherde et al. | Integrating Geographical Information Systems (GIS) with Hydrological Modelling—Applicability and Limitations | |
| CN118153787B (en) | Rain and tide disaster emergency risk avoiding path and material allocation optimization method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |