CN118037062A - Waterlogging disaster risk assessment system based on causal sum or graph - Google Patents
Waterlogging disaster risk assessment system based on causal sum or graph Download PDFInfo
- Publication number
- CN118037062A CN118037062A CN202410425548.4A CN202410425548A CN118037062A CN 118037062 A CN118037062 A CN 118037062A CN 202410425548 A CN202410425548 A CN 202410425548A CN 118037062 A CN118037062 A CN 118037062A
- Authority
- CN
- China
- Prior art keywords
- waterlogging
- risk
- causal
- loss
- point
- 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
- 230000001364 causal effect Effects 0.000 title claims abstract description 58
- 238000012502 risk assessment Methods 0.000 title claims abstract description 33
- 238000012544 monitoring process Methods 0.000 claims abstract description 32
- 230000003068 static effect Effects 0.000 claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims description 31
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 25
- 238000012545 processing Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 abstract description 10
- 230000002265 prevention Effects 0.000 abstract description 3
- 238000012163 sequencing technique Methods 0.000 abstract 1
- 238000009825 accumulation Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008595 infiltration Effects 0.000 description 2
- 238000001764 infiltration Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000008239 natural water Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/041—Abduction
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Computational Mathematics (AREA)
- Educational Administration (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Pure & Applied Mathematics (AREA)
- Development Economics (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a causal and graph-based waterlogging disaster risk assessment system, which comprises the following steps: the waterlogging point monitoring module is used for acquiring monitoring data of all waterlogging points in the risk area; the point location information sensing module is used for extracting static building information and dynamic flow information; the causal and or relation module is used for constructing a causal and or relation model of the risk area and the waterlogging point; the risk calculation module is used for calculating the probability of occurrence of waterlogging events in each risk area; the loss calculation module is used for calculating a loss value and a loss expected value of each node; the risk assessment module is used for outputting the sorting result as a risk and loss assessment result. The system is based on a causal and relational model, and by calculating the loss value and the loss expected value and evaluating and sequencing the risk areas, the risk and loss evaluation result with intuitionistic and high accuracy is provided on the premise of ensuring the evaluation efficiency, and more scientific support and guidance are provided for waterlogging prevention and control work.
Description
Technical Field
The invention relates to the technical field of urban waterlogging risk assessment, in particular to a waterlogging disaster risk assessment system based on causal sum or graph.
Background
At present, urban inland inundation is an extreme phenomenon of an urban water circulation system and is the result of interaction of natural factors and social factors. The urban water circulation system consists of a natural water circulation system and a high-strength social water circulation system, and urban waterlogging is the expression of the system. The formation of urban inland inundation involves natural factors and social factors, and has dual properties. In terms of natural factors, global warming causes global climate change, also changes local climate characteristics of cities, and increases the probability of extreme storms of cities. In the aspect of social factors, the urban process has influence on each link of urban water circulation. Urban heat island effect and rain island effect caused by urbanization increase the frequency and intensity of urban rainfall, and directly cause urban heavy rain waterlogging. In the process of producing the flow, the urban high-density hardened ground blocks the infiltration and infiltration process of rainfall, improves the flow coefficient of the ground surface and increases the surface runoff. In the converging process, most surface runoffs are converged into the river channel through the drainage pipe network of the social water circulation system, so that the converging hydraulic efficiency is improved, the river channel flood peak flow is increased, and the peak time is advanced. In addition, urban inland inundation is also affected by human factors such as unreasonable urban functional area planning, imperfect infrastructure such as rainwater recycling, low flood control scheduling management level, low design standard of a drainage pipe network and the like. Therefore, the risk assessment of urban inland inundation is of great significance. Through the assessment of the waterlogging risk, the identification and prediction capability of the waterlogging risk can be improved, so that adverse effects of the waterlogging on urban operation and resident life are effectively reduced.
There are three common methods of risk assessment for waterlogging: a historical disaster mathematical statistics method, an index system method, a hydrologic model and a simulation method.
The historical disaster mathematical statistics method is a method for carrying out statistical analysis on historical disaster data by utilizing a mathematical statistics method so as to find out a disaster development rule, and establishing a statistical model of disaster occurrence probability and influence factors so as to estimate disaster loss possibly caused in the future. In urban inland inundation disaster assessment, the method mainly researches the relationship among the heavy rain reproduction period, the flood inundation range and different property loss rates. The method can utilize historical data, and has smaller demand for real data. But this method is only applicable to a specific region or a specific type of disaster, while history data acquisition may be difficult and new situations beyond the history range cannot be evaluated.
The index system method is a method for evaluating regional waterlogging disaster risk by selecting a certain index system according to the characteristics of the urban waterlogging disaster system and processing indexes through a series of mathematical methods. The index system method relies on the collection and processing of a large amount of index data, including disaster data, environmental data, socioeconomic data, and the like. Despite its wide applicability, this method is large in data demand and faces difficulties and costs of data acquisition and arrangement. In the method, the selection of the index and the optimization of the weight have great influence on the evaluation result.
The hydrologic model and the simulation method are a method for carrying out numerical simulation calculation by setting the storm scenes with different frequencies and utilizing the drainage basin yield converging model and the flood evolution model, and deduce the submerged range, submerged depth and submerged duration of urban inland inundation possibly caused by the storm under different scenes. The key of the method is to simulate waterlogging disasters under different storm situations by using hydrologic and hydrodynamic models or hydrologic and hydrodynamic models constructed according to regional characteristics. However, this approach is generally demanding in terms of data, but still requires some data support, and data acquisition may face some challenges, especially for certain data, such as surface coverage data. In addition, the hydrologic model and the simulation method relate to a complex calculation process, and the calculated amount is large.
Therefore, how to provide a system for dynamically evaluating the risk of a large-scale waterlogging disaster, such as a district, a city, etc., which has low data demand and can fully utilize the knowledge of regional geographic information, is a problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the invention provides a waterlogging disaster risk assessment system based on causal and or graph, which fully utilizes the existing monitoring signals and sensor data, does not need a large amount of data, avoids extra data acquisition cost and complexity, realizes the fine assessment of waterlogging risk, and furthest reduces the loss caused by waterlogging events.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
A causal and graph-based waterlogging disaster risk assessment system, comprising: the system comprises a waterlogging point monitoring module, a point location information sensing module, a causal and relationship module, a risk calculation module, a loss calculation module and a risk assessment module;
The waterlogging point monitoring module is used for acquiring monitoring data of all waterlogging points in the risk area;
The point location information sensing module is used for analyzing and processing waterlogging point monitoring data and extracting static building information and dynamic flow information;
The causal and or relation module is used for acquiring an inherent causal logic relation between the risk area and the waterlogging point and constructing a causal and or relation model of the risk area and the waterlogging point;
The risk calculation module is used for calculating the probability of occurrence of waterlogging events in each risk area according to the causal and relational model;
The loss calculation module is used for calculating a loss value of each node in the causal and/or relational model according to the static building information, the dynamic flow information and the causal and/or relational model; calculating a loss expected value of the corresponding risk area according to the loss value and the probability of occurrence of the waterlogging event;
The risk assessment module is used for ordering according to the probability of occurrence of waterlogging events in the risk areas, and for risk areas with the same probability, ordering according to the magnitude of the loss value, and outputting the ordering result as risk and loss assessment result.
Wherein, the waterlogging point monitoring data includes: monitoring video information and related parameter information of waterlogging ponding.
Preferably, the static building information includes: building characteristics within a preset range around the waterlogged spot.
Preferably, the dynamic traffic information includes: traffic conditions and crowd concentration within a preset range around waterlogged spots.
Preferably, the causal and/or relational model of the risk area and the waterlogging point comprises:
each risk area is represented as a tree structure in a causal and/or relational model, and the risk areas serve as root nodes; each risk area is divided into a plurality of sub-areas which are used as branch nodes; each sub-area comprises a plurality of waterlogging points serving as leaf nodes;
Judging that the waterlogging event occurs at the waterlogging point if the waterlogging depth of the waterlogging point exceeds a preset threshold value;
The waterlogging points and the subareas are in a relation, and waterlogging events occur in all the waterlogging points in the subareas, so that the subareas are judged to have waterlogging events; and if the subarea is or is related to the risk area, and a waterlogging event occurs in any subarea, judging that the waterlogging event occurs in the risk area where the subarea is positioned.
Preferably, the edge between the branch node and the corresponding leaf node represents the probability of occurrence of the waterlogging event by the branch node when the waterlogging event occurs by the leaf node; and when the branch node generates a waterlogging event, the edge between the root node and the corresponding branch node represents the probability of the occurrence of the waterlogging event by the root node.
Preferably, the probability calculation method comprises the following steps: the probability of the leaf node corresponding to the waterlogging point of the waterlogging event is set to be 1, the probability of the leaf node corresponding to the waterlogging point of the waterlogging event is not set to be 0, and the probability of each root node of the waterlogging event is calculated from bottom to top.
Preferably, the loss value includes: static loss values and dynamic loss values;
Calculating a static loss value for one time in a period of time according to the input static building information; and continuously calculating a dynamic loss value in real time according to the input dynamic flow information.
Preferably, the method for calculating the loss value comprises the following steps: the leaf node corresponding to the waterlogging point with the waterlogging event is set as the loss value, and the loss value of the leaf node corresponding to the waterlogging point without the waterlogging event is set as 0; according to the causal and or relational model, calculating a loss value of waterlogging of each branch node and each root node;
the calculation rule is as follows: for a branch node, its penalty value is the sum of the penalty values of all its corresponding leaf nodes; for a root node, its penalty value is the maximum of all its corresponding branch node penalty values.
Preferably, the expected loss value of the corresponding risk area is the product of the area node loss value and the area node waterlogging probability.
Compared with the prior art, the invention discloses a waterlogging disaster risk assessment system based on causal sum or graph, which comprises: the system comprises a waterlogging point monitoring module, a point location information sensing module, a causal and relationship module, a risk calculation module, a loss calculation module and a risk assessment module; has the following advantages:
(1) According to the technical scheme, only the waterlogging point monitoring data of the risk area is required to be obtained, and the causal and or relation between the risk area and the risk point is established, so that the data required by waterlogging risk assessment can be effectively obtained; the static building information, the number of pedestrians, the traffic flow and other data are extracted from the waterlogging point monitoring data through an image sensing technology so as to evaluate the fixed asset loss and the dynamic loss information, the existing monitoring signals and sensor data can be fully utilized, and the additional data acquisition cost and complexity are avoided;
(2) The C-AOG model is adopted to represent an inherent causal logic relationship between the risk areas and the risk points, a forest structure of a plurality of trees is constructed, overall evaluation is carried out on waterlogging risks of different risk areas, and the waterlogging probability of each root node is accurately calculated, so that the fine evaluation on the waterlogging risks is realized;
(3) The loss calculation module combines dynamic loss data, static loss data and data of risk of waterlogging of the region, comprehensively considers economic loss factors, accurately evaluates the economic losses of different regions, pertinently takes measures according to evaluation results, and reduces the economic losses.
(4) And (3) sorting the output risk and loss assessment results according to the level of the waterlogging risk, and further sorting the areas with the same risk according to the loss, so that the waterlogging risk and loss conditions of different areas can be quickly known, the areas with high risk can be preferentially treated, and the loss caused by waterlogging events can be reduced to the greatest extent.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic structural diagram of a waterlogging disaster risk assessment system according to an embodiment of the present invention;
FIG. 2 is a graph showing the inherent causal logic relationship between waterlogging points and risk areas according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1;
As shown in fig. 1, the embodiment of the invention discloses a causal and or graph-based waterlogging disaster risk assessment system, which comprises: the system comprises a waterlogging point monitoring module, a point location information sensing module, a causal and relationship module, a risk calculation module, a loss calculation module and a risk assessment module;
the waterlogging point monitoring module is used for acquiring monitoring data of all waterlogging points in the risk area;
The point information sensing module is used for analyzing and processing waterlogging point monitoring data and extracting static building information and dynamic flow information;
the causal and or relation module is used for acquiring an inherent causal logic relation between the risk area and the waterlogging point and constructing a causal and or relation model of the risk area and the waterlogging point;
the risk calculation module is used for calculating the probability of occurrence of waterlogging events in each risk area according to the causal and relational model;
the loss calculation module is used for calculating a loss value of each node in the causal and/or relational model according to the static building information, the dynamic flow information and the causal and/or relational model; calculating a loss expected value of the corresponding risk area according to the loss value and the probability of occurrence of the waterlogging event;
The risk assessment module is used for ordering according to the probability of occurrence of waterlogging events in the risk areas, ordering the risk areas with the same probability according to the magnitude of the loss value, and outputting the ordering result as a risk and loss assessment result.
Specifically, the waterlogging point monitoring data includes: monitoring video information and related parameter information of waterlogging ponding.
The static building information includes: building characteristics within a preset range around the waterlogged spot. For assessing static economic loss in a waterlogging event; the static economic loss is the material loss of property and resource directly caused after the disaster, and is the initial loss caused by the disaster. Building characteristics include building type, structure, and scale.
Common static economic losses include: property loss of houses, vehicles, fixed equipment and the like; infrastructure damage such as roads, bridges, drainage systems, etc.; the crop is submerged, resulting in reduced yield or complete loss of the crop.
Specifically, the dynamic flow information comprises the number of pedestrians and the traffic flow information which are analyzed and identified in the monitoring video signal of the waterlogging point monitoring data, and is used for evaluating casualties, traffic conditions and dynamic economic losses of the waterlogging points involved in the waterlogging event; dynamic economic loss refers to the reduction of economic activity due to production breaks, labor losses and supply chain breaks after a disaster has occurred, resulting in economic losses.
Common dynamic economic losses include: the production environments of factories, enterprises, farmlands and the like are damaged due to waterlogging disasters, the production activities are forced to be interrupted, the production is reduced, and the economic loss is caused; work places are subjected to disaster, so that staff cannot work normally, waste of labor force is caused, and labor force loss is caused by reduction of income of the staff; the waterlogging disasters influence logistics and supply chains, so that raw materials and products are prevented from being transported, the operation of the whole economic system is further influenced, and economic losses are caused.
Preferably, the loss values include a static loss value and a dynamic loss value; calculating a static loss value once in a period of time according to the input static building information, wherein the static loss value is generally calculated once in about one hour; according to the input dynamic flow information, the dynamic loss value is calculated continuously in real time, and can be generally calculated once in ten minutes, and when the rainfall is large, the calculation interval can be reduced to one time in five minutes.
The invention extracts the static building information, the pedestrian number, the traffic flow and other data from the waterlogging point monitoring data through the image sensing technology so as to evaluate the static economic loss and the dynamic economic loss information, and can fully utilize the existing monitoring signals and sensor data, thereby avoiding the additional data acquisition cost and complexity. In addition, static loss data can be estimated by referring to information such as the information of related areas, the map of the area and the like; the dynamic loss data can be obtained through calculation in the incoming video monitoring data, and can be input as configuration information through historical statistical knowledge.
Specifically, constructing a causal and/or relational model of the risk area and the waterlogging point based on a causal and/or relational graph (causal-and or graph, C-AOG); each risk area is represented as a tree structure in a causal and/or relational model, the position of the risk area is a root node, each risk area is divided into a plurality of sub-areas, each sub-area is a branch node, one sub-area comprises a plurality of waterlogging points, and all the waterlogging points in the sub-area are leaf nodes; a leaf node may have multiple parent nodes.
If the water accumulation depth of the waterlogging point exceeds a set threshold value, judging that a waterlogging event occurs in the waterlogging point;
the waterlogging points are in a relation with the subareas, and the waterlogging events occur at all the waterlogging points in the subareas, so that the subareas are judged to have the waterlogging events; and if the subarea is or is related to the risk area, and a waterlogging event occurs in any subarea, judging that the waterlogging event occurs in the risk area where the subarea is positioned.
One typical logical relationship is that of a geographic location. For example, a city comprises a plurality of areas, each area comprising a plurality of streets, and each street has a plurality of physical locations within the area of the street that are physically prone to water accumulation.
As shown in FIG. 2, the W005 area represents a street, a plurality of accumulated water points of N0014-N0018 exist in the street according to the previous records, and the W005 area can be divided into four sub-areas A, B, C and D according to the map division knowledge; when any one of the sub-regions is waterlogged, it can be determined that the W005 region is waterlogged, and thus E is or related to A, B, C, D on the C-AOG.
A sub-area comprises a plurality of water accumulation points, and only when water accumulation events occur in all water accumulation points in the sub-area, the water accumulation events in the sub-area can be judged, wherein in the figure, A is related to leaf nodes N0014, N0015, N0016 and N0017.
It should be noted that, since a water spot accumulates, water at the spot may flow to a plurality of different areas, there may be a plurality of parent nodes for a leaf node, and for ease of calculation, the same number of leaf nodes may be repeated on the C-AOG, as in the figure where the N0014 node exists in the child node of A, B, C, D.
Specifically, when the edge between the branch node and the corresponding leaf node represents that the leaf node has a waterlogging event, the probability of the waterlogging event of the branch node represents the priori information of the waterlogging event.
When multiple risk areas need to be assessed, the C-AOG changes from a tree to a forest. For the situation that the risk assessment of waterlogging disasters in a larger area needs to be considered, the causal relationship between the first level of the area and the street, and even between the city and the area can be constructed according to the logic. In the construction of the relationship, the knowledge of the region is fully utilized, and the knowledge can be flexibly selected in use according to actual conditions. The construction of the causal and or graph has strong interpretation, and can explain specific reasons of the risks of different areas.
Specifically, the probability calculation method comprises the following steps: the probability of the leaf node corresponding to the waterlogging point of the waterlogging event is set to be 1, the probability of the leaf node corresponding to the waterlogging point of the waterlogging event is not set to be 0, and the probability of each root node for generating the waterlogging event is calculated from bottom to top, so that the precise evaluation of the waterlogging risk is realized;
The calculation rule is as follows: for branch nodes, calculating according to a full probability formula, wherein P (a) =p (a|n0014) ×p (N0014) +p (a|n0015) ×p (N0015) +p (a|n0016) ×p (N0016) +p (a|n0017) ×p (N0017); taking region a as an example, when water accumulation occurs in N0014-N0017, P (N0014) =p (N0015) =p (N0016) =p (N0017) =1, P (a|n0014) =p (a|n0015) =p (a|n0016) =p (a|n0017) =0.25, so that the calculation result of P (a) is 1, which is to say, the probability of occurrence of water accumulation event in region a is 100%.
For the root node, the probability is equal to the maximum value of the probability of the branch node, i.e., P (E) =max { P (a), P (B), P (C), P (D) }. When the early warning of the waterlogging is performed, the worst case is considered, and therefore, the subregion in the region E where the waterlogging is most likely to occur is considered.
Specifically, the method for calculating the loss value comprises the following steps: the leaf node corresponding to the waterlogging point with the waterlogging event is set as the loss value, and the loss value of the leaf node corresponding to the waterlogging point without the waterlogging event is set as 0; calculating a loss value of waterlogging of each node from bottom to top according to the causal and/or relational model;
the calculation rule is as follows: for a branch node, its penalty value is the sum of the penalty values of all its corresponding leaf nodes; for a root node, its penalty value is the maximum of all its corresponding branch node penalty values.
Example 2;
The risk assessment of waterlogging has the significance of providing accurate and comprehensive information and guidance, coping with urban waterlogging disasters and reducing potential economic losses and casualties. Through the risk assessment of waterlogging, areas and points possibly affected by waterlogging can be timely identified, and the possibility and severity of waterlogging events are predicted. The method is favorable for taking preventive measures in advance, making an early warning plan, and issuing early warning information to related departments and the public, so that disaster prevention consciousness and emergency response capability of the society are improved.
The embodiment is oriented to the waterlogging risk assessment scene of the area B of the A city. By utilizing the waterlogging depth detection data of each waterlogging monitoring point in the area 244 and combining the knowledge of experts on the geographical information and the historical waterlogging disaster information of the area, the C-AOG is constructed, and 26 street waterlogging disaster risk conditions in the area B are estimated.
The specific embodiment is as follows:
In the actual operation of this patent, adopt most direct waterlogging monitoring information-waterlogging ponding degree of depth data, divide different ponding degrees through handling this data. The specific division is as follows: when the water accumulation depth is less than 27 cm, no obvious water accumulation is shown, and the water accumulation is a low risk area and is shown by blue; when the depth of the accumulated water is more than or equal to 27 cm and less than 40 cm, a medium risk area is represented, and yellow is used for representing the medium risk area; when the depth of the accumulated water is greater than or equal to 40 cm and less than 60 cm, a higher risk area is represented, and the area is represented by orange; when the depth of the accumulated water is more than or equal to 60 cm, a high risk area is represented, and red is used for representing the high risk area; and obtaining the division of the point position alarm threshold value.
And carrying out layered estimation on each waterlogging point according to different risk levels, and calculating the static and dynamic economic losses of the waterlogging points. Static economic loss refers to fixed asset loss, which we evaluate through static building information extracted by image-aware techniques. Dynamic economic loss refers to information such as pedestrian number, traffic flow and the like, and is used for evaluating the dynamic loss of the point positions later.
For the establishment of C-AOG, B is divided into 26 streets by geographic and ponding historical data of A city B area, wherein the 26 streets comprise 244 waterlogged ponding points. Thus a C-AOG forest containing 26 trees was constructed for computational evaluation of probability and loss.
Finally, the static and dynamic economic losses are combined with the risk levels for comprehensive calculations. By evaluating the risk and loss of each waterlogging point, a comprehensive waterlogging risk evaluation result is obtained, and the comprehensive waterlogging risk evaluation result can be ranked according to the risk level, so that a targeted reference is provided, corresponding disaster prevention and reduction measures are taken, and economic losses caused by waterlogging events are reduced to the greatest extent.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A causal and graph-based waterlogging disaster risk assessment system, comprising: the system comprises a waterlogging point monitoring module, a point location information sensing module, a causal and relationship module, a risk calculation module, a loss calculation module and a risk assessment module;
The waterlogging point monitoring module is used for acquiring monitoring data of all waterlogging points in the risk area;
The point location information sensing module is used for analyzing and processing waterlogging point monitoring data and extracting static building information and dynamic flow information;
The causal and or relation module is used for acquiring an inherent causal logic relation between the risk area and the waterlogging point and constructing a causal and or relation model of the risk area and the waterlogging point;
The risk calculation module is used for calculating the probability of occurrence of waterlogging events in each risk area according to the causal and relational model;
The loss calculation module is used for calculating a loss value of each node in the causal and/or relational model according to the static building information, the dynamic flow information and the causal and/or relational model; calculating a loss expected value of the corresponding risk area according to the loss value and the probability of occurrence of the waterlogging event;
The risk assessment module is used for ordering according to the probability of occurrence of waterlogging events in the risk areas, and for risk areas with the same probability, ordering according to the magnitude of the loss value, and outputting the ordering result as risk and loss assessment result.
2. The causal and graph-based waterlogging disaster risk assessment system according to claim 1, wherein the waterlogging point monitoring data comprises: monitoring video information and related parameter information of waterlogging ponding.
3. The causal and graph-based water logging disaster risk assessment system according to claim 1, wherein the static building information comprises: building characteristics within a preset range around the waterlogged spot.
4. The causal and graph-based water logging disaster risk assessment system according to claim 1, wherein the dynamic traffic information comprises: traffic conditions and crowd concentration within a preset range around waterlogged spots.
5. The causal and graph-based waterlogging disaster risk assessment system according to claim 1, wherein the causal and or relational model of risk areas and waterlogging points comprises:
each risk area is represented as a tree structure in a causal and/or relational model, and the risk areas serve as root nodes; each risk area is divided into a plurality of sub-areas which are used as branch nodes; each sub-area comprises a plurality of waterlogging points serving as leaf nodes;
Judging that the waterlogging event occurs at the waterlogging point if the waterlogging depth of the waterlogging point exceeds a preset threshold value;
The waterlogging points and the subareas are in a relation, and waterlogging events occur in all the waterlogging points in the subareas, so that the subareas are judged to have waterlogging events; and if the subarea is or is related to the risk area, and a waterlogging event occurs in any subarea, judging that the waterlogging event occurs in the risk area where the subarea is positioned.
6. The causal and graph-based waterlogging disaster risk assessment system according to claim 5, wherein an edge between a branch node and a corresponding leaf node represents a probability of a waterlogging event occurring in the branch node when the leaf node has the waterlogging event; and when the branch node generates a waterlogging event, the edge between the root node and the corresponding branch node represents the probability of the occurrence of the waterlogging event by the root node.
7. The waterlogging disaster risk assessment system based on causal and graph according to claim 6, wherein the probability calculation method is as follows: the probability of the leaf node corresponding to the waterlogging point of the waterlogging event is set to be 1, the probability of the leaf node corresponding to the waterlogging point of the waterlogging event is not set to be 0, and the probability of each root node of the waterlogging event is calculated from bottom to top.
8. The causal and graph-based water logging disaster risk assessment system according to claim 1, wherein the loss value comprises: static loss values and dynamic loss values;
Calculating a static loss value for one time in a period of time according to the input static building information; and continuously calculating a dynamic loss value in real time according to the input dynamic flow information.
9. The system for evaluating risk of waterlogging disaster based on causal and graph according to claim 1, wherein the method for calculating the loss value comprises the following steps: the leaf node corresponding to the waterlogging point with the waterlogging event is set as the loss value, and the loss value of the leaf node corresponding to the waterlogging point without the waterlogging event is set as 0; according to the causal and or relational model, calculating a loss value of waterlogging of each branch node and each root node;
the calculation rule is as follows: for a branch node, its penalty value is the sum of the penalty values of all its corresponding leaf nodes; for a root node, its penalty value is the maximum of all its corresponding branch node penalty values.
10. The system for evaluating risk of waterlogging disaster based on causal and graph according to claim 1, wherein the expected loss value of the corresponding risk area is a product of area node loss value and area node waterlogging probability.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410425548.4A CN118037062A (en) | 2024-04-10 | 2024-04-10 | Waterlogging disaster risk assessment system based on causal sum or graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410425548.4A CN118037062A (en) | 2024-04-10 | 2024-04-10 | Waterlogging disaster risk assessment system based on causal sum or graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118037062A true CN118037062A (en) | 2024-05-14 |
Family
ID=90997153
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410425548.4A Pending CN118037062A (en) | 2024-04-10 | 2024-04-10 | Waterlogging disaster risk assessment system based on causal sum or graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118037062A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778648A (en) * | 2015-05-06 | 2015-07-15 | 北京国电经纬工程技术有限公司 | Waterlogging warning system and method |
| CN113256138A (en) * | 2021-06-01 | 2021-08-13 | 安徽建筑大学 | Flood disaster risk assessment method based on heterogeneous multi-scale monitoring data |
| CN114595764A (en) * | 2022-03-09 | 2022-06-07 | 河南工业大学 | Method and system for acquiring influence degree of urban factors on inland inundation disaster loss |
| WO2023016036A1 (en) * | 2021-08-12 | 2023-02-16 | 中交第四航务工程勘察设计院有限公司 | Multi-factor composite early warning and forecasting method for municipal road ponding |
| CN117764395A (en) * | 2023-12-27 | 2024-03-26 | 暗物质(北京)智能科技有限公司 | Accident prevention policy determination method, device, equipment and readable storage medium |
-
2024
- 2024-04-10 CN CN202410425548.4A patent/CN118037062A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104778648A (en) * | 2015-05-06 | 2015-07-15 | 北京国电经纬工程技术有限公司 | Waterlogging warning system and method |
| CN113256138A (en) * | 2021-06-01 | 2021-08-13 | 安徽建筑大学 | Flood disaster risk assessment method based on heterogeneous multi-scale monitoring data |
| WO2023016036A1 (en) * | 2021-08-12 | 2023-02-16 | 中交第四航务工程勘察设计院有限公司 | Multi-factor composite early warning and forecasting method for municipal road ponding |
| CN114595764A (en) * | 2022-03-09 | 2022-06-07 | 河南工业大学 | Method and system for acquiring influence degree of urban factors on inland inundation disaster loss |
| CN117764395A (en) * | 2023-12-27 | 2024-03-26 | 暗物质(北京)智能科技有限公司 | Accident prevention policy determination method, device, equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tsakiris et al. | A system-based paradigm of drought analysis for operational management | |
| CN110633865A (en) | Urban ponding prediction and safety early warning system based on drainage model | |
| CN113434565A (en) | Water conservancy flood control drought and waterlogging prevention comprehensive disaster reduction platform system based on CIM platform | |
| KR102473442B1 (en) | Method for calculating flood damage and system thereof | |
| CN115099677B (en) | Tailing pond safety production risk grading early warning method | |
| CN118013232B (en) | Large hydraulic engineering water level monitoring method and system based on artificial intelligence | |
| Lagadec et al. | A surface runoff mapping method for optimizing risk assessment on railways | |
| Zhang et al. | A multi-strategy-mode waterlogging-prediction framework for urban flood depth | |
| Cotti et al. | An integrated multi-risk assessment for floods and drought in the Marrakech-Safi region (Morocco) | |
| Azizi et al. | Urban pluvial flood risk assessment: challenges and opportunities for improvement using a community-based approach | |
| CN117973912A (en) | Small drainage basin dynamic risk assessment method and device based on real-time rainfall event | |
| Braud et al. | A method to use proxy data of runoff-related impacts for the evaluation of a model mapping intense storm runoff hazard: application to the railway context | |
| Savic et al. | Intelligent urban water infrastructure management | |
| Zhou et al. | Real‐time prediction and ponding process early warning method at urban flood points based on different deep learning methods | |
| CN110414027A (en) | A kind of data processing method suitable for flood forecasting system | |
| KR101297979B1 (en) | Flood hazard analysis system considering geostatistics and climate change and method thereof | |
| Barclay et al. | Assessment of advanced LiDAR based tools for enhanced flood prediction | |
| CN118037062A (en) | Waterlogging disaster risk assessment system based on causal sum or graph | |
| Chen et al. | Risk Driven Analysis of Maintenance for a Large-scale Drainage System. | |
| Santoro et al. | The Role of Stakeholders’ Risk Perception in Water Management Policies. A Case-Study Comparison in Southern Italy | |
| Wang et al. | Route selection for opportunity-sensing and prediction of waterlogging | |
| Abiri | Assessment of Flood Risks in Ifo Local Government Area of Ogun State | |
| GAMBOA et al. | Network Analysis of Disaster Response Routes for Flooding: the case of Cagayan de Oro City, Philippines | |
| Zhang et al. | Characteristics and risk management of urban surface flooding in Guangzhou, China: Insights from 2022 ground monitoring | |
| Martinić | INOPIA model for drought forecast and its consequences on water resources–example of the City of Foligno in Italy |
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 |