Flood detection method, system and equipment and storage medium
By using machine learning models to construct flood risk factor models and river flood peak flow prediction models, the shortcomings in parameter calibration and dynamic adaptation in the existing technology are solved, and more efficient and accurate flood prediction is achieved.
Patent Information
- Application Number
- CN202510130465.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-05
- Publication Date
- 2025-05-23
AI Technical Summary
The existing flood prediction technology has shortcomings in parameter calibration and dynamic adaptation. The physical model method has high requirements for parameters and is complex in calculations, while the statistical model method relies on historical data and cannot capture unknown extreme weather events.
Machine learning models (such as random forest regression, long and short-term memory networks and support vector machines) are used to construct flood risk factor models, river flood peak flow prediction models and flood occurrence probability prediction models, and dynamically optimize parameters to adapt to rapidly changing environmental conditions.
It improves the dynamic adaptability of flood prediction and the ability to describe complex nonlinear relationships, which not only retains physical interpretability, but also enhances prediction accuracy.
Smart Images
Figure CN120031379A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a flood detection method, system, equipment and storage medium, belonging to the technical field of natural disaster prediction. Background Art
[0002] Current flood prediction technologies mainly include physical model method and statistical model method.
[0003] The physical model method is based on the basic theories of hydrology and hydraulics, and uses a series of mathematical formulas to model and calculate processes such as rainfall, evaporation, runoff, and river confluence in the basin. Typical models include: SWAT model, HEC-HMS model, which has strong physical significance and strong interpretability, but has extremely high parameter requirements and requires a large amount of accurate terrain, hydrological and meteorological data. At the same time, the calculation is complex, the calibration of model parameters is time-consuming, and it is difficult to dynamically adapt to rapidly changing weather and basin conditions.
[0004] The statistical model method uses historical data to construct statistical relationship models between rainfall and runoff, flow and flood risk, such as multivariate linear regression and time series analysis. It is simple to implement and effective for small-scale areas. However, it relies on historical data, cannot capture unknown extreme weather events, has limited ability to describe nonlinear relationships, and has insufficient prediction accuracy under complex conditions. Summary of the invention
[0005] In order to solve the above problems existing in the prior art, the present invention proposes a flood detection method, system, device and storage medium.
[0006] The technical solution of the present invention is as follows:
[0007] In one aspect, the present invention provides a flood detection method, comprising the following steps:
[0008] Collect regional meteorological data, topographic data, and hydrological data and pre-process them;
[0009] Construct a flood risk factor model to calculate the flood risk factor of the current area based on the meteorological data and terrain data of the current area;
[0010] Construct a river flood peak flow prediction model to predict the river flood peak flow in the current area based on the meteorological data, topographic data and hydrological data of the current area;
[0011] A flood probability prediction model is constructed, and the flood risk factors of the current area and the peak flow of the river are input into the model to obtain the flood probability of the current area.
[0012] As a preferred embodiment of the present invention, the flood risk factor model is optimized by a random forest regression model, as shown in the following formula:
[0013]
[0014] Among them: F t represents the flood risk factor of the current area at time t; P t represents the rainfall in the current area at time t; T t Indicates the temperature of the current area at time t; H t Indicates the humidity of the current area at time t; W t Represents the wind speed in the current area at time t; R t represents the evaporation of the current region at time t; A represents the watershed area of the current region; S represents the slope factor of the current region; K s Indicates the soil permeability coefficient of the current area; α 1 , α 2 , α 3 , β 1 , β 2 Both represent adjustment coefficients, which are optimized by random forest regression model.
[0015] As a preferred embodiment of the present invention, the river peak flow prediction model is constructed by a long short-term memory network, as shown in the following formula:
[0016]
[0017] Where: Q t represents the peak flow of the river at time t in the current area output by the long short-term memory network; Q t-1 represents the peak flow of the river at time t-1 in the current area output by the long short-term memory network; C t V represents the river transport capacity of the current region at time t; t represents the reservoir water storage capacity at the current time t in the current region; γ 1 , γ 2 , γ 3 Represents the empirical coefficient.
[0018] As a preferred embodiment of the present invention, the flood occurrence probability prediction model is constructed based on a support vector machine, as shown in the following formula:
[0019]
[0020] Where: P f Indicates the probability of flooding in the current area; Represents the historical average rainfall in the current area; P σ represents the standard deviation of historical rainfall in the current region; M represents the triggering factor of historical flood events; δ 1 ,δ 2 ,δ 3 ,δ4 Represents the weight coefficient.
[0021] On the other hand, the present invention also provides a flood detection system, including a data acquisition module, a flood risk factor calculation module, a river flood peak flow calculation module and a flood occurrence probability prediction module;
[0022] The data acquisition module is used to collect regional meteorological data, topographic data and hydrological data and perform preprocessing;
[0023] The flood risk factor calculation module is used to construct a flood risk factor model and calculate the flood risk factor of the current area based on the meteorological data and terrain data of the current area;
[0024] The river peak flow calculation module is used to construct a river peak flow prediction model to predict the river peak flow in the current area based on the meteorological data, topographic data and hydrological data of the current area;
[0025] The flood occurrence probability prediction module is used to construct a flood occurrence probability prediction model, and the flood risk factor of the current area and the river flood peak flow are input into the model to obtain the flood occurrence probability of the current area.
[0026] As a preferred embodiment of the present invention, the flood risk factor model is optimized by a random forest regression model, as shown in the following formula:
[0027]
[0028] Among them: F t represents the flood risk factor of the current area at time t; P t represents the rainfall in the current area at time t; T t Indicates the temperature of the current area at time t; H t Indicates the humidity of the current area at time t; W t Represents the wind speed in the current area at time t; R t represents the evaporation of the current region at time t; A represents the watershed area of the current region; S represents the slope factor of the current region; K s Indicates the soil permeability coefficient of the current area; α 1 , α 2 , α 3 , β 1 , β 2 Both represent adjustment coefficients, which are optimized by random forest regression model.
[0029] As a preferred embodiment of the present invention, the river peak flow prediction model is constructed by a long short-term memory network, as shown in the following formula:
[0030]
[0031] Where: Q t represents the peak flow of the river at time t in the current area output by the long short-term memory network; Q t-1 represents the peak flow of the river at time t-1 in the current area output by the long short-term memory network; C t V represents the river transport capacity of the current region at time t; t represents the reservoir water storage capacity at the current time t in the current region; γ 1 , γ 2 , γ 3 Represents the empirical coefficient.
[0032] As a preferred embodiment of the present invention, the flood occurrence probability prediction model is constructed based on a support vector machine, as shown in the following formula:
[0033]
[0034] Where: P f Indicates the probability of flooding in the current area; Represents the historical average rainfall in the current area; P σ represents the standard deviation of historical rainfall in the current region; M represents the triggering factor of historical flood events; δ 1 ,δ 2 ,δ 3 ,δ 4 Represents the weight coefficient.
[0035] On the other hand, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.
[0036] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.
[0037] The present invention has the following beneficial effects:
[0038] 1. Based on the traditional flood prediction formula, this solution of the present invention uses a machine learning model to dynamically optimize the parameters of the formula, which not only retains the physical interpretability but also enhances the ability to describe complex nonlinear relationships.
[0039] 2. The present invention uses a machine learning model to adjust parameters in real time to adapt to rapidly changing environmental conditions and improve the dynamic adaptability of the model. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION
[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0042] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.
[0043] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0044] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.
[0045] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.
[0046] Embodiment 1:
[0047] See also Figure 1 , a flood detection method, comprising the following steps:
[0048] Collect regional meteorological data, topographic data, and hydrological data and pre-process them;
[0049] Construct a flood risk factor model to calculate the flood risk factor of the current area based on the meteorological data and terrain data of the current area;
[0050] Construct a river flood peak flow prediction model to predict the river flood peak flow in the current area based on the meteorological data, topographic data and hydrological data of the current area;
[0051] A flood probability prediction model is constructed, and the flood risk factors of the current area and the peak flow of the river are input into the model to obtain the flood probability of the current area.
[0052] As a preferred implementation mode of this embodiment, the meteorological data includes the real-time rainfall, temperature, humidity, wind speed, evaporation and historical average rainfall of the region; the topographic data includes the watershed area and soil permeability of the region; and the hydrological data includes the reservoir water storage capacity and river flow.
[0053] As a preferred implementation of this embodiment, the flood risk factor model is optimized by using a random forest regression model, as shown in the following formula:
[0054]
[0055] Among them: F t represents the flood risk factor of the current area at time t; P t represents the rainfall in the current area at time t; T t Indicates the temperature of the current area at time t; H t Indicates the humidity of the current area at time t; W t Represents the wind speed in the current area at time t; R t represents the evaporation of the current area at time t; A represents the watershed area of the current area; S represents the slope factor of the current area, which is calculated using the Digital Elevation Model (DEM) data and is usually standardized to a range of 0 to 1; K s Indicates the soil permeability coefficient of the current area; α 1 , α 2 , α 3 , β 1 , β 2 All represent adjustment coefficients, which are optimized by random forest regression model;
[0056] As a preferred implementation of this embodiment, the river peak flow prediction model is constructed by a long short-term memory network, as shown in the following formula:
[0057]
[0058] Where: Q t represents the peak flow of the river at time t in the current area output by the long short-term memory network; Q t-1 represents the peak flow of the river at time t-1 in the current area output by the long short-term memory network; C t V represents the river transport capacity of the current region at time t; t represents the reservoir water storage capacity at the current time t in the current region; γ 1 , γ 2 , γ 3 represents the empirical coefficient;
[0059] The calculation formula of the river transport capacity is:
[0060]
[0061] Where: k represents the empirical coefficient, which is determined according to regional characteristics; C A represents the cross-sectional area of the river; C s Indicates the river slope; h t represents the water depth of the river at time t;
[0062] As a preferred implementation of this embodiment, the flood occurrence probability prediction model is constructed based on a support vector machine, as shown in the following formula:
[0063]
[0064] Where: P f Indicates the probability of flooding in the current area; Represents the historical average rainfall in the current area; P σ represents the standard deviation of historical rainfall in the current region; M represents the triggering factor of historical flood events; δ 1 , δ 2 , δ 3 , δ 4 represents the weight coefficient;
[0065] The calculation steps of the trigger factor of the historical flood event are as follows:
[0066] Calculate rainfall similarity, river flow similarity, time similarity, and topography / watershed similarity between the current region and historical flood events;
[0067] The rainfall similarity φ P The specific formula is as follows:
[0068]
[0069] Where: P i represents the rainfall of the i-th flood event in history;
[0070] The river flow similarity φ Q The specific formula is as follows:
[0071]
[0072] Where: Q i represents the initial river flood peak flow of the i-th flood event in history;
[0073] The temporal similarity φ T The specific formula is as follows:
[0074]
[0075] Where: t i represents the time of occurrence of the i-th flood event in history; τ represents the time scale parameter, which is used to measure the impact of time difference on similarity;
[0076] The terrain / watershed similarity φ L The specific formula is as follows:
[0077]
[0078] Where: S t Indicates the regional slope factor at the current moment; S i represents the regional slope factor of the i-th flood event in history; S max represents the maximum slope in the study area;
[0079] The triggering factor of historical flood events is obtained by weighted summing up the rainfall similarity, river flow similarity, time similarity and terrain / watershed similarity between the current area and historical flood events.
[0080] Embodiment 2:
[0081] A flood detection system, comprising a data acquisition module, a flood risk factor calculation module, a river flood peak flow calculation module and a flood occurrence probability prediction module;
[0082] The data acquisition module is used to collect regional meteorological data, topographic data and hydrological data and perform preprocessing;
[0083] The flood risk factor calculation module is used to construct a flood risk factor model and calculate the flood risk factor of the current area based on the meteorological data and terrain data of the current area;
[0084] The river peak flow calculation module is used to construct a river peak flow prediction model to predict the river peak flow in the current area based on the meteorological data, topographic data and hydrological data of the current area;
[0085] The flood occurrence probability prediction module is used to construct a flood occurrence probability prediction model, and the flood risk factor of the current area and the river flood peak flow are input into the model to obtain the flood occurrence probability of the current area.
[0086] As a preferred implementation of this embodiment, the flood risk factor model is optimized by using a random forest regression model, as shown in the following formula:
[0087]
[0088] Among them: F t represents the flood risk factor of the current area at time t; P trepresents the rainfall in the current area at time t; T t Indicates the temperature of the current area at time t; H t Indicates the humidity of the current area at time t; W t Represents the wind speed in the current area at time t; R t represents the evaporation of the current region at time t; A represents the watershed area of the current region; S represents the slope factor of the current region; K s Indicates the soil permeability coefficient of the current area; α 1 , α 2 , α 3 , β 1 , β 2 Both represent adjustment coefficients, which are optimized by random forest regression model.
[0089] As a preferred implementation of this embodiment, the river peak flow prediction model is constructed by a long short-term memory network, as shown in the following formula:
[0090]
[0091] Where: Q t represents the peak flow of the river at time t in the current area output by the long short-term memory network; Q t-1 represents the peak flow of the river at time t-1 in the current area output by the long short-term memory network; C t V represents the river transport capacity of the current region at time t; t represents the reservoir water storage capacity in the current region at time t; γ 1 , γ 2 , γ 3 Represents the empirical coefficient.
[0092] As a preferred implementation of this embodiment, the flood occurrence probability prediction model is constructed based on a support vector machine, as shown in the following formula:
[0093]
[0094] Where: P f Indicates the probability of flooding in the current area; Represents the historical average rainfall in the current area; P σ represents the standard deviation of historical rainfall in the current region; M represents the triggering factor of historical flood events; δ 1 , δ 2 , δ 3 , δ 4 Represents the weight coefficient.
[0095] The system is used to implement the method in Example 1, which will not be described in detail here.
[0096] Embodiment three:
[0097] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.
[0098] Embodiment 4:
[0099] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.
[0100] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.
[0101] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0102] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0103] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.
[0104] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.
Claims
1. A flood detection method, characterized in that: The following steps are involved: Collect regional meteorological data, topographic data, and hydrological data and pre-process them; Construct a flood risk factor model to calculate the flood risk factor of the current area based on the meteorological data and terrain data of the current area; Construct a river flood peak flow prediction model to predict the river flood peak flow in the current area based on the meteorological data, topographic data and hydrological data of the current area; A flood probability prediction model is constructed, and the flood risk factors of the current area and the peak flow of the river are input into the model to obtain the flood probability of the current area.
2. A flood detection method according to claim 1, characterized in that: The flood risk factor model is optimized by using a random forest regression model, as shown in the following formula: Among them: F t represents the flood risk factor of the current area at time t; P t represents the rainfall in the current area at time t; T t Indicates the temperature of the current area at time t; H t Indicates the humidity of the current area at time t; W t Represents the wind speed in the current area at time t; R t represents the evaporation of the current region at time t; A represents the watershed area of the current region; S represents the slope factor of the current region; K s represents the soil permeability coefficient of the current area; α1, α2, α3, β1, and β2 all represent adjustment coefficients, which are optimized by the random forest regression model.
3. A flood detection method according to claim 2, characterized in that: The river flood peak flow prediction model is constructed by a long short-term memory network, as shown in the following formula: Where: Q t represents the peak flow of the river at time t in the current area output by the long short-term memory network; Q t-1 represents the peak flow of the river at time t-1 in the current area output by the long short-term memory network; C t V represents the river transport capacity of the current region at time t; t represents the reservoir water storage capacity in the current area at time t; γ1, γ2, and γ3 represent empirical coefficients.
4. A flood detection method according to claim 3, characterized in that: The flood occurrence probability prediction model is constructed based on the support vector machine, as shown in the following formula: Where: P f Indicates the probability of flooding in the current area; Represents the historical average rainfall in the current area; P σ represents the standard deviation of historical rainfall in the current area; M represents the triggering factor of historical flood events; δ1, δ2, δ3, and δ4 represent weight coefficients.
5. A flood detection system, characterized in that: It includes data acquisition module, flood risk factor calculation module, river flood peak flow calculation module and flood occurrence probability prediction module; The data acquisition module is used to collect regional meteorological data, topographic data and hydrological data and perform preprocessing; The flood risk factor calculation module is used to construct a flood risk factor model and calculate the flood risk factor of the current area based on the meteorological data and terrain data of the current area; The river peak flow calculation module is used to construct a river peak flow prediction model to predict the river peak flow in the current area based on the meteorological data, topographic data and hydrological data of the current area; The flood occurrence probability prediction module is used to construct a flood occurrence probability prediction model, and the flood risk factor of the current area and the river flood peak flow are input into the model to obtain the flood occurrence probability of the current area.
6. A flood detection system according to claim 5, characterized in that: The flood risk factor model is optimized by using a random forest regression model, as shown in the following formula: Among them: F t represents the flood risk factor of the current area at time t; P t represents the rainfall in the current area at time t; T t Indicates the temperature of the current area at time t; H t Indicates the humidity of the current area at time t; W t Represents the wind speed in the current area at time t; R t represents the evaporation of the current region at time t; A represents the watershed area of the current region; S represents the slope factor of the current region; K s represents the soil permeability coefficient of the current area; α1, α2, α3, β1, and β2 all represent adjustment coefficients, which are optimized by the random forest regression model.
7. A flood detection system according to claim 6, characterized in that: The river flood peak flow prediction model is constructed by a long short-term memory network, as shown in the following formula: Where: Q t represents the peak flow of the river at time t in the current area output by the long short-term memory network; Q t-1 represents the peak flow of the river at time t-1 in the current area output by the long short-term memory network; C t V represents the river transport capacity of the current region at time t; t represents the reservoir water storage capacity in the current area at time t; γ1, γ2, and γ3 represent empirical coefficients.
8. A flood detection system according to claim 7, characterized in that: The flood occurrence probability prediction model is constructed based on the support vector machine, as shown in the following formula: Where: P f Indicates the probability of flooding in the current area; Represents the historical average rainfall in the current area; P σ represents the standard deviation of historical rainfall in the current area; M represents the triggering factor of historical flood events; δ1, δ2, δ3, and δ4 represent weight coefficients.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.