Mountain torrent disaster early warning method and system

Abstract

The invention discloses a mountain torrent disaster early warning method and system. The method comprises the following steps: acquiring cloud layer image data; processing the cloud layer image data based on a pre-trained deep learning model to obtain a predicted rainfall sequence; a hydrological and hydrodynamic model is constructed, scene simulation is carried out, and disaster threshold rainfall is delimited; and performing early warning in combination with the predicted rainfall sequence and the disaster threshold rainfall. The system comprises an image acquisition module, a rainfall prediction module, a threshold determination module and an early warning module. According to the invention, mountain torrent disaster early warning can be carried out in advance, important disaster relief and risk avoiding time can be won for mountain torrent disasters, and the rainfall prediction module is combined with air pressure observation and a cloud layer rainfall estimation method based on deep learning, so that the prediction precision is well guaranteed. The method can be widely applied to the field of natural disaster early warning.

Description

Technical Field

[0001] The present invention relates to the field of natural disaster early warning, and in particular to a flash flood disaster early warning method and system. Background Art

[0002] Flash floods are sudden floods caused by heavy rainfall in small and medium-sized river basins in mountainous areas. They are sudden and extremely destructive. As one of the most serious natural disasters in the world, flash floods pose a huge threat to human society and the natural environment. With the impact of climate change, flash floods are more frequent and their destructive power is increasing.

[0003] At present, flash flood prediction mainly relies on meteorological observation data, combined with hydrological models to achieve flash flood warning and forecast. This flash flood prediction method has obvious shortcomings in the forecast period. Flash floods often occur when disaster warnings are issued, making it difficult to provide strong protection for disaster prevention and risk avoidance. Summary of the invention

[0004] In view of this, in order to solve the technical problem that most of the existing flash flood disaster warning methods rely on real-time rainfall data, which makes it difficult to foresee the occurrence of flash flood disasters early, the present invention proposes a flash flood disaster warning method, which includes the following steps:

[0005] Acquire cloud image data;

[0006] Processing the cloud image data based on a pre-trained deep learning model to obtain a predicted rainfall sequence;

[0007] Construct hydrological and hydrodynamic models and conduct scenario simulations to define the threshold rainfall for disasters;

[0008] An early warning is issued in combination with the predicted rainfall sequence and the disaster threshold rainfall.

[0009] In some embodiments, it also includes:

[0010] Monitor air pressure data to improve rainfall forecast accuracy.

[0011] Through this preferred step, the monitored atmospheric pressure is also sent to the server. Combining cloud photography with dynamic air pressure monitoring can greatly improve the accuracy of rainfall prediction.

[0012] In some embodiments, the cloud image data includes historical observation data and real-time cloud photography data, and the step of processing the cloud image data based on the pre-trained deep learning model to obtain the predicted rainfall sequence specifically includes:

[0013] Calculating the spatiotemporal sequence of clear sky background brightness based on the recent historical observation data;

[0014] According to the real-time observation data, the data is divided into a cloud area and a clear sky area;

[0015] Extracting brightness values ​​from the clear sky area and performing spatiotemporal interpolation on the cloud area to obtain a clear sky background brightness sequence;

[0016] Subtracting brightness from the real-time cloud photography data and the clear sky background brightness sequence to obtain corrected cloud brightness;

[0017] The corrected cloud brightness is input into a pre-trained deep learning model to output a predicted rainfall sequence.

[0018] The above rainfall prediction method is applicable to both daytime and nighttime.

[0019] Through this preferred embodiment, combined with continuous photographic observations, the clear sky background brightness at each moment is calculated through the spatiotemporal interpolation method. The background brightness calculation result includes the brightness of contributing factors such as light scattering, which can more accurately match the actual situation and has higher reliability.

[0020] In some embodiments, the step of constructing a hydrological and hydrodynamic model and performing scenario simulation to define the threshold rainfall for disasters specifically includes:

[0021] Obtain the underlying surface information of the target area;

[0022] constructing a hydrological dynamic model according to the underlying surface information;

[0023] A simulation is performed based on the hydrological dynamic model and a preset rainfall scenario to determine the threshold rainfall for disasters.

[0024] Through this preferred step, the above hydrological and hydrodynamic simulation is used as a pre-simulation to calculate the critical rainfall that causes the disaster as a characteristic signal of the flash flood disaster, so that it has disaster predictability. However, the existing flash flood warning technology mainly relies on real-time hydrological and hydrodynamic simulation when rainfall occurs to predict the disaster, and such prediction is too delayed.

[0025] In some embodiments, the hydrodynamic model includes a runoff generation module and a runoff confluence module.

[0026] The hydrological and hydrodynamic models used in existing flash flood simulations are relatively traditional and lack consideration of the impact of soil moisture on runoff generation and confluence. The hydrological and hydrodynamic simulation in this embodiment will calculate the change of soil moisture over time based on rainfall to achieve dynamic changes in the runoff generation and confluence model.

[0027] The present invention also proposes a flash flood disaster early warning system, the system comprising:

[0028] An image acquisition module, used for acquiring cloud image data;

[0029] A rainfall prediction module processes the cloud image data based on a pre-trained deep learning model to obtain a predicted rainfall sequence;

[0030] The threshold determination module is used to construct a hydrological and hydrodynamic model and conduct scenario simulations to define the threshold rainfall for disasters;

[0031] The early warning module is used to provide early warning by combining the predicted rainfall sequence and the disaster threshold rainfall.

[0032] Based on the above scheme, the present invention provides a flash flood disaster warning method and system, which uses a photographic monitoring element to obtain cloud dynamic image data, combines a barometer element to monitor the atmospheric pressure dynamic data, inputs the above input data into a deep learning model to estimate the predicted rainfall sequence, and combines the warning rainfall pre-simulated by the hydrological and hydrodynamic model to determine whether a flash flood disaster will occur, and ultimately realizes early signal recognition and warning of flash flood disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a flow chart of the steps of a flash flood disaster early warning method of the present invention;

[0034] Figure 2 is a schematic diagram of the structure of a cloud photography data acquisition device according to an embodiment of the present invention;

[0035] Figure 3 It is a schematic diagram of the structure of the deep learning model of an embodiment of the present invention;

[0036] Figure 4 is an equivalent schematic diagram of a confluence module according to an embodiment of the present invention;

[0037] Figure 5 It is a structural block diagram of a flash flood disaster early warning system of the present invention; DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0039] It should be noted that, for the convenience of description, only the parts related to the relevant invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0040] It should be understood that the "system", "device", "unit" and / or "module" used in this application is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the word can be replaced by other expressions.

[0041] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "a kind" and / or "the" do not refer to the singular, but also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements. The elements defined by the sentence "includes a..." do not exclude the existence of other identical elements in the process, method, commodity or device that includes the elements.

[0042] In the description of the embodiments of the present application, "plurality" means two or more than two. The following terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0043] In addition, flow charts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, the various steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0044] Reference Figure 1 , is a flow chart of an optional example of a flash flood disaster warning method proposed in the present invention, which can be applied to computer equipment. The warning method proposed in this embodiment may include but is not limited to the following steps:

[0045] Step S1, obtaining cloud layer image data;

[0046] Step S2, processing the cloud image data based on a pre-trained deep learning model to obtain a predicted rainfall sequence;

[0047] Step S3, constructing a hydrological and hydrodynamic model and conducting scenario simulation to define the threshold rainfall for disasters;

[0048] Step S4: issuing an early warning in combination with the predicted rainfall sequence and the disaster threshold rainfall.

[0049] In some feasible embodiments, the step S1 specifically includes:

[0050] Use photographic acquisition components to continuously obtain cloud photography dynamic data.

[0051] Among them, cloud photography data collection equipment refers to Figure 2 The working process is as follows: 1. The lens element obtains cloud photography data, and the barometer element obtains atmospheric pressure monitoring data; 2. The data is temporarily stored in the storage element; 3. The data is sent to the server via the network module; 4. When the transmission fails, the server sends a data request, and the device resends the relevant data when it receives the data request; 5. Delete expired data to release storage space. 6. The parameters of the device, such as lens parameters, power parameters, etc., can be monitored and set through the networking function to achieve remote maintenance of the device.

[0052] The power supply solution is suitable for mountainous areas: for areas with mains electricity, you can choose to install it on the roof of a building or a street light pole and use the mains electricity to supply power; for areas without mains electricity, you can choose to use a photovoltaic kit, which will be powered by photovoltaic panels during the day and charge the batteries in the equipment, and use batteries to supply power at night.

[0053] The device of this embodiment adopts a fully sealed design to avoid the impact of outdoor moisture, dust and insects on the device; the lens cover adopts a hydrophobic design to ensure that observation capabilities are still available during rain; the device has a heat dissipation module, and turns on the fan based on the temperature sensor to achieve internal air duct circulation, and discharges heat from the heat dissipation fins in the shade at the bottom to ensure that the inside of the device meets the working temperature conditions under the scorching sun.

[0054] In some feasible embodiments, it also includes:

[0055] Monitor air pressure data.

[0056] The above device contains a barometer, and the monitored atmospheric pressure is also sent to the server.

[0057] Traditional cloud photography observations only estimate the water content through cloud shape characteristics, and the accuracy of rainfall prediction is not high. The present invention combines cloud photography with dynamic air pressure monitoring, which can greatly improve the accuracy of rainfall prediction.

[0058] In some feasible embodiments, the step S2 specifically includes:

[0059] S2.1. Calculate the spatiotemporal sequence of clear sky background brightness based on the nearby historical observation data;

[0060] S2.2, dividing into a cloud area and a clear sky area according to the real-time observation data;

[0061] S2.3, extracting brightness values ​​from the clear sky area, and performing spatiotemporal interpolation on the cloud area to obtain a clear sky background brightness sequence;

[0062] S2.4, performing brightness subtraction based on the real-time cloud photography data and the clear sky background brightness sequence to obtain a corrected cloud brightness;

[0063] Among them, S2.1-S2.4 are data preprocessing steps. The server calculates the spatiotemporal sequence of the clear sky background brightness of each cloud photography device at 0:00 every day, and uses the continuous observation data of the past 24 hours to divide the image into cloud area and clear sky area according to the classification algorithm. The brightness value of the clear sky area (including the night sky) is extracted, and the spatiotemporal interpolation is performed on the part without clear sky to calculate the clear sky background brightness sequence at each moment of the 24 hours of the day. For the extreme case of continuous no clear sky, the previous clear sky background brightness calculation result is used.

[0064] When the server receives the real-time cloud photography data, it subtracts the clear sky background brightness calculated above from the real-time cloud photography brightness to obtain the corrected cloud brightness. The cloud brightness sequence at any time and within the past 24 hours is used as the input data for the next deep learning model.

[0065] The cloud photography data preprocessing method is characterized by using continuous clear sky observations near the 10th to complete the continuous change value of the clear sky background brightness for 24 hours on that day. Most of the existing radiation correction methods are based on the atmospheric transmission theory of solar radiation. Local areas are affected by complex near-ground influences (such as light scattering, etc.), and there is a large deviation between the actual background brightness and the theoretical radiation brightness. The above method combines continuous photography observations and calculates the clear sky background brightness at each moment through the spatiotemporal interpolation method. The background brightness calculation result includes the brightness of contribution factors such as light scattering, which can more accurately match the actual situation and has higher reliability.

[0066] S2.5. Input the corrected cloud brightness into a pre-trained deep learning model and output a predicted rainfall sequence.

[0067] Among them, the model architecture integrates convolutional neural network and long short-term memory network. The specific model structure is as follows Figure 3 As shown in the figure, the input data is a 12-hour cloud image sequence and an air pressure monitoring sequence. The LSTM layer is used to process the temporal dynamics of the cloud layer and the air pressure; the 3D convolution layer is used for cloud perception; the Dropout layer is used to prevent the model from overfitting; the middle layer is used to match the temporal dynamics of the cloud layer and the air pressure; and finally the fully connected layer is used to output the predicted rainfall sequence for the next 6 hours.

[0068] In some feasible embodiments, the prior training steps of the deep learning model are as follows:

[0069] Set up rainfall observation stations and cloud photography hardware equipment, conduct rainfall records, cloud photography observations and atmospheric pressure monitoring for a period of time, use the acquired rainfall records, cloud dynamic process data and atmospheric pressure dynamic process data to perform deep learning prior training and obtain a deep learning model. For areas with similar climatic conditions, the trained deep learning model can be used directly.

[0070] The above-mentioned deep learning model for cloud rainfall prediction is characterized by: the input data is background brightness, photographic images and atmospheric pressure, and the output data is the predicted rainfall sequence; in terms of model structure, it integrates convolutional neural networks and long short-term memory networks, has the ability to perceive the spatiotemporal dynamics of clouds, and combined with the perception of the dynamic process of air pressure, it can greatly improve the accuracy of rainfall prediction.

[0071] In some feasible embodiments, the step S3 specifically includes:

[0072] Before a disaster occurs, multiple rainfall scenarios are established in advance, and flash flood disaster drills are conducted in combination with hydrological and hydrodynamic models to clarify the conditions for flash flood disasters to occur in the target area (i.e., the rainfall threshold for disasters).

[0073] Among them, the hydrological and hydrodynamic model mainly includes the runoff generation module and the confluence module.

[0074] (1) The runoff generation module divides the underlying surface into permeable surface and impermeable surface. Permeable surfaces include grasslands, wetlands, and woodlands. On this underlying surface, the main flow generation is full storage, and the infiltration equation is as follows:

[0075]

[0076] A+P <W' mm hour:

[0077]

[0078] A+P>W' mm hour:

[0079] R PA =P-(WM-k·API)

[0080] Among them, API is the previous rainfall index, which represents the change of soil moisture over time, A is the original water storage capacity of the catchment unit (mm), P represents rainfall; W' mm is the maximum water storage capacity of the catchment unit (mm); k is the attenuation coefficient of the previous rainfall exponential given value; WM is the average water storage capacity of the catchment unit (mm); B is the uneven distribution of water storage capacity on the catchment unit; R PA is the flow rate of the permeable surface (mm).

[0081] Impervious surface refers to built-up areas such as roads. The infiltration formula of this underlying surface is as follows:

[0082]

[0083] In the formula, R DA is the flow rate of the direct impervious surface (mm); F is the infiltration volume (mm); f is the infiltration rate (mm / h); x is the duration of rainfall (h). In the model, rainfall within 4 hours after the rainfall time is defined as continuous rainfall; A DA , B DA and C DA These are all calculation parameters for infiltration rate.

[0084] Indirect impervious surface refers to the impervious surface in built-up areas such as buildings and roads where water flows through the permeable surface first and then drains to the stormwater pipe. The main innovation of this infiltration model is the introduction of API to improve the calculation of CN value in the SCS-CN model to adapt to different previous rainfall scenarios:

[0085] CN'=(a·API+b)·CN

[0086] Where CN' is the characteristic value of the improved runoff curve; a and b are empirical values ​​that can be determined by actual measurement or parameter adjustment.

[0087]

[0088] In the formula, R NDA is the indirect flow production from impervious surface; S is the loss rainfall.

[0089] (2) The confluence module simulates the process of net rainwater flowing from all parts of the basin to the outlet section. The model generalizes the basin into a nonlinear reservoir, such as Figure 4 As shown, the confluence is calculated by solving a system of equations consisting of the continuity equation and the Manning equation.

[0090] The water balance equation of a nonlinear reservoir is as follows:

[0091]

[0092] In the formula, d is the water depth, m; i is the rainfall intensity, mm / s; e is the surface evaporation rate, mm / s; f is the infiltration rate, mm / s; q is the surface runoff, mm / s;.

[0093] The surface runoff flow calculation formula (Manning formula) is as follows:

[0094]

[0095] Where, Q is the runoff (m3); n is the Manning coefficient; S is the basin slope; R X is the hydraulic radius (m); A X is the cross-sectional area of ​​nonlinear reservoir water flow (m2).

[0096] Where R X and A X The following formulas are used for calculation:

[0097] A X =W(dd s )

[0098] R X =dd s

[0099] Where W is the characteristic width of the basin (m); d is the water depth (m); and ds is the maximum depression water depth (m).

[0100] Dividing Q by the basin area, we can get the expression for the surface runoff flow q of the basin:

[0101]

[0102] In some feasible embodiments, the step S4 specifically includes:

[0103] The calculation results of the hydrological and hydrodynamic simulation of a certain mountainous basin show that flash floods will occur when the rainfall reaches 50mm; cloud photography data acquisition equipment is installed in the basin to conduct dynamic monitoring and prediction of rainfall; at a certain moment, it is recognized that a shower is about to occur and the expected rainfall exceeds the threshold of 50mm, that is, the early signal of flash floods has appeared, and a flash flood disaster warning is immediately issued.

[0104] The flash flood signal recognition and warning methods widely used in current projects, such as flash flood warning systems based on ground rain gauges, weather radars or remote sensing satellites, cannot take into account the construction cost, forecast period and accuracy, and have many limitations in practical applications. Based on the above scheme, the present invention has the characteristics of low cost, timely forecast and high accuracy, which has great advantages.

[0105] like Figure 5 As shown, a flash flood disaster warning system comprises:

[0106] An image acquisition module, used for acquiring cloud image data;

[0107] A rainfall prediction module processes the cloud image data based on a pre-trained deep learning model to obtain a predicted rainfall sequence;

[0108] The threshold determination module is used to construct a hydrological and hydrodynamic model and conduct scenario simulations to define the threshold rainfall for disasters;

[0109] The early warning module is used to provide early warning by combining the predicted rainfall sequence and the disaster threshold rainfall.

[0110] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0111] A flash flood disaster warning device:

[0112] at least one processor;

[0113] at least one memory for storing at least one program;

[0114] When the at least one program is executed by the at least one processor, the at least one processor implements the flash flood disaster warning method as described above.

[0115] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0116] A storage medium stores instructions executable by a processor, wherein the instructions executable by the processor are used to implement a flash flood disaster early warning method as described above when executed by the processor.

[0117] The contents of the above method embodiments are all applicable to the present storage medium embodiments. The functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0118] The above is a specific description of the preferred implementation of the present invention, but the invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A flash flood disaster early warning method, characterized in that: The following steps are involved: Acquire cloud image data; Processing the cloud image data based on a pre-trained deep learning model to obtain a predicted rainfall sequence; Construct hydrological and hydrodynamic models and conduct scenario simulations to define the threshold rainfall for disasters; An early warning is issued in combination with the predicted rainfall sequence and the disaster threshold rainfall.

2. A flash flood disaster early warning method according to claim 1, characterized in that: Also includes: Monitor air pressure data.

3. A flash flood disaster early warning method according to claim 1, characterized in that: The cloud image data includes recent historical observation data and real-time cloud photography data. The step of processing the cloud image data based on the pre-trained deep learning model to obtain a predicted rainfall sequence specifically includes: Calculating the spatiotemporal sequence of clear sky background brightness based on the recent historical observation data; According to the real-time observation data, the data is divided into a cloud area and a clear sky area; Extracting brightness values ​​from the clear sky area and performing spatiotemporal interpolation on the cloud area to obtain a clear sky background brightness sequence; Subtracting brightness from the real-time cloud photography data and the clear sky background brightness sequence to obtain corrected cloud brightness; The corrected cloud brightness is input into a pre-trained deep learning model to output a predicted rainfall sequence.

4. A flash flood disaster early warning method according to claim 1, characterized in that: The step of constructing a hydrological and hydrodynamic model and conducting scenario simulation to define the threshold rainfall for disasters specifically includes: Obtain the underlying surface information of the target area; constructing a hydrological dynamic model according to the underlying surface information; A simulation is performed based on the hydrological dynamic model and a preset rainfall scenario to determine the threshold rainfall for disasters.

5. A flash flood disaster early warning method according to claim 4, characterized in that: The hydrological dynamic model includes a flow generation module and a flow confluence module.

6. A flash flood disaster early warning method according to claim 5, characterized in that: In the runoff generation module, the underlying surface is divided into permeable surface, directly impermeable surface and indirectly impermeable surface, where: The infiltration equation for a permeable surface is as follows: A+P <W' mm hour: A+P>W' mm hour: R PA =P-(WM-k·API) Among them, API is the previous rainfall index, which represents the change of soil moisture over time, A is the original water storage capacity of the catchment unit, P represents rainfall; W' mm is the maximum water storage capacity of the catchment unit; k is the exponential attenuation coefficient of the previous rainfall at a given value; WM is the average water storage capacity of the catchment unit; B is the uneven distribution of water storage capacity on the catchment unit; R PA The flow rate is generated by the permeable surface; The infiltration equation for a directly impervious surface is as follows: Among them, R DA is the flow rate of direct impervious surface; F is the infiltration volume; f is the infiltration rate; x is the duration of rainfall; A DA , B DA and C DA are all calculation parameters of infiltration rate, Δt represents infiltration time, and P represents rainfall; The infiltration equation for an indirect impervious surface is as follows: CN'=(a·API+b)·CN Where, CN' is the characteristic value of the improved runoff curve; a and b are preset empirical values; In the formula, R NDA is the indirect flow production from impervious surface; S is the loss rainfall.

7. A flash flood disaster early warning method according to claim 6, characterized in that: In the confluence module, the formula for the surface runoff flow of the basin is expressed as follows: Where W is the characteristic width of the watershed; d is the depth of ponding; d s is the maximum depression storage depth; S is the basin slope; A represents the catchment area; n represents the roughness.

8. A flash flood disaster early warning system, characterized in that: include: An image acquisition module, used for acquiring cloud image data; A rainfall prediction module processes the cloud image data based on a pre-trained deep learning model to obtain a predicted rainfall sequence; The threshold determination module is used to construct a hydrological and hydrodynamic model and conduct scenario simulations to define the threshold rainfall for disasters; The early warning module is used to provide early warning by combining the predicted rainfall sequence and the disaster threshold rainfall.

9. A flash flood disaster warning device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a flash flood disaster warning method as described in any one of claims 1-7.

Images