Mountain torrent debris flow early warning method and device based on multivariate heterogeneous data

Abstract

The invention discloses a mountain torrent debris flow early warning method and device based on multivariate heterogeneous data, and relates to the technical field of disaster early warning. The method comprises the following steps: acquiring monitoring data in real time; determining a data source from which the monitoring data comes, and determining a disaster early warning algorithm or a disaster early warning model according to the data source; and inputting the monitoring data into the determined disaster early warning algorithm or disaster early warning model, and obtaining an early warning result of the mountain torrent and debris flow according to an output result. According to the embodiment provided by the invention, a disaster early warning algorithm or a disaster early warning model and a self-adaptive mechanism of monitoring data are provided, and the accuracy of mountain torrent debris flow early warning is improved.

Description

Technical Field

[0001] The present application relates to the technical field of disaster warning, and specifically to a flash flood and mud-rock flow warning method based on multi-dimensional heterogeneous data, a flash flood and mud-rock flow warning device based on multi-dimensional heterogeneous data, a computer-readable storage medium, and a computer program product. Background Art

[0002] Automated monitoring and early warning of flash floods and debris flows generally include warnings based on rainfall and warnings based on monitoring instrument data. Warnings based on rainfall are related to the specific conditions of the flash flood and debris flow channels, while in monitoring based on mud and water level height, there are data jumps and abnormal changes due to equipment status and external interference, which reduces the accuracy of the warning.

[0003] Flash flood and debris flow warning requires a large amount of relevant information, including: geological information of flash flood and debris flow basins, historical information of flash flood and debris flow areas, rainfall information related to flash flood and debris flow areas (including monitoring data of rain gauges, data produced by weather radar maps and satellite cloud maps), and actual monitoring data of water levels in channels through which flash flood and debris flow flows. Different flash flood and debris flow warning algorithms can be designed based on different data conditions, but due to the uneven distribution of data sources, communication and equipment health, monitoring instruments, insufficient coverage of monitoring instruments / radars in different regions, and the limited capabilities of warning algorithms corresponding to a single data source, there are problems such as the inability to obtain complete information in real time, insufficient monitoring data quality, data jumps, and different reliability and accuracy, which leads to inaccurate and untimely warning results. Summary of the invention

[0004] The purpose of the implementation mode of the present application is to provide a flash flood and mudslide warning method and device based on multi-heterogeneous data, which utilizes data sources of different dimensions, differently distributed, and different types of monitoring data, including a flash flood and mudslide warning method that combines mud water level monitoring and rainfall information of multiple dimensions. This can better improve the reliability of flash flood and mudslide warnings, reduce the possibility of false alarms, and at least solve some of the technical problems in the background technology.

[0005] In order to achieve the above-mentioned object, the first aspect of the present application provides a flash flood and mud-rock flow early warning method based on multivariate heterogeneous data, the method comprising:

[0006] Acquire monitoring data in real time; determine the data source from which the monitoring data comes, and determine a disaster warning algorithm or disaster warning model based on the data source; input the monitoring data into the determined disaster warning algorithm or disaster warning model, and obtain warning results for mountain torrents and mudslides based on the output results.

[0007] Optionally, determining the data source from which the monitoring data comes includes: distinguishing the data source of the monitoring data according to a generating device and / or data content of the monitoring data.

[0008] Optionally, determining the data source from which the monitoring data comes includes: if the monitoring data is mountain torrent debris flow mud water level height monitoring data, determining that the monitoring data comes from a first type of data source; if the monitoring data is rainfall data monitored by a rain gauge, determining that the monitoring data comes from a second type of data source; if the monitoring data is grid rainfall data obtained based on meteorological data conversion, determining that the monitoring data comes from a third type of data source.

[0009] Optionally, a disaster warning algorithm or disaster warning model is determined based on the data source, including: if the monitoring data comes from a single type of data source, determining the disaster warning algorithm corresponding to this type of data source according to a preset corresponding relationship; if the monitoring data comes from multiple types of data sources, determining the corresponding disaster warning model according to the combination of the multiple types of data sources.

[0010] Optionally, the disaster warning algorithm corresponding to the first type of data source includes: determining the numerical interval in which the monitoring data is located, each numerical interval is delimited by a maximum threshold and several intermediate threshold points and has a corresponding digital interval; linearly converting the monitoring data into a number within the digital interval of the corresponding numerical interval, and using the obtained number as the output of the disaster warning algorithm.

[0011] Optionally, the disaster warning algorithm corresponding to the second type of data source includes: calculating the ratio of the numerical value of each dimension in the monitoring data to the reference numerical value of the dimension, wherein the dimensions include at least two of rainfall, rainfall intensity and duration information; mapping the weighted sum of the ratios of all dimensions to a preset numerical range, and using the mapping result as the output of the disaster warning algorithm.

[0012] Optionally, the disaster warning algorithm corresponding to the third type of data source includes: determining the flood discharge capacity according to the geological conditions; converting the monitoring data into runoff data after basin confluence; and obtaining the output of the disaster warning algorithm based on the flood discharge capacity and runoff data.

[0013] Optionally, determining a disaster warning model according to a combination of the multiple types of data sources includes: combining different types of data sources in combination with their respective disaster warning algorithms to form a corresponding disaster warning model.

[0014] Optionally, the monitoring data is input into a determined disaster warning algorithm or disaster warning model, and a warning result for flash floods and mudslides is obtained based on the output result, including: if the data source is a single-category data source, the warning result is obtained based on the output of the disaster warning algorithm; if the data source is a multi-category data source, the weight is determined based on the characteristics of the monitoring data corresponding to each type of data source, and the result of each disaster warning algorithm in the disaster warning algorithm is weighted calculated based on the weight, so as to obtain the warning result based on the calculation result.

[0015] Optionally, weights are determined based on characteristics of the monitoring data corresponding to each type of data source, including: determining the weight of the monitoring data based on the quality of the monitoring data, and / or determining the weight of the monitoring data based on the reliability of the monitoring data, and / or determining the weight of the monitoring data based on the monitoring density of the monitoring data.

[0016] Optionally, the method further includes: generating an alarm corresponding to the risk level according to the early warning result.

[0017] In the second aspect of the present application, a flash flood and mud-rock flow warning device based on multi-heterogeneous data is also provided, which also includes: a data acquisition module for acquiring monitoring data in real time; a multi-source processing module for determining the data source from which the monitoring data comes, and determining a disaster warning algorithm or a disaster warning model based on the data source; and a result output module for inputting the monitoring data into the determined disaster warning algorithm or disaster warning model, and obtaining a warning result for the flash flood and mud-rock flow based on the output result.

[0018] In the third aspect of the present application, an electronic device is also provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the aforementioned flash flood and mudslide warning method based on multivariate heterogeneous data are implemented.

[0019] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein instructions are stored in the storage medium, and when the instructions are executed on a computer, the computer executes the steps of the aforementioned flash flood and mud-rock flow early warning method based on multivariate heterogeneous data.

[0020] In a fifth aspect of the present application, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the aforementioned flash flood and mud-rock flow early warning method based on multivariate heterogeneous data.

[0021] The above technical solution has at least the following beneficial effects:

[0022] The algorithm is automatically adjusted according to the data source and data quality, and different dimensions of data sources, different distributions, and different types of monitoring data are comprehensively utilized, including a flash flood and debris flow early warning method that combines mud and water level monitoring and multi-dimensional rainfall information, thereby realizing flash flood and debris flow early warning with multi-dimensional heterogeneous data, which can better improve the reliability of flash flood and debris flow early warning and reduce the possibility of false alarms.

[0023] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0025] Figure 1 The schematic diagram of the steps of the flash flood and mud-rock flow early warning method based on multivariate heterogeneous data in the embodiment of the present application is schematically shown;

[0026] Figure 2 The schematic diagram of the structure of the flash flood and mud-rock flow early warning device based on multivariate heterogeneous data according to the embodiment of the present application is shown schematically;

[0027] Figure 3 The internal structure of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the implementation methods of the present application clearer, the technical solutions in the implementation methods of the present application will be clearly and completely described below in conjunction with the drawings in the implementation methods of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the implementation methods of the present application, and are not used to limit the implementation methods of the present application. Based on the implementation methods in the present application, all other implementation methods obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0029] It should be noted that if the implementation methods of the present application involve directional indications (such as up, down, left, right, front, back...), such directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0030] In addition, if there are descriptions involving "first", "second", etc. in the implementation methods of this application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various implementation methods can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0031] Figure 1 The following is a schematic diagram showing the steps of a flash flood and mudslide early warning method based on multivariate heterogeneous data according to an embodiment of the present application. Figure 1 As shown, a flash flood and mud-rock flow early warning method based on multivariate heterogeneous data includes:

[0032] S01. Acquire monitoring data in real time. The monitoring data here refers to monitoring data on mountain torrents and debris flows, and mainly refers to data that have an impact on the occurrence and development of mountain torrents and debris flows, which comes from different monitoring technologies and monitoring methods.

[0033] S02. Determine the data source from which the monitoring data comes, and determine the disaster warning algorithm or disaster warning model based on the data source; different monitoring technologies generate different monitoring data, and different monitoring data require different processing processes. The data source here refers to the data source of the monitoring data, which includes but is not limited to the data generated by the sensor, obtained after analysis and summary, and inference and estimation based on existing information. Due to the different data sources of the monitoring data, different disaster warning algorithms or disaster warning models need to be determined to process the corresponding monitoring data.

[0034] S03. Input the monitoring data into the determined disaster warning algorithm or disaster warning model, and obtain the warning result of mountain torrents and mud-rock flows based on the output result. Input the monitoring data into the determined disaster warning algorithm or disaster warning model, and obtain the warning result of mountain torrents and mud-rock flows based on the output result of the disaster warning algorithm or disaster warning model.

[0035] Through the above implementation, the corresponding algorithm or model is determined based on the monitoring data of different data sources, which can comprehensively use the data of different data sources and adapt to the real-time changes of the monitoring data to improve the accuracy of the early warning results. This implementation avoids the problem of insufficient early warning reliability of a single data source and early warning model.

[0036] There are already early warning methods in the prior art that integrate multiple early warning results, but the premise is still to use the corresponding monitoring data to input into a pre-set model, and then fuse the multiple results output by the model to obtain the early warning result. There are also fusions of multiple early warning models in the prior art, but when using the fused early warning model, there is still a disadvantage of needing to limit the input monitoring data. The implementation method of the present application overcomes the above defects.

[0037] In some embodiments of the present application, determining the data source from which the monitoring data comes includes: distinguishing the data source of the monitoring data according to the generation device and / or data content of the monitoring data. For example, according to the generation device of the monitoring data, it can be divided into direct generation by sensors, obtained after sensor integration, and generated by data analysis equipment. According to the data content of the monitoring data, it can be divided into direct measurement data, grid rainfall data, and point rainfall data. The division method of the data source can be set by itself, and its purpose is to distinguish the monitoring data and affect the number of subsequent algorithms or the number of combinations of models.

[0038] In some embodiments of the present application, determining the data source from which the monitoring data comes includes: if the monitoring data is monitoring data of mud water level height of mountain torrents and debris flows, determining that the monitoring data comes from the first type of data source, which is direct monitoring data, including mud water level height data obtained by a mud water level meter, and data of mud water level exceeding a set threshold obtained by a line break meter; if the monitoring data is rainfall data monitored by a rain gauge, determining that the monitoring data comes from the second type of data source; this type of data is point rainfall data, obtained by deploying rain gauges in the drainage area of ​​mountain torrents and debris flow gullies; if the monitoring data is grid rainfall data obtained based on meteorological data conversion, determining that the monitoring data comes from the third type of data source. This type of data is grid rainfall data based on other sources, which may come from the following aspects: grid rainfall data obtained by converting radar map data using meteorological radar; grid rainfall data obtained by converting satellite data; grid rainfall data obtained by converting data after the fusion of meteorological radar data and satellite data. Since weather radar and satellite data may not be obtained in a timely and reliable manner in actual use, and it is difficult for weather radar to fully cover all areas, there are some places where weather radar data and satellite data cannot be obtained at the same time. At this time, the conversion algorithm will be selected according to the different data in the grid to obtain grid rainfall data in a larger range as much as possible. According to the data source, the conversion method can be selected: when there is only weather radar data, the radar echo grid is used to calculate the grid rainfall; when there is only satellite data, the satellite-related channel value grid data is used to calculate the grid rainfall; when both of the above two types of data exist, the fusion data of the two is used to calculate the grid rainfall. Among them, the reliability of point rainfall data (the second type of data source) is stronger than the grid rainfall data from other sources (the third type of data source). When the second and third types of data sources exist at the same time, this setting method can make certain trade-offs based on reliability.

[0039] In some embodiments of the present application, a disaster warning algorithm or disaster warning model is determined according to a data source, including: if the monitoring data comes from a single type of data source, the disaster warning algorithm corresponding to the data source is determined according to a preset corresponding relationship; for example, the corresponding relationship can be obtained by direct mapping, that is, the first type of data source corresponds to the first disaster warning algorithm, the second type of data source corresponds to the second disaster warning algorithm, the third type of data source corresponds to the third disaster warning algorithm, etc. If the monitoring data comes from multiple types of data sources, the corresponding disaster warning model is determined according to the combination of the multiple types of data sources. The corresponding relationship can also be obtained by direct mapping, or it can be determined by evaluating the evaluation value obtained after evaluating the monitoring data.

[0040] In some embodiments of the present application, the disaster warning algorithm corresponding to the first type of data source includes: determining the numerical interval in which the monitoring data is located, each numerical interval is delineated by a maximum threshold and several intermediate threshold points and has a corresponding digital interval; linearly converting the monitoring data to a number within the digital interval of the corresponding numerical interval, and using the obtained number as the output of the disaster warning algorithm. The alarm thresholds for different mountain torrents and debris flow gullies are different. The alarm thresholds are mainly determined by local geographical features and the results determined based on surveys or actual situation analysis, including basic data such as geographical information, geological conditions, historical disasters, rainfall distribution, etc. of different mountain torrents and debris flow gullies, combined with actual surveys to set the initial threshold, which can be adjusted according to actual conditions. Taking the aforementioned first type of data source as direct monitoring data as an example, when there is only this data source, the monitoring value of the monitoring data is directly used for warning. Taking the monitoring data as the mud water level height collected by the mud water level meter as an example, the corresponding score is calculated according to the mud water level height. The reference calculation method is: set 5 reference heights a, b, c, d, and e, e is the aforementioned maximum threshold, a, b, c, and d are the aforementioned intermediate threshold points, and when the measurement height interval is in the numerical interval of [0, a], it is linearly converted to 0 to 30 points, that is, the aforementioned digital interval. Similarly, when the numerical interval is [a, b], it is linearly converted to 30 to 50, the numerical interval is [b, c], it is linearly converted to 50 to 70 points, the numerical interval is [c, d], it is linearly converted to 70 to 90 points, and the numerical interval is [d, e], it is linearly converted to 90 to 100. If it is greater than e, it is 100 points. Finally, the score obtained after linear conversion is used as the output of the disaster warning algorithm. The mud water level thresholds corresponding to different levels of different mountain torrent debris flow gullies can be determined according to the specific conditions of different mountain torrent debris flow gullies.

[0041] In some embodiments of the present application, the disaster warning algorithm corresponding to the second type of data source includes: respectively calculating the ratio of the value of each dimension in the monitoring data to the reference value of the dimension, wherein the dimension includes at least two of rainfall, rainfall intensity and duration information; mapping the weighted sum of the ratios of all dimensions to a preset numerical interval, and using the mapping result as the output of the disaster warning algorithm. Taking the aforementioned second type of data source as point rainfall data as an example, when there is only the second type of data source, the rain gauge data is directly used, and the score is calculated according to the rainfall, rainfall intensity and duration information. The reference calculation method is: (α*rainfall intensity / reference rainfall intensity+β*rainfall / reference rainfall+γ*duration / reference duration)*100, α, β, γ are preset coefficients, the sum of which is 1, and is determined according to historical data or its degree of influence. When one of the rainfall, rainfall intensity and duration information does not exist, the non-existent item is set to 0 for calculation. When the score is greater than 100, it is cut to 100, and an early warning is issued according to the calculated score.

[0042] In some embodiments of the present application, the disaster warning algorithm corresponding to the third type of data source includes: determining the flood discharge capacity according to the geological conditions; converting the monitoring data into runoff data after the basin convergence; obtaining the output of the disaster warning algorithm according to the flood discharge capacity and the runoff data. Taking the aforementioned third type of data source as grid rainfall data as an example, when there is only the third type of data source, the grid rainfall data is converted into runoff data after the basin convergence in conjunction with the basin model and the confluence model, and the score is calculated according to the runoff and geological conditions. Reference calculation method: δ*runoff / flood discharge capacity determined by geological conditions*100, δ is an adjustment parameter set according to local conditions, used to calculate the score, which can be set to 2. When the calculated score is greater than 100, it is truncated to 100, and a warning is issued according to the calculated score.

[0043] In some embodiments of the present application, a disaster warning model is determined according to the combination of the multiple types of data sources, including: according to the combination of different types of data sources, the corresponding disaster warning model is combined in combination with their respective disaster warning algorithms. When the second type of data source and the third type of data source exist at the same time, the third type of data source is ignored; since the second type of data source is more reliable than the third type of data source, when the two data sources exist at the same time, the third type of data source needs to be ignored. The correspondence or mapping relationship between the data source combination and the disaster warning algorithm combination is preset and can be presented in the form of a table or chart, for example. For example, when the first type of data source, the second type of data source and the third type of data source exist at the same time, the disaster warning model is obtained by integrating the first disaster warning algorithm and the second disaster warning algorithm based on the correspondence or mapping relationship. Other situations in the data source combination can also obtain a disaster warning model based on the preset correspondence or mapping relationship.

[0044] In some embodiments of the present application, the monitoring data is input into the determined disaster warning algorithm or disaster warning model, and the warning result of the flash flood mudslide is obtained according to the output result, including: if the data source is a single-type data source, the warning result is obtained by the output of the disaster warning algorithm; if the data source is a multi-type data source, the weight is determined according to the characteristics of the monitoring data corresponding to each type of data source, and the result of each disaster warning algorithm in the disaster warning algorithm is weighted according to the weight, and the warning result is obtained by the calculation result. In the flash flood mudslide basin, the flash flood mudslide warning is to be carried out, and the choice of warning method will be judged according to all the data that can be obtained in the basin. All warning algorithms will convert the data into a score of 0 to 100, and the warning level will be determined according to the score. One data source corresponds to one calculation method. When there are multiple data sources, a calculation method will be selected. When multiple calculation methods are selected, the calculation results will be fused, and the warning will be issued according to the fused score. For example, when there are a first type of data source and a second type of data source, the results of the warning based on the mud water level height and the warning based on the rainfall are combined and used.

[0045] In some embodiments of the present application, weights are determined according to the characteristics of the monitoring data corresponding to each type of data source, including: determining the weight of the monitoring data according to the quality of the monitoring data, and / or determining the weight of the monitoring data according to the reliability of the monitoring data, and / or determining the weight of the monitoring data according to the monitoring density of the monitoring data. The aforementioned combination of early warning results usually adopts a weighted average method, and the weighted weight is determined according to the quality or characteristics of the monitoring data. The monitoring data is compared and scored based on the above data quality, reliability and monitoring density. For example, the sigma value can be used to judge the quality and the artificial intelligence deep learning method can be used for classification and judgment to distinguish abnormal data situations. When the monitoring data of the two types of data sources are at a balanced level, the weights can be divided equally. When the data quality of the first type of data source decreases, the weight of the early warning result corresponding to the second type of data source will be increased.

[0046] When the first and third types of data sources are used, the mud water level height score and the rainfall score are combined and used, generally as a weighted average method based on the contribution ratio; since the reliability of the third type of data source is lower than that of the first type of data source, the weight of the warning result of the first type of data source is higher than that of the third type of data source. For example, the weight of the warning result of the first type of data source is 0.6, and the weight of the warning result of the third type of data source is 0.4.

[0047] In some embodiments of the present application, the method further includes: generating an alarm corresponding to the risk level according to the early warning result. Early warning score example: when the score is less than 30 points, it is a low risk; when the score range is [30,50), it is a blue risk, corresponding to a blue warning; when the score range is [50,70), it is a yellow risk, corresponding to a yellow warning; when the score range is [70,90), it is an orange risk, corresponding to an orange warning; when the score is greater than or equal to 90, it is a red risk, corresponding to a red warning.

[0048] It can be seen from the above implementation methods that the present application has the advantage of adaptive early warning algorithm or early warning model to monitoring data.

[0049] Based on the same inventive concept, the present application also provides a flash flood and mud-rock flow warning device based on multi-heterogeneous data. Figure 2 The schematic diagram of the structure of the flash flood and mud-rock flow early warning device based on multivariate heterogeneous data according to the embodiment of the present application is shown schematically. Figure 2 As shown, a flash flood and mud-rock flow warning device based on multivariate heterogeneous data includes: a data acquisition module for acquiring monitoring data in real time; a multi-source processing module for determining the data source from which the monitoring data comes, and determining a disaster warning algorithm or a disaster warning model according to the data source; and a result output module for inputting the monitoring data into the determined disaster warning algorithm or disaster warning model, and obtaining a warning result for the flash flood and mud-rock flow according to the output result.

[0050] In some optional implementations of the present application, determining the data source from which the monitoring data comes includes: distinguishing the data source of the monitoring data according to a generating device and / or data content of the monitoring data.

[0051] In some optional embodiments of the present application, determining the data source from which the monitoring data comes includes: if the monitoring data is mountain torrent debris flow mud water level height monitoring data, determining that the monitoring data comes from a first type of data source; if the monitoring data is rainfall data monitored by a rain gauge, determining that the monitoring data comes from a second type of data source; if the monitoring data is grid rainfall data obtained based on meteorological data conversion, determining that the monitoring data comes from a third type of data source.

[0052] In some optional embodiments of the present application, a disaster warning algorithm or disaster warning model is determined based on a data source, including: if the monitoring data comes from a single type of data source, determining the disaster warning algorithm corresponding to this type of data source based on a preset corresponding relationship; if the monitoring data comes from multiple types of data sources, determining the corresponding disaster warning model based on the combination of the multiple types of data sources.

[0053] In some optional embodiments of the present application, the disaster warning algorithm corresponding to the first type of data source includes: determining the numerical interval in which the monitoring data is located, each numerical interval is delimited by a maximum threshold and several intermediate threshold points and has a corresponding digital interval; linearly converting the monitoring data into a number within the digital interval of the corresponding numerical interval, and using the obtained number as the output of the disaster warning algorithm.

[0054] In some optional embodiments of the present application, the disaster warning algorithm corresponding to the second type of data source includes: calculating the ratio of the numerical value of each dimension in the monitoring data to the reference numerical value of the dimension, wherein the dimensions include at least two of rainfall, rainfall intensity and duration information; mapping the weighted sum of the ratios of all dimensions to a preset numerical range, and using the mapping result as the output of the disaster warning algorithm.

[0055] In some optional embodiments of the present application, the disaster warning algorithm corresponding to the third type of data source includes: determining the flood discharge capacity based on the geological conditions; converting the monitoring data into runoff data after basin confluence; and obtaining the output of the disaster warning algorithm based on the flood discharge capacity and runoff data.

[0056] In some optional implementations of the present application, a disaster warning model is determined according to the combination of the multiple types of data sources, including: combining different types of data sources in combination with their respective disaster warning algorithms to form a corresponding disaster warning model.

[0057] In some optional embodiments of the present application, the monitoring data is input into a determined disaster warning algorithm or disaster warning model, and a warning result for mountain torrents and mudslides is obtained based on the output result, including: if the data source is a single-category data source, the warning result is obtained by the output of the disaster warning algorithm; if the data source is a multi-category data source, the weight is determined according to the characteristics of the monitoring data corresponding to each type of data source, and the result of each disaster warning algorithm in the disaster warning algorithm is weighted calculated according to the weight, so as to obtain the warning result by the calculation result.

[0058] In some optional embodiments of the present application, weights are determined based on characteristics of the monitoring data corresponding to each type of data source, including: determining the weight of the monitoring data based on the quality of the monitoring data, and / or determining the weight of the monitoring data based on the reliability of the monitoring data, and / or determining the weight of the monitoring data based on the monitoring density of the monitoring data.

[0059] In some optional implementations of the present application, the device further includes a risk level module, and the risk level module is used to generate an alarm corresponding to the risk level according to the early warning result.

[0060] The specific definition of each functional module in the above-mentioned flash flood and debris flow warning device based on multi-heterogeneous data can be found in the above-mentioned definition of the flash flood and debris flow warning method based on multi-heterogeneous data, which will not be repeated here. Each module in the above-mentioned device or system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. The device acts on the flash flood and debris flow warning based on multi-heterogeneous data, and also has the advantages of algorithm and monitoring data adaptation.

[0061] The embodiment of the present application provides a storage medium on which a program is stored. When the program is executed by a processor, the above-mentioned flash flood and mud-rock flow early warning method based on multivariate heterogeneous data is implemented.

[0062] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 shown. Figure 3 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected via a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a flash flood and mudslide early warning method based on multivariate heterogeneous data is implemented.

[0063] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0064] In one embodiment, the flash flood and mud-rock flow early warning device based on multivariate heterogeneous data provided by the present application can be implemented in the form of a computer program. The computer program can be used in Figure 3The computer device is run on the computer device shown. The memory of the computer device can store various program modules constituting the flash flood and debris flow warning device based on multivariate heterogeneous data, and the computer program composed of various program modules enables the processor to execute the steps of the flash flood and debris flow warning method based on multivariate heterogeneous data in various embodiments of the present application described in this specification.

[0065] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0066] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0067] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0068] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0069] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0070] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0071] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0072] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0073] The above is only the implementation mode of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A flash flood and debris flow early warning method based on multivariate heterogeneous data, characterized in that: The method includes: Obtain monitoring data in real time; Determine the data source from which the monitoring data comes, and determine the disaster warning algorithm or disaster warning model according to the data source; The monitoring data is input into the determined disaster warning algorithm or disaster warning model, and the warning results for mountain torrents and mud-rock flows are obtained based on the output results.

2. The method according to claim 1, characterized in that Determining the data source from which the monitoring data comes, including: The data source of the monitoring data is distinguished according to the generating device and / or data content of the monitoring data.

3. The method according to claim 1, characterized in that Determining the data source from which the monitoring data comes, including: If the monitoring data is monitoring data of mud and water level height of mountain torrents, debris flow, it is determined that the monitoring data comes from the first type of data source; If the monitoring data is rainfall data monitored by a rain gauge, determining that the monitoring data comes from a second type of data source; If the monitoring data is grid rainfall data obtained based on meteorological data conversion, it is determined that the monitoring data comes from the third type of data source.

4. The method according to claim 3, characterized in that Determine the disaster warning algorithm or disaster warning model based on the data source, including: If the monitoring data comes from a single type of data source, determine the disaster warning algorithm corresponding to the type of data source according to a preset corresponding relationship; If the monitoring data comes from multiple types of data sources, the corresponding disaster warning model is determined according to the combination of the multiple types of data sources.

5. The method according to claim 4, characterized in that The disaster warning algorithms corresponding to the first type of data sources include: Determine the numerical interval of the monitoring data, each numerical interval is delimited by a maximum threshold and several intermediate threshold points and has a corresponding digital interval; The monitoring data is linearly converted into numbers within a digital interval corresponding to the numerical interval, and the obtained numbers are used as the output of the disaster warning algorithm.

6. The method according to claim 4, characterized in that The disaster warning algorithms corresponding to the second type of data sources include: Calculate the ratio of the value of each dimension in the monitoring data to the reference value of the dimension, wherein the dimension includes at least two of rainfall amount, rainfall intensity and duration information; The weighted sum of the ratios of all dimensions is mapped to a preset numerical range, and the mapping result is used as the output of the disaster warning algorithm.

7. The method according to claim 4, characterized in that The disaster warning algorithms corresponding to the third type of data sources include: Determine flood discharge capacity based on the geological conditions described; Convert monitoring data into runoff data after basin confluence; The output of the disaster warning algorithm is obtained based on the flood discharge capacity and runoff data.

8. The method according to claim 4, characterized in that Determining a disaster warning model according to the combination of the multiple types of data sources includes: According to the combination of different categories of data sources, combined with their respective disaster warning algorithms, a corresponding disaster warning model is formed.

9. The method according to claim 4, characterized in that The monitoring data is input into the determined disaster warning algorithm or disaster warning model, and the warning results of flash floods and mud-rock flows are obtained according to the output results, including: If the data source is a single-category data source, the warning result is obtained by using the output of the disaster warning algorithm; If the data source is a multi-category data source, the weight is determined according to the characteristics of the monitoring data corresponding to each type of data source, and the results of each disaster warning algorithm in the disaster warning algorithm are weighted calculated according to the weight to obtain the warning result by calculating the result.

10. The method according to claim 9, characterized in that The weight is determined according to the characteristics of the monitoring data corresponding to each type of data source, including: Determine the weight of the monitoring data according to the quality of the monitoring data, and / or Determining the weight of the monitoring data according to the reliability of the monitoring data, and / or The weight of the monitoring data is determined according to the monitoring density of the monitoring data.

11. The method according to claim 1, characterized in that: The method further includes: generating an alarm corresponding to the risk level according to the early warning result.

12. A flash flood and mud-rock flow early warning device based on multivariate heterogeneous data, characterized in that: The device also includes: Data acquisition module, real-time acquisition of monitoring data; A multi-source processing module, used to determine the data source from which the monitoring data comes, and determine a disaster warning algorithm or a disaster warning model according to the data source; and The result output module is used to input the monitoring data into the determined disaster warning algorithm or disaster warning model, and obtain the warning result of mountain torrents and mud-rock flows according to the output result.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the flash flood and mud-rock flow early warning method based on multivariate heterogeneous data as described in any one of claims 1 to 11 are implemented.

14. A computer-readable storage medium storing instructions which, when executed on a computer, enable the computer to execute the steps of the flash flood and mud-rock flow early warning method based on multivariate heterogeneous data as described in any one of claims 1 to 11.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the steps of the flash flood and mud-rock flow early warning method based on multivariate heterogeneous data as described in any one of claims 1 to 11.

Images