CN116523112A - Method for determining probability value of occurrence of geological landslide hazard, storage medium and processor - Google Patents

Abstract

The embodiment of the application provides a method for determining a probability value of occurrence of a geological landslide disaster, a storage medium and a processor. Comprising the following steps: determining a target prediction model from a plurality of prediction models; acquiring a plurality of grids of a region to be researched; acquiring a first predicted rainfall total amount of each grid point included in the grid in a first target time period and a second predicted rainfall total amount in a second target time period; sequentially inputting the first predicted rainfall total amount and the second predicted rainfall total amount into a target prediction model to obtain a prediction result of geological landslide disasters occurring at grid points; and determining the probability value of the geological landslide disaster at the target position in the grid according to all the prediction results. According to the technical scheme, the prediction result of the geological landslide disaster occurring at the grid points can be obtained through the target prediction model, so that the probability value of the geological landslide disaster occurring at the target position can be accurately determined, early warning and protection work can be performed in advance, the loss of life and property is reduced, and the method has extremely high practical value.

Description

Method for determining probability value of occurrence of geological landslide hazard, storage medium and processor

Technical Field

The application relates to the technical field of electrical engineering, in particular to a method storage medium and a processor for determining probability value of occurrence of geological landslide disaster.

Background

In recent years, with global climate change, extreme weather disasters frequently occur, and the sudden rain landslide causes more and more accidents of damaged outage of the transmission and transformation line. The method has very important significance in developing geological landslide disaster prediction. The storm process which causes frequent occurrence of summer land disasters often has the characteristics of short duration, large rainfall, rapid change and the like, so that the occurrence of geological landslide disasters has stronger locality. The current calculation method for the geological landslide disasters mainly comprises the step of forecasting the daily scale or the medium-short-term storm geological disasters in the future of 3-7 days by factors such as daily rainfall, easy occurrence degree of secondary geological disasters and the like. The accurate prediction of geological landslide disasters cannot be realized by the existing technical scheme, and an effective early warning effect cannot be achieved.

Disclosure of Invention

The embodiment of the application aims to provide a method, a storage medium and a processor for determining a probability value of occurrence of a geological landslide disaster.

To achieve the above object, a first aspect of the present application provides a method for determining a probability value of occurrence of a geological landslide hazard, including:

Determining a target prediction model from a plurality of prediction models;

acquiring a plurality of grids of an area to be studied, wherein each grid comprises a plurality of grid points;

for each grid, acquiring a first predicted rainfall amount of each grid point included in the grid in a first target time period and a second predicted rainfall amount in a second target time period;

for each grid point, sequentially inputting the first predicted rainfall total amount and the second predicted rainfall total amount of the grid point into a target prediction model to obtain a prediction result of geological landslide disaster of the grid point output by the target prediction model;

and determining the probability value of the geological landslide disaster at the target position in the grid according to all the prediction results aiming at any grid.

In an embodiment of the present application, determining the target prediction model from the plurality of prediction models includes: obtaining a plurality of sample data, wherein each sample data comprises a first historical rainfall amount and a second historical rainfall amount; inputting each sample data into the prediction model in turn aiming at each prediction model to obtain a prediction result corresponding to the sample data output by the prediction model; aiming at each prediction model, determining prediction parameters of the prediction model according to the matching degree of the prediction result and the historical occurrence condition of landslide hazard; for each prediction model, determining a comprehensive evaluation index of the prediction model according to the prediction parameters; and determining a prediction model corresponding to the comprehensive evaluation index with the largest numerical value as a target prediction model.

In the embodiment of the present application, the prediction parameters include a hit rate, a false positive rate, and a critical success index, and for each prediction model, determining the prediction parameters of the prediction model according to the matching degree between the prediction result and the historical occurrence condition of the landslide hazard includes: the predicted result is expressed as geological landslide disasters, and the occurrence frequency of the geological landslide disasters with the historical occurrence condition being the historical occurrence is determined to be a first numerical value; the predicted result is expressed as no geological landslide disaster, the historical occurrence condition is the occurrence frequency of the historical non-occurrence geological landslide disaster, and the number of occurrence times is determined to be a second numerical value; the predicted result is expressed as no geological landslide disaster, the historical occurrence condition is the occurrence frequency of the historical occurrence of the geological landslide disaster, and the occurrence frequency is determined to be a third numerical value; the predicted result is expressed as geological landslide disasters, the historical occurrence condition is that the occurrence frequency of the geological landslide disasters does not occur is determined to be a fourth numerical value; determining a hit rate according to the first value and the second value; determining a false alarm rate according to the first value and the fourth value; and determining a critical success index according to the first value, the third value and the fourth value.

In this embodiment of the present application, for any one grid, determining, according to all prediction results, a probability value of occurrence of a geological landslide disaster at a target position in the grid includes: calculating a probability value according to formula (1):

Wherein,,Z ₀ representing probability value, Z _i Representing the prediction result of the ith grid point of the grid, D _i Represents the distance between the target position and the grid point, p represents the power of the distance, n represents the total number of grid points, i represents the ith grid point, X _o Longitude coordinates representing the target position, Y _o Representing latitude coordinates of the target position, X _i Representing longitude coordinates of the ith grid point, Y _i Representing the latitude coordinate of the ith grid point.

In this embodiment of the present application, after determining, for any one grid, a probability value of occurrence of a geological landslide disaster at a target location in the grid according to all prediction results, the method further includes: an alert level for the target location is determined based on the probability value.

In an embodiment of the present application, determining the alert level for the target location according to the probability value includes: under the condition that the probability value is in a first preset range, determining that no alarm is needed at the target position; under the condition that the probability value is in a second preset range, determining the alarm level as a primary alarm; under the condition that the probability value is in a third preset range, determining the alarm level as a secondary alarm; and under the condition that the probability value is in a fourth preset range, determining the alarm level as three-level alarm.

In an embodiment of the present application, the method further includes: before determining a target prediction model from a plurality of prediction models, acquiring a plurality of historical landslide disaster data and a plurality of historical rainfall data of a region to be researched; determining a first historical rainfall total amount in a first historical time period and a second historical rainfall total amount in a second historical time period according to the historical landslide hazard data and the historical rainfall data; determining a rainfall threshold curve according to each historical landslide hazard data, each first historical rainfall amount and each second historical rainfall amount; and determining a corresponding prediction model according to each rainfall threshold curve.

A second aspect of the present application provides a processor configured to perform the above-described method of determining a probability value of occurrence of a geological landslide hazard.

A third aspect of the present application provides an apparatus for determining a probability value of occurrence of a geological landslide hazard, the apparatus comprising:

the first processing module is used for determining a target prediction model from a plurality of prediction models;

the device comprises a first acquisition module, a second acquisition module and a first detection module, wherein the first acquisition module is used for acquiring a plurality of grids of an area to be studied, and each grid comprises a plurality of grid points;

a second acquisition module for acquiring, for each grid, a first predicted total rainfall amount of each grid point included in the grid in a first target period and a second predicted total rainfall amount in a second target period;

The second processing module is used for inputting the first predicted rainfall total quantity and the second predicted rainfall total quantity of the grid points into the target prediction model in sequence for each grid point to obtain a prediction result of geological landslide disasters of the grid points output by the target prediction model;

and the third processing module is used for determining the probability value of the geological landslide disaster at the target position in the grid according to all the prediction results aiming at any grid.

A fourth aspect of the present application provides a machine-readable storage medium having stored thereon instructions that, when executed by a processor, cause the processor to be configured to perform the above-described method of determining a probability value for an occurrence of a geological landslide hazard.

According to the technical scheme, the target prediction model is determined from a plurality of prediction models; acquiring a plurality of grids of an area to be studied, wherein each grid comprises a plurality of grid points; for each grid, acquiring a first predicted rainfall amount of each grid point included in the grid in a first target time period and a second predicted rainfall amount in a second target time period; for each grid point, sequentially inputting the first predicted rainfall total amount and the second predicted rainfall total amount of the grid point into a target prediction model to obtain a prediction result of geological landslide disaster of the grid point output by the target prediction model; and determining the probability value of the geological landslide disaster at the target position in the grid according to all the prediction results aiming at any grid. By adopting the technical scheme, the prediction result of the geological landslide disaster occurring at the grid points can be obtained through the target prediction model, so that the probability value of the geological landslide disaster occurring at the target position can be accurately determined, early warning and protection work can be performed in advance, the loss of life and property is reduced, and the method has extremely high practical value.

Additional features and advantages of embodiments of the present application will be set forth in the detailed description that follows.

Drawings

The accompanying drawings are included to provide a further understanding of embodiments of the present application and are incorporated in and constitute a part of this specification, illustrate embodiments of the present application and together with the description serve to explain, without limitation, the embodiments of the present application. In the drawings:

FIG. 1 schematically illustrates a flow diagram of a method of determining probability values of occurrence of a geological landslide hazard in accordance with an embodiment of the application;

FIG. 2 schematically illustrates a schematic of a rainfall threshold curve according to an embodiment of the present application;

fig. 3 schematically shows an internal structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the specific implementations described herein are only for illustrating and explaining the embodiments of the present application, and are not intended to limit the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present application based on the embodiments herein.

Fig. 1 schematically shows a flow diagram of a method of determining a probability value of occurrence of a geological landslide hazard according to an embodiment of the application. As shown in fig. 1, in an embodiment of the present application, there is provided a method for determining a probability value of occurrence of a geological landslide hazard, including the steps of:

and step 101, determining a target prediction model from a plurality of prediction models.

Step 102, a plurality of grids of the area to be studied are acquired, wherein each grid comprises a plurality of grid points.

Step 103, for each grid, obtaining a first predicted total rainfall amount of each grid point included in the grid in a first target time period and a second predicted total rainfall amount of each grid point in a second target time period.

Step 104, for each grid point, sequentially inputting the first predicted rainfall total amount and the second predicted rainfall total amount of the grid point into the target prediction model to obtain a prediction result of geological landslide disaster of the grid point output by the target prediction model.

Step 105, determining a probability value of occurrence of geological landslide disaster at a target position in the grid according to all prediction results for any grid.

Geological landslide disasters refer to the natural phenomenon that soil bodies or rock bodies on a slope are influenced by river scouring, groundwater movement, rainwater soaking, earthquakes, manual slope cutting and other factors, and slide downwards along a certain weak surface or a weak zone integrally or dispersedly under the action of gravity. The historical landslide hazard data may include information of landslide occurrence time, landslide level, and the like. The historical rainfall amount refers to the rainfall amount in the historical period before the landslide occurrence time.

The processor may determine a target predictive model from a plurality of predictive models. Wherein each predictive model may correspond to a data set, each data set including a historical landslide hazard data, a first historical total amount of rainfall, and a second historical total amount of rainfall.

The first and second historical amounts of rainfall are two amounts of rainfall over different historical time periods.

After determining the target predictive model, the processor may acquire a plurality of grids of the region to be studied, wherein each grid includes a plurality of grid points. For each grid, the processor may obtain a first predicted total amount of rainfall for a first target period and a second predicted total amount of rainfall for a second target period for each grid point included in the grid. The predicted total rainfall amount may be obtained by analyzing weather data in a future time period by the processor.

For each grid point, after obtaining the first predicted rainfall total amount and the second predicted rainfall total amount of each grid point, the processor can sequentially input the first predicted rainfall total amount and the second predicted rainfall total amount of the grid point into the target prediction model, and obtain a prediction result of geological landslide disaster occurring at the grid point, which is output by the target prediction model. For any grid, after the prediction results of the geological landslide disasters of the grid points are obtained, the processor can determine the probability value of the geological landslide disasters of the target positions in the grid according to all the prediction results.

In one embodiment, the method further comprises: before determining a target prediction model from a plurality of prediction models, acquiring a plurality of historical landslide disaster data and a plurality of historical rainfall data of a region to be researched; determining a first historical rainfall total amount in a first historical time period and a second historical rainfall total amount in a second historical time period according to the historical landslide hazard data and the historical rainfall data; determining a rainfall threshold curve according to each historical landslide hazard data, each first historical rainfall amount and each second historical rainfall amount; and determining a corresponding prediction model according to each rainfall threshold curve.

The processor may obtain a plurality of historical landslide hazard data and a plurality of historical rainfall data for the area to be studied prior to determining the target predictive model from the plurality of predictive models. After obtaining the historical landslide hazard data and the historical rainfall data, the processor may determine a first historical total amount of rainfall in a first historical time period and a second historical total amount of rainfall in a second historical time period from the historical landslide hazard data and the historical rainfall data. After obtaining the first and second historical amounts of rainfall, the processor may determine a rainfall threshold curve based on each historical landslide hazard data, each first historical amount of rainfall, and each second historical amount of rainfall. And determining a corresponding prediction model according to each rainfall threshold curve.

For example, the processor may obtain a plurality of historical landslide hazard data and a plurality of historical rainfall data for the area under study. The historical landslide disaster data can comprise landslide occurrence time and other information. The historical rainfall data may be the amount of rainfall per hour prior to the landslide occurrence time. The processor may determine a first historical total amount of rainfall over a first historical time period and a second historical total amount of rainfall over a second historical time period from the historical landslide hazard data and the historical rainfall data. Specifically, the processor may generate a landslide time t _n For the ending time, respectively acquiring the occurrence time t of landslide _n Rainfall in each hour before. Then calculating to obtain the occurrence time t of landslide _n First history period t before _n-a First historical rainfall amount H _n-a And a second history period T _n-b Second historical rainfall amount H _n-b . Assuming that the processor determines that the landslide time in one of the historical landslide hazard data is 10 am, and determines that the historical rainfall data includes 1mm of rainfall in 9 to 10 am, 2mm of rainfall in 8 to 9 am, and 2mm of rainfall in 7 to 8 am. The processor can calculate the obtained front The total amount of the historical rainfall in 1 hour is 1mm, and the total amount of the historical rainfall in the first 3 hours is 5mm. The processor can obtain a rainfall threshold curve X according to historical landslide disaster data comprising landslide disasters occurring at 10 am, the total amount of historical rainfall in the previous 1 hour being 1mm and the total amount of historical rainfall in the previous 3 hours being 5mm _1-3 . Specifically, the processor may input historical landslide hazard data including landslide hazards occurring at 10 am, a total amount of historical rainfall 1mm in the first 1 hour, and a total amount of historical rainfall 5mm in the first 3 hours to a Support Vector Machine (SVM) machine learning model to output a corresponding rainfall threshold curve X through the vector machine (SVM) machine learning model _1-3 . X after obtaining rainfall threshold curve _1-3 The processor can calculate the post-curve X according to the rainfall threshold _1-3 Determining a corresponding predictive model Y _1-3 . After deriving the plurality of predictive models, the processor may determine a target predictive model from the plurality of predictive models. And acquiring a plurality of grids of the region to be studied.

Specifically, the area to be studied may be an area where a plurality of transmission line towers are located, and the processor may acquire the number of grids corresponding to the resolution based on the resolution between the transmission line towers, where one grid may be formed by four grid points, and the grid includes a target position where the transmission line towers are located. Assume that the target prediction model is Y _1-3 . For each grid, the processor may pass through the target prediction model Y _1-3 And determining the probability value of the geological landslide disaster at the target position of the power transmission line tower. For example, the processor needs to determine that the target position is at some future time t _d Probability value of occurrence of geological landslide hazard. First, the processor may acquire each grid point included in the grid at t _d First rainfall forecast total amount H in the previous hour _d-1 And at t _d Total second rainfall prediction amount H in the first 3 hours _d-3 . For each grid point, the processor may predict the first rainfall prediction total amount H of the grid point in turn _d-1 And a second rainfall prediction total amount H _d-3 Input to the target prediction model Y _1-3 To pass through the target predictive model Y _1-3 Output grid point place of occurrenceAnd predicting a landslide hazard. For any one grid, the processor can determine the probability value of geological landslide disaster occurring at the target position in the grid according to the prediction results of the four grid points. In one embodiment, for any one grid, determining a probability value of occurrence of a geological landslide hazard at a target location in the grid according to all prediction results includes: calculating a probability value according to formula (1):

wherein,,Z ₀ representing probability value, Z _i Representing the prediction result of the ith grid point of the grid, D _i Represents the distance between the target position and the grid point, p represents the power of the distance, n represents the total number of grid points, i represents the ith grid point, X _o Longitude coordinates representing the target position, Y _o Representing latitude coordinates of the target position, X _i Representing longitude coordinates of the ith grid point, Y _i Representing the latitude coordinate of the ith grid point.

In one embodiment, determining the target predictive model from the plurality of predictive models includes: obtaining a plurality of sample data, wherein each sample data comprises a first historical rainfall amount and a second historical rainfall amount; inputting each sample data into the prediction model in turn aiming at each prediction model to obtain a prediction result corresponding to the sample data output by the prediction model; aiming at each prediction model, determining prediction parameters of the prediction model according to the matching degree of the prediction result and the historical occurrence condition of landslide hazard; for each prediction model, determining a comprehensive evaluation index of the prediction model according to the prediction parameters; and determining a prediction model corresponding to the comprehensive evaluation index with the largest numerical value as a target prediction model.

The processor may determine a target predictive model from a plurality of predictive models. In particular, the processor may obtain a plurality of sample data, wherein each sample data includes a first historical total amount of rainfall and a second historical total amount of rainfall. For each prediction model, after obtaining a plurality of sample data, the processor may input each sample data to the prediction model, and obtain a prediction result corresponding to the sample data output by the prediction model. For each prediction model, after obtaining the prediction result, the processor can determine the prediction parameters of the prediction model according to the matching degree of the prediction result and the historical occurrence condition of landslide hazard. For each prediction model, after obtaining the prediction parameters of the prediction model, the processor may determine a comprehensive evaluation index of the prediction model according to the prediction parameters. And determining a prediction model corresponding to the comprehensive evaluation index with the largest numerical value as a target prediction model.

In one embodiment, the prediction parameters include hit rate, false positive rate and critical success index, and for each prediction model, determining the prediction parameters of the prediction model according to the matching degree of the prediction result and the historical occurrence of landslide hazard includes: the predicted result is expressed as geological landslide disasters, and the occurrence frequency of the geological landslide disasters with the historical occurrence condition being the historical occurrence is determined to be a first numerical value; the predicted result is expressed as no geological landslide disaster, the historical occurrence condition is the occurrence frequency of the historical non-occurrence geological landslide disaster, and the number of occurrence times is determined to be a second numerical value; the predicted result is expressed as no geological landslide disaster, the historical occurrence condition is the occurrence frequency of the historical occurrence of the geological landslide disaster, and the occurrence frequency is determined to be a third numerical value; the predicted result is expressed as geological landslide disasters, the historical occurrence condition is that the occurrence frequency of the geological landslide disasters does not occur is determined to be a fourth numerical value; determining a hit rate according to the first value and the second value; determining a false alarm rate according to the first value and the fourth value; and determining a critical success index according to the first value, the third value and the fourth value.

The prediction parameters include hit rate, false positive rate, and critical success index. For each prediction model, after obtaining the prediction result of the prediction model, the processor can determine the prediction parameters of the prediction model according to the matching degree of the prediction result and the historical occurrence condition of landslide hazard. Specifically, the processor may determine the number of occurrences of the geological landslide hazard as the first value as the prediction result indicates that the geological landslide hazard is present and as the history of occurrence. The processor may determine that the predicted result is represented as no geological landslide hazard and the historical occurrence is the number of occurrences of the historical non-occurrence of the geological landslide hazard as the second value. The processor may determine that the predicted result is represented as no geological landslide hazard and the historical occurrence is the number of occurrences of the geological landslide hazard that has been historically occurred as the third value. The processor may determine that the predicted result is indicated as having the geological landslide hazard and the historical occurrence is the number of occurrences of the geological landslide hazard that has not occurred historically as the fourth value. After obtaining the first value, the second value, the third value, and the fourth value, the processor may determine the hit rate based on the first value and the second value. The processor may also determine a false positive rate based on the first value and the fourth value. The processor also determines a critical success index based on the first value, the third value, and the fourth value.

For example, the processor may obtain a plurality of sample data. For each prediction model, the processor may sequentially input each sample data to the prediction model to output a prediction result corresponding to the sample data through the prediction model. The processor may determine that the predicted result is indicated as having the geological landslide hazard and the historical occurrence is the occurrence number of the geological landslide hazard as being historically occurred as the first numerical value TP. The processor may determine the number of occurrences of the prediction result as no geological landslide hazard and the historical occurrence of the historical non-occurrence of the geological landslide hazard as the second value TN. The processor may determine that the predicted result is represented as no geological landslide hazard and the historical occurrence is the number of occurrences of the historical occurrence of the geological landslide hazard as the third numerical value FN. The processor may determine the number of occurrences of the prediction result as having a geological landslide hazard and the historical occurrence as having no geological landslide hazard as the fourth value FP. After obtaining the first value TP, the second value TN, the third value FN and the fourth value FP, the processor can determine the hit rate POD according to the first value TP and the second value TN, namelyThe processor can determine the false alarm rate FAR, i.e./according to the first value TP and the fourth value FP >The processor can determine the critical success index CSI, i.e., +.>

In one embodiment, the prediction parameters include hit rate, false positive rate, and critical success index. The processor may determine a mean of the hit rate, false positive rate, and critical success index as the composite evaluation index. For example, the processor may sum the hit rate POD, the false positive rate FAR, and the critical success index CSI and then average the sum, and determine the obtained average as the integrated evaluation index score.

In one embodiment, after determining the probability value of the occurrence of the geological landslide hazard at the target position in the grid according to all the prediction results for any one grid, the method further comprises: an alert level for the target location is determined based on the probability value.

For any grid, the processor can determine the probability value of geological landslide disaster occurrence at the target position in the grid according to all the prediction results. After obtaining the probability values, the processor may determine an alert level for the target location based on the probability values. In one embodiment, determining the alert level for the target location based on the probability value includes: under the condition that the probability value is in a first preset range, determining that no alarm is needed at the target position; under the condition that the probability value is in a second preset range, determining the alarm level as a primary alarm; under the condition that the probability value is in a third preset range, determining the alarm level as a secondary alarm; and under the condition that the probability value is in a fourth preset range, determining the alarm level as three-level alarm.

For example, the processor may calculate a probability value for the occurrence of a geological landslide hazard at a target location in the grid according to equation (1):

wherein,,Z ₀ representing probability value, Z _i Representing the prediction result of the ith grid point of the grid, D _i Represents the distance between the target position and the grid point, p represents the power of the distance, n represents the total number of grid points, i represents the ith grid point, X _o Longitude coordinates representing the target position, Y _o Representing latitude coordinates of the target position, X _i Representing longitude coordinates of the ith grid point, Y _i Representing the latitude coordinate of the ith grid point.

After the probability value is calculated, the processor may determine an alert level for the target location divided by the probability value. In the event that the probability value is determined to be within 0,0.5, the processor may determine that no alert is needed at the target location. The processor may determine that the alert level at the target location is a first level alert if the probability value is determined to be within (0.5,0.7), the processor may determine that the alert level at the target location is a second level alert if the probability value is determined to be within (0.7,0.9), and may determine that the alert level at the target location is a third level alert if the probability value is determined to be within (0.9,1).

In one embodiment, the processor may obtain a plurality of historical landslide hazard data and a plurality of historical rainfall data for the area under study. After obtaining the historical landslide hazard data and the historical rainfall data, the processor may determine a first historical total amount of rainfall in a first historical time period and a second historical total amount of rainfall in a second historical time period from the historical landslide hazard data and the historical rainfall data. After obtaining the first and second historical amounts of rainfall, the processor may determine a rainfall threshold curve based on each historical landslide hazard data, each first historical amount of rainfall, and each second historical amount of rainfall. And determining a corresponding prediction model according to each rainfall threshold curve. As shown in fig. 2, four corresponding prediction models are obtained according to the four rainfall threshold curves. The four rainfall threshold curves are respectively a rainfall threshold curve corresponding to the total amount of rainfall (accumulative rainfall) in the first 3h and the total amount of rainfall in the first 24h, a rainfall threshold curve corresponding to the total amount of rainfall in the first 12h and the total amount of rainfall in the first 24h, a rainfall threshold curve corresponding to the total amount of rainfall in the first 3h and the total amount of rainfall in the first 12h, and a rainfall threshold curve corresponding to the total amount of rainfall in the first 1h and the total amount of rainfall in the first 3 h.

The processor may determine corresponding four predictive models from the four rainfall threshold curves. And determining a target prediction model from the four prediction models. Specifically, the processor may determine a prediction parameter for each prediction model, where the prediction parameters may include a hit rate POD, a false positive rate FAR, and a critical success index CSI. Further, the processor may determine that the predicted result is indicated as having the geological landslide hazard and the historical occurrence is the occurrence number of the historical occurrence of the geological landslide hazard as the first value TP. And determining the occurrence frequency of the geological landslide disaster, which is indicated as no geological landslide disaster and the historical occurrence condition as the historical non-occurrence of the geological landslide disaster, as a second value TN. And determining the number of occurrence times of the geological landslide disaster, which is indicated as no geological landslide disaster and the historical occurrence condition as the historical occurrence of the geological landslide disaster, as a third numerical value FN. And determining the number of occurrence times of the geological landslide disaster, wherein the occurrence times are the occurrence times of the geological landslide disaster, the geological landslide disaster is indicated as the prediction result, and the historical occurrence condition is the occurrence time of the geological landslide disaster which does not occur as the history, as a fourth value FP. In fig. 2, the hit rate POD, false positive rate FAR, and critical success index CSI of the first prediction model (3 h-24 h) are 0.933, 0.282, and 0.683, respectively. Hit rate POD, false positive rate FAR, and critical success index CSI of the second prediction model (12 h-24 h) were 0.933, 0.243, and 0.718, respectively. The hit rate POD, false positive rate FAR, and critical success index CSI of the third predictive model (3 h-12 h) were 0.933, 0.3, and 0.667, respectively. The hit rate POD, false positive rate FAR, and critical success index CSI of the fourth predictive model (1 h-3 h) were 0.833, 0.468, and 0.481, respectively. The hit rate POD is determined according to the first value TP and the second value TN, the false positive rate FAR is determined according to the first value TP and the fourth value FP, and the critical success index CSI is determined according to the first value TP, the third value FN and the fourth value FP.

After determining the hit rate, the false alarm rate and the critical success index of each prediction model, the processor can determine the comprehensive evaluation index of each prediction model according to the hit rate, the false alarm rate and the critical success index, and determine the prediction model corresponding to the comprehensive evaluation index with the largest value as the target prediction model. After determining the target predictive model, the processor may acquire a plurality of grids of the region to be studied, wherein each grid includes a plurality of grid points. For each grid, the processor may obtain a first predicted total amount of rainfall for a first target period and a second predicted total amount of rainfall for a second target period for each grid point included in the grid. For each grid point, after obtaining the first predicted rainfall amount and the second predicted rainfall amount of each grid point, the processor may sequentially input the first predicted rainfall amount and the second predicted rainfall amount of the grid point to the target prediction model, so as to output a prediction result of occurrence of the geological landslide disaster of the grid point through the target prediction model. For any grid, after obtaining the prediction results of the possible occurrence of the geological landslide disaster at the grid point, the processor can determine the probability value of the occurrence of the geological landslide disaster at the target position in the grid according to all the prediction results.

According to the technical scheme, the target prediction model is determined from a plurality of prediction models; acquiring a plurality of grids of an area to be studied, wherein each grid comprises a plurality of grid points; for each grid, acquiring a first predicted rainfall amount of each grid point included in the grid in a first target time period and a second predicted rainfall amount in a second target time period; for each grid point, sequentially inputting the first predicted rainfall total amount and the second predicted rainfall total amount of the grid point into a target prediction model to obtain a prediction result of geological landslide disaster of the grid point output by the target prediction model; and determining the probability value of the geological landslide disaster at the target position in the grid according to all the prediction results aiming at any grid. By adopting the technical scheme, the prediction result of the geological landslide disaster occurring at the grid points can be obtained through the target prediction model, so that the probability value of the geological landslide disaster occurring at the target position can be accurately determined, early warning and protection work can be performed in advance, the loss of life and property is reduced, and the method has extremely high practical value.

FIG. 1 is a flow diagram of a method of determining a probability value of occurrence of a geologic landslide hazard in one embodiment. It should be understood that, although the steps in the flowchart of fig. 1 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 1 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of other steps or sub-steps of other steps.

In one embodiment, an apparatus for determining a probability value of occurrence of a geological landslide hazard is provided, including a first processing module, a first acquisition module, a second processing module, and a third processing module, wherein:

the first processing module is used for determining a target prediction model from a plurality of prediction models;

the device comprises a first acquisition module, a second acquisition module and a first detection module, wherein the first acquisition module is used for acquiring a plurality of grids of an area to be studied, and each grid comprises a plurality of grid points;

a second acquisition module for acquiring, for each grid, a first predicted total rainfall amount of each grid point included in the grid in a first target period and a second predicted total rainfall amount in a second target period;

the second processing module is used for inputting the first predicted rainfall total quantity and the second predicted rainfall total quantity of the grid points into the target prediction model in sequence for each grid point to obtain a prediction result of geological landslide disasters of the grid points output by the target prediction model;

and the third processing module is used for determining the probability value of the geological landslide disaster at the target position in the grid according to all the prediction results aiming at any grid.

In one embodiment, the first processing module includes a first processing unit, a second processing unit, a third processing unit, a fourth processing unit, and a fifth processing unit, wherein:

the first processing unit is used for acquiring a plurality of sample data, wherein each sample data comprises a first historical rainfall total amount and a second historical rainfall total amount;

the second processing unit is used for inputting each sample data into the prediction model in sequence for each prediction model to obtain a prediction result corresponding to the prediction model output sample data;

the third processing unit is used for determining the prediction parameters of the prediction models according to the matching degree of the prediction results and the historical occurrence condition of landslide disasters aiming at each prediction model;

the fourth processing unit is used for determining the comprehensive evaluation index of the prediction model according to the prediction parameters for each prediction model;

and the fifth processing unit is used for determining a prediction model corresponding to the comprehensive evaluation index with the largest numerical value as a target prediction model.

In one embodiment, the prediction parameters include a hit rate, a false positive rate, and a critical success index, and the third processing unit is configured to:

The predicted result is expressed as geological landslide disasters, and the occurrence frequency of the geological landslide disasters with the historical occurrence condition being the historical occurrence is determined to be a first numerical value; the predicted result is expressed as no geological landslide disaster, the historical occurrence condition is the occurrence frequency of the historical non-occurrence geological landslide disaster, and the number of occurrence times is determined to be a second numerical value; the predicted result is expressed as no geological landslide disaster, the historical occurrence condition is the occurrence frequency of the historical occurrence of the geological landslide disaster, and the occurrence frequency is determined to be a third numerical value; the predicted result is expressed as geological landslide disasters, the historical occurrence condition is that the occurrence frequency of the geological landslide disasters does not occur is determined to be a fourth numerical value; determining a hit rate according to the first value and the second value; determining a false alarm rate according to the first value and the fourth value; and determining a critical success index according to the first value, the third value and the fourth value.

In one embodiment, for any one grid, the third processing module is configured to determine, according to all prediction results, a probability value of occurrence of a geological landslide disaster at a target position in the grid, where the probability value includes: calculating a probability value according to formula (1):

wherein,,Z ₀ representing probability value, Z _i Representing the prediction result of the ith grid point of the grid, D _i Represents the distance between the target position and the grid point, p represents the power of the distance, n represents the total number of grid points, i represents the ith grid point, X _o Longitude coordinates representing the target position, Y _o Representing latitude coordinates of the target position, X _i Representing longitude coordinates of the ith grid point, Y _i Representing the latitude coordinate of the ith grid point.

In one embodiment, the apparatus for determining a probability value of occurrence of a geological landslide hazard further includes a fourth processing module for determining an alarm level for a target location in the grid based on the probability values after determining the probability value of occurrence of the geological landslide hazard for the target location in the grid based on all of the prediction results for any one of the grids.

In one embodiment, the fourth processing module is configured to determine that no alert is required at the target location if the probability value is within the first preset range; under the condition that the probability value is in a second preset range, determining the alarm level as a primary alarm; under the condition that the probability value is in a third preset range, determining the alarm level as a secondary alarm; and under the condition that the probability value is in a fourth preset range, determining the alarm level as three-level alarm.

In one embodiment, the apparatus for determining a probability value of occurrence of a geological landslide hazard further includes a fifth processing module for acquiring a plurality of historical landslide hazard data and a plurality of historical rainfall data of the area to be studied before determining the target prediction model from the plurality of prediction models; determining a first historical rainfall total amount in a first historical time period and a second historical rainfall total amount in a second historical time period according to the historical landslide hazard data and the historical rainfall data; determining a rainfall threshold curve according to each historical landslide hazard data, each first historical rainfall amount and each second historical rainfall amount; and determining a corresponding prediction model according to each rainfall threshold curve.

The device for determining the probability value of the occurrence of the geological landslide disaster comprises a processor and a memory, wherein the first processing module, the first acquisition module, the second processing module, the third processing module, the fourth processing module, the fifth processing module and the like are all stored in the memory as program units, and the processor executes the program modules stored in the memory to realize corresponding functions.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and the method for determining the probability value of the occurrence of the geological landslide disaster is realized by adjusting the parameters of the kernel.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the application provides a processor, which is used for running a program, wherein the program runs to execute the method for determining the probability value of occurrence of geological landslide disasters.

The embodiment of the application provides a storage medium, and a program is stored on the storage medium, and the program is executed by a processor to realize the method for determining the probability value of occurrence of geological landslide disasters.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 3. The computer device includes a processor a01, a network interface a02, a memory (not shown) and a database (not shown) connected by a system bus. Wherein the processor a01 of the computer device is adapted to provide computing and control capabilities. The memory of the computer device includes internal memory a03 and nonvolatile storage medium a04. The nonvolatile 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 nonvolatile storage medium a04. The database of the computer device is used for storing rainfall total data and landslide disaster data. The network interface a02 of the computer device is used for communication with an external terminal through a network connection. The computer program B02, when executed by the processor a01, implements a method of determining a probability value of occurrence of a geological landslide hazard.

It will be appreciated by those skilled in the art that the structure shown in fig. 3 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

The embodiment of the application provides equipment, which comprises a processor, a memory and a program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the following steps: determining a target prediction model from a plurality of prediction models; acquiring a plurality of grids of an area to be studied, wherein each grid comprises a plurality of grid points; for each grid, acquiring a first predicted rainfall amount of each grid point included in the grid in a first target time period and a second predicted rainfall amount in a second target time period; for each grid point, sequentially inputting the first predicted rainfall total amount and the second predicted rainfall total amount of the grid point into a target prediction model to obtain a prediction result of geological landslide disaster of the grid point output by the target prediction model; and determining the probability value of the geological landslide disaster at the target position in the grid according to all the prediction results aiming at any grid.

In one embodiment, determining the target predictive model from the plurality of predictive models includes: obtaining a plurality of sample data, wherein each sample data comprises a first historical rainfall amount and a second historical rainfall amount; inputting each sample data into the prediction model in turn aiming at each prediction model to obtain a prediction result corresponding to the sample data output by the prediction model; aiming at each prediction model, determining prediction parameters of the prediction model according to the matching degree of the prediction result and the historical occurrence condition of landslide hazard; for each prediction model, determining a comprehensive evaluation index of the prediction model according to the prediction parameters; and determining a prediction model corresponding to the comprehensive evaluation index with the largest numerical value as a target prediction model.

In one embodiment, the prediction parameters include hit rate, false positive rate and critical success index, and for each prediction model, determining the prediction parameters of the prediction model according to the matching degree of the prediction result and the historical occurrence of landslide hazard includes: the predicted result is expressed as geological landslide disasters, and the occurrence frequency of the geological landslide disasters with the historical occurrence condition being the historical occurrence is determined to be a first numerical value; the predicted result is expressed as no geological landslide disaster, the historical occurrence condition is the occurrence frequency of the historical non-occurrence geological landslide disaster, and the number of occurrence times is determined to be a second numerical value; the predicted result is expressed as no geological landslide disaster, the historical occurrence condition is the occurrence frequency of the historical occurrence of the geological landslide disaster, and the occurrence frequency is determined to be a third numerical value; the predicted result is expressed as geological landslide disasters, the historical occurrence condition is that the occurrence frequency of the geological landslide disasters does not occur is determined to be a fourth numerical value; determining a hit rate according to the first value and the second value; determining a false alarm rate according to the first value and the fourth value; and determining a critical success index according to the first value, the third value and the fourth value.

In one embodiment, for any one grid, determining a probability value of occurrence of a geological landslide hazard at a target location in the grid according to all prediction results includes: calculating a probability value according to formula (1):

Wherein,,Z ₀ representing probability value, Z _i Representing the prediction result of the ith grid point of the grid, D _i Represents the distance between the target position and the grid point, p represents the power of the distance, n represents the total number of grid points, i represents the ith grid point, X _o Longitude coordinates representing the target position, Y _o Representing latitude coordinates of the target position, X _i Representing longitude coordinates of the ith grid point, Y _i Representing the latitude coordinate of the ith grid point.

In one embodiment, after determining the probability value of the occurrence of the geological landslide hazard at the target position in the grid according to all the prediction results for any one grid, the method further comprises: an alert level for the target location is determined based on the probability value.

In one embodiment, determining the alert level for the target location based on the probability value includes: under the condition that the probability value is in a first preset range, determining that no alarm is needed at the target position; under the condition that the probability value is in a second preset range, determining the alarm level as a primary alarm; under the condition that the probability value is in a third preset range, determining the alarm level as a secondary alarm; and under the condition that the probability value is in a fourth preset range, determining the alarm level as three-level alarm.

In one embodiment, the method further comprises: before determining a target prediction model from a plurality of prediction models, acquiring a plurality of historical landslide disaster data and a plurality of historical rainfall data of a region to be researched; determining a first historical rainfall total amount in a first historical time period and a second historical rainfall total amount in a second historical time period according to the historical landslide hazard data and the historical rainfall data; determining a rainfall threshold curve according to each historical landslide hazard data, each first historical rainfall amount and each second historical rainfall amount; and determining a corresponding prediction model according to each rainfall threshold curve.

The present application also provides a computer program product adapted to perform a program initialized with method steps such as determining a probability value of occurrence of a geological landslide hazard when executed on a data processing device.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

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

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer 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 disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims (10)

1. A method of determining a probability value of occurrence of a geological landslide hazard, the method comprising:

determining a target prediction model from a plurality of prediction models;

acquiring a plurality of grids of an area to be studied, wherein each grid comprises a plurality of grid points;

For each grid, acquiring a first predicted rainfall total amount of each grid point included in the grid in a first target time period and a second predicted rainfall total amount in a second target time period;

for each grid point, sequentially inputting the first predicted rainfall total amount and the second predicted rainfall total amount of the grid point into the target prediction model to obtain a prediction result of the geological landslide disaster of the grid point output by the target prediction model;

and determining the probability value of the geological landslide disaster occurring at the target position in any grid according to all the prediction results.

2. The method of claim 1, wherein determining a target prediction model from a plurality of prediction models comprises:

obtaining a plurality of sample data, wherein each sample data comprises a first historical rainfall amount and a second historical rainfall amount;

inputting each sample data into each prediction model in turn aiming at each prediction model to obtain a prediction result corresponding to the sample data output by the prediction model;

for each prediction model, determining prediction parameters of the prediction model according to the matching degree of the prediction result and the historical occurrence condition of the landslide hazard;

For each prediction model, determining a comprehensive evaluation index of the prediction model according to the prediction parameters;

and determining a prediction model corresponding to the comprehensive evaluation index with the largest numerical value as a target prediction model.

3. The method of claim 2, wherein the prediction parameters include hit rate, false positive rate, and critical success index, and wherein for each prediction model, determining the prediction parameters of the prediction model according to the degree of matching between the prediction result and the historical occurrence of the landslide hazard comprises:

the prediction result is expressed as geological landslide disasters, the historical occurrence condition is the occurrence frequency of the geological landslide disasters, and the occurrence frequency is determined to be a first numerical value;

the predicted result is expressed as no geological landslide disaster, the historical occurrence condition is the occurrence frequency of the historical non-occurrence geological landslide disaster, and the occurrence frequency is determined to be a second numerical value;

the prediction result is expressed as no geological landslide disaster, the historical occurrence condition is the occurrence frequency of the historical occurrence of the geological landslide disaster, and the occurrence frequency is determined to be a third numerical value;

the predicted result is expressed as geological landslide disaster, the historical occurrence condition is the occurrence frequency of the historical non-occurrence geological landslide disaster, and the occurrence frequency is determined to be a fourth numerical value;

Determining the hit rate according to the first value and the second value;

determining the false alarm rate according to the first value and the fourth value;

and determining the critical success index according to the first value, the third value and the fourth value.

4. The method according to claim 1, wherein determining, for any one grid, a probability value of occurrence of a geological landslide hazard at a target location in the grid according to all prediction results, comprises: calculating the probability value according to formula (1):

wherein,,Z ₀ representing the probability value, Z _i Representing the prediction result of the ith grid point of the grid, D _i Represents the distance between the target position and the grid point, p represents the power of the distance, n represents the total number of grid points, i represents the ith grid point, X _o Longitude coordinates representing the target position, Y _o Representing latitude coordinates of the target position, X _i Representing longitude coordinates of the ith grid point, Y _i Representing the latitude coordinate of the ith grid point.

5. The method of claim 1, wherein after determining the probability value of occurrence of a geological landslide hazard at a target location in any one of the grids based on all of the predictions, the method further comprises:

And determining an alarm level for the target position according to the probability value.

6. The method of claim 5, wherein the determining an alert level for the target location based on the probability value comprises:

under the condition that the probability value is in a first preset range, determining that no alarm is needed at the target position;

under the condition that the probability value is in a second preset range, determining the alarm level as a primary alarm;

under the condition that the probability value is in a third preset range, determining the alarm level as a secondary alarm;

and under the condition that the probability value is in a fourth preset range, determining the alarm level as a three-level alarm.

7. The method according to claim 1, wherein the method further comprises:

before a target prediction model is determined from a plurality of prediction models, acquiring a plurality of historical landslide disaster data and a plurality of historical rainfall data of the region to be researched;

determining a first historical rainfall total amount in a first historical time period and a second historical rainfall total amount in a second historical time period according to the historical landslide disaster data and the historical rainfall data;

Determining a rainfall threshold curve according to each historical landslide hazard data, each first historical rainfall amount and each second historical rainfall amount;

and determining a corresponding prediction model according to each rainfall threshold curve.

8. A processor configured to perform the method of determining a probability value of occurrence of a geological landslide hazard of any one of claims 1 to 7.

9. An apparatus for determining a probability value of occurrence of a geological landslide hazard, the apparatus comprising:

the first processing module is used for determining a target prediction model from a plurality of prediction models;

a first acquisition module for acquiring a plurality of grids of an area to be studied, wherein each grid comprises a plurality of grid points;

a second acquisition module for acquiring, for each grid, a first predicted total rainfall amount in a first target period and a second predicted total rainfall amount in a second target period for each grid point included in the grid;

the second processing module is used for inputting the first predicted rainfall total amount and the second predicted rainfall total amount of each grid point into the target prediction model in sequence to obtain a prediction result of the geological landslide disaster, which is output by the target prediction model, of the grid points;

And the third processing module is used for determining the probability value of the geological landslide disaster at the target position in the grid according to all the prediction results aiming at any grid.

10. A machine-readable storage medium having instructions stored thereon, which when executed by a processor cause the processor to be configured to perform the method of determining a probability value of occurrence of a geological landslide hazard of any one of claims 1 to 7.