Landslide monitoring method

Abstract

The invention discloses a landslide monitoring method, and relates to the technical field of electric power. The method comprises the steps that a landslide hidden danger area is determined based on mountain slope information, vegetation coverage types and rainfall distribution conditions of an area where a power grid is located, and the landslide hidden danger area is the area where the mountain stability is low and the landslide risk exists in the area where the power grid is located; predicting the landslide volume of the landslide hidden danger area to obtain a landslide volume prediction value; based on the moisture state of the landslide hidden danger area, the moisture space-time change rate and the moisture abnormal range of the landslide hidden danger area are determined, and the moisture state at least comprises the soil layer moisture content; and determining a monitoring result according to the landslide volume predicted value, the moisture temporal-spatial change rate and the moisture abnormal range, the monitoring result being used for representing the danger degree of the landslide hidden danger area. The technical problem that the monitoring accuracy of the landslide is low is solved.

Description

Technical Field

[0001] The invention relates to the field of electric power technology, and in particular to a method for monitoring landslides. Background Art

[0002] Power transmission lines, substations, distribution facilities and other power grid equipment distributed in mountainous areas may be threatened by landslides and other geohazards. Therefore, monitoring of landslide risk areas can provide early warning for high-risk areas and provide security for power grid operation, which is very important and indispensable.

[0003] Related technologies usually rely on ground measurements when assessing the impact of precipitation on landslides and determining landslide risk areas. However, the efficiency of ground measurements is limited and large-scale, high-frequency monitoring cannot be achieved. The data obtained from the measurements is limited, resulting in low accuracy in monitoring landslides.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiment of the present invention provides a method for monitoring a landslide, so as to at least solve the technical problem of low accuracy in monitoring a landslide.

[0006] According to one aspect of an embodiment of the present invention, a method for monitoring landslides is provided, comprising: determining a landslide hazard area based on mountain slope information, vegetation coverage type, and precipitation distribution in an area where a power grid is located, wherein the landslide hazard area is an area in the area where the power grid is located where the mountain stability is low and there is a risk of landslides; predicting the landslide volume in the landslide hazard area to obtain a landslide volume prediction value; determining the spatiotemporal change rate of moisture and a moisture anomaly range in the landslide hazard area based on the moisture state in the landslide hazard area, wherein the moisture state includes at least the moisture content of the soil layer; determining a monitoring result based on the landslide volume prediction value, the spatiotemporal change rate of moisture, and the moisture anomaly range, wherein the monitoring result is used to characterize the degree of danger of the landslide hazard area.

[0007] Optionally, predicting the landslide volume in the landslide hazard area to obtain a landslide volume prediction value includes: obtaining mountain structure characteristics in the landslide hazard area, wherein the mountain structure characteristics include at least one of the following: mountain elevation, mountain slope, mountain aspect, vegetation index, precipitation, and rock edge movement rate; inputting the mountain structure characteristics into a landslide volume prediction model, and using the landslide volume prediction model to predict the landslide volume in the landslide hazard area to obtain a landslide volume prediction value.

[0008] Optionally, based on the moisture status of the landslide hazard area, the spatiotemporal moisture change rate and the moisture anomaly range of the landslide hazard area are determined, including: determining at least one key analysis area in the landslide hazard area, wherein at least one key analysis area is an area with abnormal surface temperature in the landslide hazard area; obtaining the surface temperature, atmospheric temperature, vegetation index and precipitation of at least one key analysis area at different times; inputting the surface temperature, atmospheric temperature, vegetation index and precipitation of at least one key analysis area at different times into a moisture prediction model, and using the moisture prediction model to predict the moisture status of at least one key analysis area at different times to obtain the moisture status of at least one key analysis area at different times; based on the moisture status of at least one key analysis area at different times, determining the spatiotemporal moisture change rate and the moisture anomaly range.

[0009] Optionally, based on the moisture status of at least one key analysis area at different moments, the spatiotemporal moisture change rate and the moisture abnormality range are determined, including: determining the moisture change rate of at least one key analysis area based on the moisture status of at least one key analysis area at different moments; determining the spatiotemporal moisture change rate based on the moisture change rate of at least one key analysis area; comparing the moisture change rate of at least one key analysis area with a preset change rate to determine whether at least one key analysis area is in an abnormal moisture state, wherein the abnormal moisture state is used to characterize that the moisture change rate is greater than the preset change rate; and determining the abnormal moisture range according to the range of the key analysis area in the abnormal moisture state.

[0010] Optionally, determining at least one key analysis area in the landslide hazard area includes: acquiring a satellite thermal infrared image of the landslide hazard area; processing the satellite thermal infrared image to obtain thermal infrared radiation brightness; using a single scattering inversion algorithm to process the thermal infrared radiation brightness to obtain surface temperature data of the landslide hazard area; using a clustering algorithm to identify abnormal data in the surface temperature data, and determining the area corresponding to the abnormal data as the key analysis area.

[0011] Optionally, the monitoring results are determined according to the predicted landslide volume, the spatiotemporal variation rate of moisture and the abnormal moisture range, including: respectively determining the weights of the predicted landslide volume, the spatiotemporal variation rate of moisture and the abnormal moisture range; determining the hazard factor of the landslide potential area based on the predicted landslide volume, the spatiotemporal variation rate of moisture, the abnormal moisture range, and the weight of the predicted landslide volume, the weight of the spatiotemporal variation rate of moisture and the weight corresponding to the abnormal moisture range; determining the monitoring results according to the hazard factor of the landslide potential area.

[0012] Optionally, the landslide hazard area is determined based on the mountain slope information, vegetation coverage type and precipitation distribution of the area where the power grid is located, including: determining at least one slope abnormality area based on the mountain slope information of the area where the power grid is located; inputting the vegetation coverage type and precipitation distribution of at least one slope abnormality area into a mathematical model, and using the mathematical model to predict the mountain stability index of the at least one slope abnormality area to obtain the mountain stability index of the at least one slope abnormality area; determining the landslide hazard area in at least one slope abnormality area according to the mountain stability index of the at least one slope abnormality area.

[0013] Optionally, at least one area with abnormal slope is determined based on the mountain slope information of the power grid area, including: dividing the area where the power grid is located into multiple areas to be determined; obtaining the mountain slope information of the multiple areas to be determined; judging whether the mountain slope information of the multiple areas to be determined is within a preset slope range; and determining the area to be determined whose mountain slope information is within the preset slope range as an area with abnormal slope.

[0014] Optionally, a landslide hazard area in at least one slope abnormality area is determined based on a mountain stability index of at least one slope abnormality area, including: determining a slope abnormality area whose mountain stability index is within a preset index range as a candidate landslide hazard area; determining a rock edge movement rate of the candidate landslide hazard area based on the bare rock distribution in the candidate landslide hazard area; when the rock edge movement rate of the candidate landslide hazard area is greater than a preset rate, determining the candidate landslide hazard area as a landslide hazard area.

[0015] Optionally, the method further includes: determining a landslide response strategy based on the monitoring results; and performing emergency treatment on power grid equipment in the landslide hazard area according to the landslide response strategy.

[0016] According to another aspect of an embodiment of the present invention, a monitoring device for landslides is also provided, including: a first determination module, used to determine a landslide hazard area based on mountain slope information, vegetation coverage type and precipitation distribution in the area where the power grid is located, wherein the landslide hazard area is an area in the area where the power grid is located where the mountain stability is low and there is a risk of landslide; a prediction module, used to predict the landslide volume in the landslide hazard area and obtain a landslide volume prediction value; a second determination module, used to determine the spatiotemporal change rate of moisture and the moisture abnormality range in the landslide hazard area based on the moisture state of the landslide hazard area, wherein the moisture state at least includes the moisture content of the soil layer; a third determination module, used to determine a monitoring result based on the landslide volume prediction value, the spatiotemporal change rate of moisture and the moisture abnormality range, wherein the monitoring result is used to characterize the degree of danger of the landslide hazard area.

[0017] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the above-mentioned landslide monitoring method is executed when the program is running.

[0018] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, including: the computer-readable storage medium includes a stored executable program, wherein when the executable program runs, the device where the storage medium is located is controlled to execute the above-mentioned landslide monitoring method.

[0019] According to another aspect of an embodiment of the present invention, a computer program product is provided, including: a computer program, and when the computer program is executed by a processor, the computer program implements the above-mentioned landslide monitoring method.

[0020] In an embodiment of the present invention, a landslide hazard area is determined based on the mountain slope information, vegetation coverage type and precipitation distribution in the area where the power grid is located, wherein the landslide hazard area is an area where the mountain stability in the area where the power grid is located is low and there is a risk of landslide; the landslide volume in the landslide hazard area is predicted to obtain a landslide volume prediction value; based on the moisture state of the landslide hazard area, the spatiotemporal change rate of moisture and the moisture abnormal range in the landslide hazard area are determined; and the monitoring result is determined according to the landslide volume prediction value, the spatiotemporal change rate of moisture and the moisture abnormal range. It is easy to notice that the landslide hazard area is determined by the mountain slope information, vegetation coverage type and precipitation distribution, and the detection result is determined using the landslide volume prediction value, the spatiotemporal change rate of moisture and the moisture abnormal range in the landslide hazard area, which fully considers the influence of the mountain's own slope and vegetation coverage on the landslide, and predicts the landslide volume, overcomes the disadvantage that ground measurement cannot achieve large-scale and high-frequency monitoring, and achieves the technical effect of improving the monitoring accuracy of landslides, thereby solving the technical problem of low monitoring accuracy of landslides. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0022] Figure 1 is a flow chart of a landslide monitoring method according to an embodiment of the present invention;

[0023] Figure 2 is a flow chart of an optional landslide monitoring method according to an embodiment of the present invention;

[0024] Figure 3 is a flow chart of an optional locking of a landslide hazard area according to an embodiment of the present invention;

[0025] Figure 4 is another optional flow chart for locking a landslide hazard area according to an embodiment of the present invention;

[0026] Figure 5 is a schematic diagram of a landslide monitoring device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Example 1

[0030] According to an embodiment of the present invention, an embodiment of a method for monitoring a landslide is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Figure 1 FIG. 1 is a flow chart of a landslide monitoring method according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0032] Step S102, based on the mountain slope information, vegetation coverage type and precipitation distribution of the area where the power grid is located, determine the landslide hazard area, wherein the landslide hazard area is an area in the area where the power grid is located where the mountain stability is low and there is a risk of landslide.

[0033] The mountain slope information in the above steps is the mountain slope in the area where the power grid is located. The mountain slope is the ratio of the surface in the vertical direction to the horizontal direction, and is usually used to describe the inclination of the terrain. A steeper slope may be more prone to landslides.

[0034] The vegetation coverage type in the above steps refers to the type of plants covering the surface of the area where the power grid is located. Different types of vegetation, such as coniferous forests, broad-leaved forests, grasslands, etc., have different physical and ecological characteristics, which will affect the stability of the soil and its ability to retain water, and thus affect the probability of landslides.

[0035] The precipitation distribution in the above steps refers to the spatial distribution of precipitation in different regions or at different times over a period of time. Precipitation is one of the important factors that induce landslides. Heavy precipitation may cause soil saturation and increase the risk of landslides.

[0036] In an optional embodiment, the Normalized Difference Vegetation Index (NDVI) can be obtained through satellite remote sensing images that can reflect the vegetation coverage and vitality, and the vegetation coverage type of the power grid area can be determined. Then, the power grid area can be divided according to the different vegetation coverage types to obtain the distribution areas of different types of vegetation. The digital elevation model (DEM) is used to determine the mountain slope information of the distribution areas of different types of vegetation.

[0037] For example, the NDVI of coniferous forests is generally between 0.5 and 0.8. If the NDVI of a certain area extracted from satellite remote sensing images is 0.6, it can be determined that the area is a coniferous forest distribution area. Then the digital elevation model DEM can be used to determine the mountain slope information of these coniferous forest areas. Each pixel in the DEM data corresponds to an elevation value, and the elevation change of adjacent pixels can be calculated to obtain the mountain slope information. If the slope obtained is 35 degrees, it is determined that the area is a coniferous forest distribution area with a mountain slope of 35°.

[0038] According to the mountain slope information of the distribution areas of different types of vegetation, the distribution areas with mountain slopes greater than the slope threshold are determined. The satellite cloud image data of the highest cloud cover period in these distribution areas are obtained, and the precipitation distribution in the distribution areas is determined through the satellite cloud image data. The vegetation coverage type, mountain slope information, and precipitation distribution of the distribution area are input into the trained model, and the mountain stability of the distribution area is predicted through the model. The distribution area with mountain stability lower than the stability threshold is determined as a landslide hazard area.

[0039] It should be noted that the above-mentioned slope threshold and stability threshold can be set according to the actual application situation. The specific values ​​of the slope threshold and stability threshold are not limited here, and the numerical values ​​in the above examples are only examples. The numerical values ​​involved in actual applications may not be limited to this.

[0040] Step S104, predicting the landslide volume in the landslide potential area to obtain a landslide volume prediction value.

[0041] The landslide volume prediction value in the above steps is obtained by predicting the landslide volume when a landslide occurs in the landslide potential area. The landslide volume is the amount of earth and stone that slides down from the original position in the landslide potential area during the entire landslide process.

[0042] In an optional embodiment, a high-resolution satellite image of the landslide hazard area is obtained, and DEM numerical elevation data within the image coverage range is extracted from the high-resolution satellite image, and GPS point cloud data of the landslide hazard area is obtained through the Global Positioning System (GPS) technology. Based on the DEM data and the GPS point cloud data, a triangulated mesh construction method is used to establish a three-dimensional digital elevation model, and the mountain structure data is extracted from the three-dimensional digital elevation model.

[0043] The neural network model is trained using historical mountain structure data of landslide-prone areas, so that the neural network model has the ability to predict landslide volume based on mountain structure data. The trained neural network model is used to process mountain structure data to generate landslide volume prediction values.

[0044] Step S106, based on the moisture state of the landslide potential area, determining the spatiotemporal change rate of moisture and the moisture anomaly range in the landslide potential area, wherein the moisture state at least includes the moisture content of the soil layer.

[0045] The spatiotemporal moisture change rate in the above steps is the speed of change of soil moisture content in the landslide potential area, which is usually expressed by dividing the change by time, that is, the change in moisture content per unit time.

[0046] The moisture abnormality range in the above steps is the area of ​​the region in the landslide potential area that is in an abnormal moisture state. The moisture abnormality state is a state in which the change of the moisture content of the soil layer exceeds the normal or expected range.

[0047] The soil moisture content in the above step refers to the amount of water contained in the soil.

[0048] In an optional embodiment, a trained gradient boosting decision tree model is used to predict the soil moisture content of the landslide hazard area at different times. Then, the soil moisture content of the landslide hazard area at different times is divided by the time interval between different times to determine the spatiotemporal change rate of moisture in the landslide hazard area. By comparing the spatiotemporal change rate of moisture with the change rate threshold, it is determined whether the landslide hazard area is in an abnormal moisture state. If it is in an abnormal moisture state, the area of ​​the landslide hazard area is used as the abnormal moisture range.

[0049] In another optional embodiment, the landslide hazard area is divided into different partitions, and the trained gradient boosting decision tree model is used to predict the soil moisture content of different partitions, and then the spatiotemporal change rate of moisture in different partitions is calculated. According to the relationship between the change rate threshold and the spatiotemporal change rate of moisture in different partitions, it is judged whether different partitions are in an abnormal moisture state, the area of ​​each partition in an abnormal moisture state is determined, and the areas of all partitions in an abnormal moisture state are added to obtain the abnormal moisture range.

[0050] It should be noted that the above change rate threshold can be set according to actual application conditions, and the specific value of the change rate threshold is not limited here.

[0051] Step S108, determining the monitoring result according to the predicted landslide volume, the spatiotemporal change rate of moisture and the abnormal moisture range, wherein the monitoring result is used to characterize the danger level of the landslide potential area.

[0052] The monitoring results in the above steps may include high risk, medium risk, and low risk, but are not limited thereto.

[0053] In an optional embodiment, the slope volume prediction value, the spatiotemporal change rate of moisture and the moisture abnormal range can be normalized, and the slope volume prediction value, the spatiotemporal change rate of moisture and the moisture abnormal range are normalized to between 0 and 1 respectively. Then the slope volume prediction value, the spatiotemporal change rate of moisture and the moisture abnormal range are calculated and weighted and summed to obtain a weighted result. The weight can be set according to industry experience, reference materials or actual conditions, and the specific value of the weight is not limited here. According to the mapping relationship between the pre-set weighted result and the monitoring result, the monitoring result corresponding to the weighted result is determined. Exemplarily, the mapping relationship between the weighted result and the monitoring result can be that the weighted result is greater than or equal to 4, then the landslide hazard area is a high risk; the weighted result is greater than or equal to 2 and less than 4, then the landslide hazard area is a medium risk; the weighted result is less than 2, then the landslide hazard area is a low risk. If the weighted result is 4.7, the monitoring result is that the landslide hazard area is a high risk. It should be noted that the numerical values ​​in the above examples are only examples, and the numerical values ​​involved in actual applications may not be limited to this.

[0054] In an embodiment of the present invention, a landslide hazard area is determined based on the mountain slope information, vegetation coverage type and precipitation distribution in the area where the power grid is located, wherein the landslide hazard area is an area in the area where the power grid is located where the mountain stability is low and there is a risk of landslide; the landslide volume in the landslide hazard area is predicted to obtain a landslide volume prediction value; based on the moisture state of the landslide hazard area, the spatiotemporal change rate of moisture and the moisture abnormal range in the landslide hazard area are determined; and the monitoring result is determined according to the landslide volume prediction value, the spatiotemporal change rate of moisture and the moisture abnormal range. It is easy to notice that the landslide hazard area is determined by the mountain slope information, vegetation coverage type and precipitation distribution, and the detection result is determined by using the landslide volume prediction value, the spatiotemporal change rate of moisture and the moisture abnormal range in the landslide hazard area, which fully considers the influence of the mountain's own slope and vegetation coverage on the landslide, achieves the technical effect of improving the monitoring accuracy of the landslide, and thus solves the technical problem of low monitoring accuracy of the landslide.

[0055] Optionally, predicting the landslide volume in the landslide hazard area to obtain a landslide volume prediction value includes: obtaining mountain structure characteristics in the landslide hazard area, wherein the mountain structure characteristics include at least one of the following: mountain elevation, mountain slope, mountain aspect, vegetation index, precipitation, and rock edge movement rate; inputting the mountain structure characteristics into a landslide volume prediction model, and using the landslide volume prediction model to predict the landslide volume in the landslide hazard area to obtain a landslide volume prediction value.

[0056] The mountain structure features in the above steps are the physical and geometric properties of the mountain.

[0057] The mountain elevation in the above steps is the height of the highest point of the mountain relative to sea level or a certain reference surface, which can be used to determine the absolute height of the mountain and the undulation of the terrain.

[0058] The mountain slope in the above steps refers to the inclination of the ground surface on the horizontal plane, usually expressed as an angle or percentage. The greater the mountain slope, the steeper the inclination of the ground surface.

[0059] The slope aspect in the above steps is the inclination direction of the mountain slope, usually measured clockwise from a certain reference direction. The slope aspect is very important for understanding solar radiation, precipitation distribution, and surface water flow direction.

[0060] The vegetation index in the above steps is an indicator to measure the density and health of vegetation, namely NDVI.

[0061] The precipitation in the above steps refers to the total amount of water that falls to the ground in a certain period of time, usually in millimeters or inches. Precipitation is an important factor affecting the occurrence of landslides. Precipitation increases the moisture content of the soil and may reduce the stability of the soil.

[0062] The rock edge movement rate in the above steps refers to the speed at which the rock edge in the mountain moves due to weathering, erosion or other geological actions. A higher rock edge movement rate can indicate potential landslide activity.

[0063] The landslide volume prediction model in the above steps can be a back propagation neural network (BP neural network model for short), a radial basis function network (RBF for short), or a convolutional neural network (CNN for short), but is not limited to these.

[0064] In an optional embodiment, the mountain elevation, mountain slope, mountain aspect, vegetation index, precipitation, and rock edge movement rate of the landslide potential area can be extracted as mountain structure characteristics from a three-dimensional digital elevation model constructed based on DEM numerical elevation data and GPS point cloud data.

[0065] Construct a BP neural network model, that is, a landslide volume prediction model, obtain the historical mountain structure characteristics of the landslide potential area as training data, train the BP neural network model, adjust the BP neural network model parameters to obtain the best fit, and obtain a trained BP neural network model. Input the mountain structure characteristics into the trained BP neural network model to obtain the landslide volume prediction value.

[0066] Exemplarily, a data set for training the BP neural network model is constructed, with the landslide volume as the dependent variable, and the mountain elevation, mountain slope, mountain aspect, vegetation index, precipitation and rock edge movement rate as independent variables. The mountain aspect adopts the azimuth, with the north direction as 0 degrees, clockwise measurement, southeast direction is about 45 degrees to 135 degrees, northeast direction is about 135 degrees to 225 degrees, southwest direction is about 225 degrees to 315 degrees, and northwest direction is about 315 degrees to 45 degrees. 1000 sample points are selected as the training set, and another 500 sample points are used as the test set to train the BP neural network model, and the model parameters are adjusted to obtain the best fit.

[0067] In the prediction stage, the mountain elevation in the landslide hazard area is 950 meters, the mountain slope is 18°, the mountain slope is 45°, the vegetation index is 0.6, the precipitation is 50 mm, and the rock edge movement rate is 1 meter per year. The mountain structure characteristics of the landslide hazard area are input into the trained BP neural network model to obtain the landslide volume prediction value.

[0068] It should be noted that the numerical values ​​in the above examples are only examples, and the numerical values ​​involved in actual applications may not be limited to these.

[0069] Optionally, based on the moisture status of the landslide hazard area, the spatiotemporal moisture change rate and the moisture anomaly range of the landslide hazard area are determined, including: determining at least one key analysis area in the landslide hazard area, wherein at least one key analysis area is an area with abnormal surface temperature in the landslide hazard area; obtaining the surface temperature, atmospheric temperature, vegetation index and precipitation of at least one key analysis area at different times; inputting the surface temperature, atmospheric temperature, vegetation index and precipitation of at least one key analysis area at different times into a moisture prediction model, and using the moisture prediction model to predict the moisture status of at least one key analysis area at different times to obtain the moisture status of at least one key analysis area at different times; based on the moisture status of at least one key analysis area at different times, determining the spatiotemporal moisture change rate and the moisture anomaly range.

[0070] The surface temperature in the above steps refers to the temperature of natural objects such as rocks, soil, and water on the earth's surface. It can be measured by thermal infrared remote sensing and is usually measured in degrees Celsius.

[0071] The atmospheric temperature in the above steps refers to the average kinetic energy of gas molecules in the atmosphere at a certain altitude, usually expressed as air temperature.

[0072] The moisture prediction model in the above steps can be a gradient boosting decision tree model, but is not limited thereto. The gradient boosting decision tree is an ensemble learning algorithm that improves the prediction performance of the model by combining multiple decision tree weak predictors. The basic idea of ​​gradient boosting is to first build a basic decision tree model, and then gradually add new decision trees based on the prediction error of the model. The prediction direction of the new tree is the gradient direction that reduces the overall model error. The trained gradient boosting decision tree model can be used to predict the moisture status of at least one key analysis area at different times.

[0073] In an optional embodiment, the surface temperature of the landslide potential area may be obtained, and the area with abnormal surface temperature is taken as a key analysis area, and there is at least one key analysis area.

[0074] The soil moisture content measured at different historical moments in the key analysis area and the surface temperature, atmospheric temperature, vegetation index and precipitation corresponding to different historical moments are used as training data sets and test data sets. The training data set and the test data set are divided according to a ratio. An optimal ratio is 7:3, but not limited to this. The training data set is used to train the gradient boosting decision tree model, and the test data set is used to test the gradient boosting decision tree model. The grid search method is used to adjust the learning rate and the number of trees to optimize the performance of the model, and a trained gradient boosting decision tree model is obtained.

[0075] The surface temperature of at least one key analysis area at different times is obtained using satellite thermal infrared images, the atmospheric temperature of at least one key analysis area at different times is obtained using satellite sensors, the vegetation index NDVI of at least one key analysis area at different times is obtained through satellite remote sensing images, and the precipitation of at least one key analysis area at different times is obtained through satellite cloud images. The surface temperature, atmospheric temperature, vegetation index and precipitation of at least one key analysis area at different times are input into the trained gradient boosting decision tree model to obtain the moisture state of at least one key analysis area at different times predicted by the gradient boosting decision tree model.

[0076] Exemplarily, the surface temperature data at time A, time B and time C are obtained using satellite thermal infrared images. The surface temperature at time A is 28°C, the surface temperature at time B is 32°C, and the surface temperature at time C is 30°C. Then, the atmospheric temperature data is obtained using satellite sensors, and the vegetation index and precipitation are obtained. The atmospheric temperature at time A is 25°C, the vegetation index is 0.5, and the precipitation is 10mm. The atmospheric temperature at time B is 28°C, the vegetation index is 0.6, and the precipitation is 15mm. The atmospheric temperature at time C is 27°C, the vegetation index is 0.7, and the precipitation is 12mm. The data at time A, specifically the surface temperature of 28°C, the atmospheric temperature of 25°C, the vegetation index of 0.5, and the precipitation of 10mm, are input into the trained gradient boosting decision tree model, and the soil moisture content predicted by the model is 12%. The prediction of soil moisture content at time B and time C is similar, and will not be repeated here. It should be noted that the numerical values ​​in the above examples are only examples, and the numerical values ​​involved in actual applications may not be limited to these.

[0077] After obtaining the moisture state of at least one key analysis area at different times, that is, the layer moisture content, the spatiotemporal moisture change rate and the moisture anomaly range can be determined based on the moisture state of at least one key analysis area at different times.

[0078] Optionally, based on the moisture status of at least one key analysis area at different moments, the spatiotemporal moisture change rate and the moisture abnormality range are determined, including: determining the moisture change rate of at least one key analysis area based on the moisture status of at least one key analysis area at different moments; determining the spatiotemporal moisture change rate based on the moisture change rates of multiple key analysis areas; comparing the moisture change rate of at least one key analysis area with a preset change rate to determine whether at least one key analysis area is in an abnormal moisture state, wherein the abnormal moisture state is used to characterize that the moisture change rate is greater than the preset change rate; determining the abnormal moisture range according to the range of the key analysis area in the abnormal moisture state.

[0079] The preset change rate in the above steps is a preset change rate, which can be preset according to actual application conditions, and no restriction is imposed on the specific value of the predicted change rate.

[0080] The moisture change rate in the above steps can characterize the moisture change in the key analysis area, and the moisture change rates of multiple key analysis areas can be used to determine the spatiotemporal moisture change rate.

[0081] In an optional embodiment, according to the soil moisture content of at least one key analysis area at different times, the spatiotemporal change rate of moisture in at least one key analysis area at different times is calculated, and the calculation formula of the moisture change rate is as follows:

[0082] k = ΔM1 / (t2-t1);

[0083] Among them, k is the spatiotemporal change rate of moisture, ΔM1 is the difference between the moisture content of the soil layer at time t2 and the moisture content of the soil layer at time t1, and time t2 is later than time t1.

[0084] The average of the moisture change rates of multiple key analysis areas in the landslide hazard area can be calculated and used as the moisture spatiotemporal change rate. A key analysis area in the landslide hazard area can also be randomly selected and the moisture change rate of the key analysis area can be used as the moisture spatiotemporal change rate, but the method of determining the moisture spatiotemporal change rate is not limited to this.

[0085] The moisture change rate of the key analysis area is compared with the preset change rate. If the moisture change rate is greater than the preset change rate, the key analysis area is in an abnormal moisture state; if the moisture change rate is not greater than the preset change rate, the key analysis area is not in an abnormal moisture state. The area of ​​the key analysis area in an abnormal moisture state is added to obtain the area of ​​abnormal moisture, that is, the abnormal moisture range.

[0086] Optionally, determining at least one key analysis area in the landslide hazard area includes: acquiring a satellite thermal infrared image of the landslide hazard area; processing the satellite thermal infrared image to obtain thermal infrared radiation brightness; using a single scattering inversion algorithm to process the thermal infrared radiation brightness to obtain surface temperature data of the landslide hazard area; using a clustering algorithm to identify abnormal data in the surface temperature data, and determining the area corresponding to the abnormal data as the key analysis area.

[0087] The satellite thermal infrared image in the above steps is a surface temperature image obtained from a satellite using an infrared band sensor. Since the temperature of different objects will produce different thermal radiation, this satellite thermal infrared image can reveal the temperature distribution of the surface.

[0088] The thermal infrared radiation brightness in the above steps is a physical quantity that characterizes the intensity of radiation energy radiated from the surface in the thermal infrared band. Thermal infrared radiation brightness is the radiation characteristic of each pixel in the thermal infrared image, which is directly related to the surface temperature.

[0089] The single scattering inversion algorithm in the above steps is an algorithm for inverting the surface temperature based on the thermal infrared radiation brightness. The surface temperature is estimated by solving the nonlinear relationship between the thermal infrared radiation brightness and the surface temperature.

[0090] The clustering algorithm in the above steps can be a density-based spatial clustering of applications with noise (DBSCAN) algorithm, which is a density-based clustering algorithm that can divide areas with sufficiently high density into clusters, does not need to pre-specify the number of clusters, can identify clusters of any shape, and has good robustness to noise data. It can also be a hierarchical clustering algorithm or a mean shift algorithm, but is not limited to this.

[0091] In an optional embodiment, a satellite thermal infrared image of the landslide hazard area is obtained, and the original satellite thermal infrared image is preprocessed, the preprocessing includes radiation correction and denoising, and the preprocessed thermal infrared radiation brightness is obtained. The thermal infrared radiation brightness is input into a single scattering inversion algorithm, and the single scattering inversion algorithm obtains the surface temperature data by iteratively calculating the nonlinear relationship between the thermal infrared radiation brightness and the surface temperature.

[0092] The DBSCAN algorithm is used to identify whether the surface temperature data of the landslide hazard area contains abnormal data. If abnormal surface temperature data is detected, the landslide hazard area is extracted as the key analysis area.

[0093] Optionally, the monitoring results are determined according to the predicted landslide volume, the spatiotemporal variation rate of moisture and the abnormal moisture range, including: respectively determining the weights of the predicted landslide volume, the spatiotemporal variation rate of moisture and the abnormal moisture range; determining the hazard factor of the landslide potential area based on the predicted landslide volume, the spatiotemporal variation rate of moisture, the abnormal moisture range, and the weight of the predicted landslide volume, the weight of the spatiotemporal variation rate of moisture and the weight corresponding to the abnormal moisture range; determining the monitoring results according to the hazard factor of the landslide potential area.

[0094] The hazard coefficient in the above steps is used to quantify the risk of landslide in the landslide hazard area, that is, to measure the potential risk level of the landslide hazard area.

[0095] In an optional embodiment, the predicted landslide volume, the spatiotemporal change rate of moisture, and the abnormal moisture range can be normalized, and then the weights of the predicted landslide volume, the spatiotemporal change rate of moisture, and the abnormal moisture range can be preset according to the actual situation. Then, the hazard coefficient of the landslide hazard area is calculated according to the normalization result and the weight. The formula for determining the hazard coefficient of the landslide hazard area is as follows:

[0096] M = A*q1+B*q2+C*q3;

[0097] Among them, M is the hazard coefficient, A is the predicted landslide volume after normalization, B is the spatiotemporal change rate of moisture after normalization, C is the abnormal moisture range after normalization, q1 is the weight of the predicted landslide volume, q2 is the weight of the spatiotemporal change rate of moisture, and q3 is the weight of the abnormal moisture range.

[0098] For example, the predicted landslide volume in the landslide hazard area is 1000 cubic meters, the spatiotemporal change rate of moisture is 5 cubic meters per day, and the abnormal range area, that is, the moisture abnormal range is 200 square meters. First, normalization is performed to normalize the predicted landslide volume, the spatiotemporal change rate of moisture, and the abnormal range area to a range between 0 and 1. After normalization, the predicted landslide volume, the spatiotemporal change rate of moisture, and the abnormal range area are 0.5, 0.5, and 0.4, respectively. The influence weights of the predicted landslide volume, the spatiotemporal change rate of moisture, and the abnormal range area are 4, 3, and 3, respectively.

[0099] The risk factor = 0.5*4+0.5*3+0.4*3=2+1.5+1.2=4.7. The severity level of landslide events is divided according to the risk factor. If the risk factor is greater than or equal to 4, it is a high risk; if the risk factor is greater than or equal to 2 and less than 4, it is a medium risk; if the risk factor is less than 2, it is a low risk. According to the calculation results, the risk factor of the landslide hazard area is 4.7, and the monitoring result shows that the landslide risk area is a high risk.

[0100] It should be noted that the numerical values ​​in the above examples are only examples, and the numerical values ​​involved in actual applications may not be limited to these.

[0101] Optionally, the landslide hazard area is determined based on the mountain slope information, vegetation coverage type and precipitation distribution of the area where the power grid is located, including: determining at least one slope abnormality area based on the mountain slope information of the area where the power grid is located; inputting the vegetation coverage type and precipitation distribution of at least one slope abnormality area into a mathematical model, and using the mathematical model to predict the mountain stability index of the at least one slope abnormality area to obtain the mountain stability index of the at least one slope abnormality area; determining the landslide hazard area in at least one slope abnormality area according to the mountain stability index of the at least one slope abnormality area.

[0102] The slope abnormality area in the above steps is the area where the power grid is located, and the area where the slope abnormality needs to be further monitored.

[0103] The mathematical model in the above steps can be a transient rainfall infiltration and grid-based regional slope stability model (TRIGRS) model. The TRIGRS model combines rainfall infiltration and fluid dynamics principles, and can predict the possibility of slope instability by calculating the impact of groundwater flow on soil stability, thereby obtaining a mountain stability index, but is not limited to this.

[0104] The mountain stability index in the above steps is a quantitative indicator used to evaluate the stability of mountain slopes under specific environmental conditions.

[0105] In an optional embodiment, at least one abnormal slope area in the area where the power grid is located is determined based on whether the mountain slope information of each subarea in the area where the power grid is located is within a normal slope range.

[0106] Obtain satellite cloud image data for different periods of time in the slope anomaly area, and compare the cloud distribution data for different periods. Identify the period with the highest cloud cover, and obtain the cloud image of this period as the key period cloud image. According to the spatial distribution information displayed in the cloud image of the key period, the cloud area is divided into different types based on the deep convolutional neural network. Obtain representative sample areas containing multiple cloud types as analysis areas for different rainfall distribution types. The satellite quantitative precipitation estimation model QPE is used for each cloud type sample area to calculate the precipitation distribution corresponding to different cloud types. The calculation results are corrected with the measured precipitation data on the ground, and the model parameters of the satellite quantitative precipitation estimation model QPE are adjusted to improve the accuracy of the results. Finally, the precipitation distribution corresponding to different cloud types in the slope anomaly area is accurately calculated.

[0107] The vegetation index NDVI is obtained through satellite remote sensing images to determine the vegetation coverage type in the slope anomaly area. The slope range and vegetation coverage type prone to landslides are preset to determine whether there is terrain prone to landslides in each cloud type sample area. If such terrain exists, the precipitation distribution, slope and vegetation coverage type in different periods of time in the area where such terrain is located are obtained, and the TRIGRS model is used to calculate the mountain stability index under different rainfall conditions.

[0108] For example, satellite cloud image data for July, August and September in the slope anomaly area can be obtained, including different types of thick clouds, thin clouds and cumulonimbus clouds. First, the cloud detection algorithm is used to analyze the cloud cover, and it is judged that the cloud cover is the highest in mid-August. Therefore, the cloud image of August 15 is extracted as the cloud image of the key period. Then the cloud image is classified, and the deep convolutional neural network is used to divide the clouds into 5 categories, including thin clouds, thick clouds, cumulonimbus clouds, etc. Three types of clouds are selected as samples, and cloud image slices of three areas of thick clouds, thin clouds and cumulonimbus clouds are extracted respectively. The satellite quantitative precipitation estimation model QPE is started for each cloud slice, which can estimate the precipitation under the cloud based on parameters such as cloud top temperature and cloud body thickness. The precipitation inverted in the thick cloud area is 25mm, thin clouds is 5mm, and cumulonimbus clouds is 50mm. The results are compared with the actual rainfall observed by the meteorological station. If there is a large error, it is necessary to adjust the parameters inside the model and iterate the calculation again until the inversion result is close to the measured result. Afterwards, by comparing the slope range and vegetation cover type, check whether there is terrain prone to landslides in each cloud type sample area. If there is terrain prone to landslides in the thick cloud area and cumulonimbus cloud area, the coordinate position of the terrain is extracted. Finally, a quantitative stability assessment model is used to input different rainfall distributions, slopes, and vegetation cover types into the TRIGRS model to calculate the mountain stability index under different precipitation conditions. It should be noted that the values ​​in the above examples are only examples, and the values ​​involved in actual applications may not be limited to this.

[0109] When determining the landslide hazard area, the mountain stability level can be determined based on the mountain stability index. The slope abnormality area with potential instability and unstable stability level is regarded as the unstable abnormal area. Multi-phase satellite images of the unstable abnormal area are obtained. The Landsat satellite (a type) is used to obtain satellite images of four phases. Based on the multi-phase satellite images, a long-term and short-term memory network model is constructed to identify areas where vegetation coverage has changed. The vegetation index NDVI of each phase image is calculated. The specific calculation formula is:

[0110] NDVI=(NI R-RED) / (NI R+RED);

[0111] Among them, NDVI is the vegetation index, NIR is the value of the near-infrared band, and RED is the value of the red light band.

[0112] Then, the gray-level co-occurrence matrix is ​​used to calculate the texture features of the image in each phase. The vegetation index NDVI and texture features of the image in each phase are used as input values, and the trained long short-term memory (LSTM) model is used to predict the vegetation coverage of the image in each phase. By comparing the prediction results of adjacent phase steps, it is determined whether the vegetation coverage of each pixel has changed, and the changed area is extracted as the landslide hazard area.

[0113] Optionally, at least one area with abnormal slope is determined based on the mountain slope information of the power grid area, including: dividing the area where the power grid is located into multiple areas to be determined; obtaining the mountain slope information of the multiple areas to be determined; judging whether the mountain slope information of the multiple areas to be determined is within a preset slope range; and determining the area to be determined whose mountain slope information is within the preset slope range as an area with abnormal slope.

[0114] The area to be determined in the above step may be divided according to the vegetation coverage type on the surface of the area, or may be divided according to the moisture content of the soil layer, or may be divided according to the soil type, but the division method is not limited thereto.

[0115] The preset slope range in the above steps is a preset slope range, which can be preset according to actual application conditions, and no limitation is imposed on the specific value of the preset slope range.

[0116] In an optional embodiment, the vegetation index NDVI is obtained through satellite remote sensing images to determine the vegetation coverage type of the area where the power grid is located, and the area where the power grid is located is divided according to the vegetation coverage type to obtain multiple areas to be determined. The multiple areas to be determined are processed using a digital elevation model, and the mountain slope information of the multiple areas to be determined is determined based on the DEM data output by the digital elevation model. According to whether the mountain slope information of the multiple areas to be determined is within a preset slope range, it is determined whether the area to be determined is an abnormal slope area.

[0117] For example, the preset slope range is 30 to 45 degrees. If the mountain slope information of the area to be determined is 35 degrees, the area to be determined can be determined as an abnormal slope area. It should be noted that the values ​​in the above examples are only examples, and the values ​​involved in actual applications may not be limited thereto.

[0118] Optionally, a landslide hazard area in at least one slope abnormality area is determined based on a mountain stability index of at least one slope abnormality area, including: determining a slope abnormality area whose mountain stability index is within a preset index range as a candidate landslide hazard area; determining a rock edge movement rate of the candidate landslide hazard area based on the bare rock distribution in the candidate landslide hazard area; when the rock edge movement rate of the candidate landslide hazard area is greater than a preset rate, determining the candidate landslide hazard area as a landslide hazard area.

[0119] The candidate landslide hazard areas in the above steps are slope abnormality areas with low mountain stability index, and the landslide hazard areas are selected from the candidate landslide hazard areas.

[0120] The bare rock distribution in the above steps refers to the distribution of bare rocks on the surface in the candidate landslide hazard area.

[0121] The preset index range in the above steps is a pre-set data range, which can be preset according to actual application conditions, and no restriction is imposed on the specific value of the preset index range.

[0122] In an optional embodiment, it is determined whether the mountain stability index of the slope abnormality area is within a preset index range. If it is within the preset index range, the slope abnormality area is determined to be a candidate landslide hazard area.

[0123] Exemplarily, according to the mountain stability index, the mountain is divided into stable, potentially unstable and unstable levels. The levels are divided by the index value. The mountain stability index is greater than 8 for stable, 6-8 for potentially unstable, and less than 6 for unstable. The slope abnormality areas with the mountain stability level of potentially unstable and unstable are taken as candidate landslide hazard areas. That is, the preset index range is less than 8, and the slope abnormality areas with the mountain stability index less than 8 are determined as candidate landslide hazard areas. It should be noted that the numerical values ​​in the above examples are only examples, and the numerical values ​​involved in actual applications may not be limited to this.

[0124] According to the surface information in the candidate landslide hazard area, determine whether there is bare rock distribution in the area. If there is bare rock distribution, obtain the multi-temporal image of the bare rock area to obtain the bare rock distribution of the candidate landslide hazard area. Use the scale-invariant feature transform (SIFT) algorithm to match and analyze the multi-temporal images containing the bare rock distribution, and calculate the rock edge movement rate. If the rock edge displacement rate is greater than the preset rate, the candidate landslide hazard area is locked as a landslide hazard area.

[0125] Exemplarily, then, the surface information is extracted based on the multi-phase satellite image data of the candidate landslide hazard area, including reflectivity data, texture features and edge features of different bands, to determine whether there is bare rock distribution. The extracted reflectivity data, texture features and edge features are used as input values, and a discrimination model is constructed based on the support vector machine (SVM) to automatically identify the bare rock distribution area and determine the bare rock distribution. If there is bare rock distribution, the SI FT algorithm is used to perform image matching analysis based on the multi-phase satellite images of the bare rock area, calculate the distance between the feature points in the images of different phases, match the feature points, and calculate the displacement information of the rock edge according to the position change of the feature points after registration, including its displacement in the horizontal and vertical directions. The displacement data is analyzed to determine the rock edge movement rate. The calculation formula is:

[0126]

[0127] Among them, X is the horizontal displacement of the rock, Y is the vertical displacement of the rock, and T is the time interval.

[0128] The preset rate is 5 cm per day. When the rock edge displacement rate is greater than 5 cm per day, the candidate landslide hazard area is locked as a landslide hazard area and needs to be monitored and warned. It should be noted that the values ​​in the above examples are only examples, and the values ​​involved in actual applications may not be limited to these.

[0129] Optionally, the method further includes: determining a landslide response strategy based on the monitoring results; and performing emergency treatment on power grid equipment in the landslide hazard area according to the landslide response strategy.

[0130] The landslide response strategy in the above steps is a strategy for emergency treatment of power grid equipment when the monitoring results show that there is a risk of landslide in the area where the power grid is located. There is a corresponding relationship between the landslide response strategy and the monitoring results. Different monitoring results correspond to different landslide response strategies.

[0131] In an optional embodiment, areas with high risk of landslide hazards can be determined based on the monitoring results, and landslide response strategies can be adopted to reduce the impact of landslides on power grid equipment.

[0132] The response strategy for landslides with high risk of monitoring results is: check whether there are power facilities in the landslide hazard area. If there are power grid equipment, obtain the number of transmission lines in the area to calculate the power outage area. According to the damaged power outage area, formulate targeted emergency maintenance and backup power supply plans, and carry out preventive response measures in advance to ensure power supply. At the same time, obtain the backup capacity information of other power suppliers around the landslide hazard area with high risk of danger, and determine whether feeder support can be provided through the adjacent power supply network. If it is confirmed that the adjacent power grid can take over part of the load, the automatic transfer program of network failure is pre-set to respond quickly in the event of a power outage.

[0133] If the monitoring result of a landslide hazard area is high risk, emergency treatment shall be carried out on the power grid equipment in the landslide hazard area according to the above-mentioned landslide response strategy. That is, it is necessary to query whether there are power facilities in the area. If there are power grid equipment, assume that there are 3 transmission lines in the area. According to the number of transmission lines, calculate the power outage area. If the average power supply area of ​​each transmission line is 5 square kilometers, the total power outage area is 3*5=15 square kilometers. According to the calculation results of the power outage area, formulate targeted emergency maintenance and backup power supply plans, and carry out preventive response measures in advance to ensure power supply. At the same time, obtain the spare capacity information of other power suppliers around the landslide hazard area with high risk, and determine whether feeder support can be provided through the adjacent power supply network. If the spare capacity of the surrounding power supplier A is 500 megawatts, and the spare capacity of supplier B is 800 megawatts. According to the spare capacity information, determine whether part of the load can be taken over by the adjacent power grid. If the blackout area requires 200 MW of power supply, since the spare capacity of supplier A is 500 MW, which is greater than the demand of 200 MW, the adjacent power grid supplier A can be used to take over part of the load. In view of this situation, the automatic power transfer program for network failure is pre-set to respond quickly when a power outage occurs and transfer part of the load to supplier A of the adjacent power supply network.

[0134] It should be noted that the numerical values ​​in the above examples are only examples, and the numerical values ​​involved in actual applications may not be limited to these.

[0135] A preferred embodiment is described below. Figure 2 is a flow chart of an optional landslide monitoring method according to an embodiment of the present invention, such as Figure 2 As shown:

[0136] Step S202, using GPS technology to obtain mountain structure data of the landslide potential area, establish a three-dimensional digital elevation model, and predict the landslide volume.

[0137] Step S204, using satellite red-hot external images to analyze soil moisture changes in the landslide potential area, monitor moisture anomalies, and calculate the temporal and spatial moisture change rate and the abnormal range area.

[0138] The abnormal range area in the above steps is also the moisture abnormal range mentioned above.

[0139] Step S206, judging the severity of the landslide event according to the predicted landslide volume, the spatiotemporal change rate of moisture and the abnormal range area, and determining whether the landslide hazard area is a high-risk landslide area according to the severity of the landslide event in the landslide hazard area.

[0140] Step S208: taking preventive measures to reduce the impact of the landslide on the power grid equipment.

[0141] Figure 3 is a flow chart of an optional locking landslide hazard area according to an embodiment of the present invention, such as Figure 3 As shown:

[0142] Step S302, extracting the slope and vegetation coverage type of the key focus area, and analyzing the precipitation distribution using satellite cloud images.

[0143] The key focus area in the above steps is also the slope anomaly area mentioned above.

[0144] Step S304, judging the mountain stability level in combination with the slope and the vegetation coverage type, and determining the target area according to the mountain stability level.

[0145] The mountain stability level in the above steps can be determined based on the mountain stability coefficient mentioned above.

[0146] Step S306, determining the surface changes in the target area through satellite images, and identifying the landslide potential area.

[0147] The target area in the above steps is also the candidate landslide hazard area mentioned above.

[0148] Figure 4 is another optional flow chart of locking the landslide hazard area according to an embodiment of the present invention, such as Figure 4 As shown:

[0149] Step S402, acquiring multi-temporal satellite images.

[0150] Step S404: Identify the vegetation coverage change area.

[0151] Step S406: extract the changed area.

[0152] Step S408, determining bare rock distribution.

[0153] Step S410, acquiring multi-temporal images of the bare rock area.

[0154] Step S412: Perform matching analysis using a feature matching algorithm.

[0155] Step S414, calculating the rock edge movement rate.

[0156] Step S416, comparing with a preset first threshold value, and locking the landslide potential area.

[0157] The preset first threshold in the above steps is the preset rate mentioned above.

[0158] Example 2

[0159] According to an embodiment of the present invention, an embodiment of a landslide monitoring device is provided, which can execute the landslide monitoring method provided in the above embodiment 1. The specific implementation method and preferred application scenario are the same as those of the above embodiment 1 and will not be repeated here.

[0160] Figure 5 is a schematic diagram of a landslide monitoring device according to an embodiment of the present invention, such as Figure 5 As shown, the landslide monitoring device includes:

[0161] The first determination module 50 is used to determine the landslide hazard area based on the mountain slope information, vegetation coverage type and precipitation distribution of the area where the power grid is located, wherein the landslide hazard area is an area where the mountain stability in the area where the power grid is located is low and there is a risk of landslide;

[0162] Prediction module 52, used to predict the landslide volume in the landslide potential area and obtain the landslide volume prediction value;

[0163] A second determination module 54 is used to determine the spatiotemporal change rate of moisture and the abnormal range of moisture in the landslide potential area based on the moisture state of the landslide potential area, wherein the moisture state at least includes the moisture content of the soil layer;

[0164] The third determination module 56 is used to determine the monitoring result according to the landslide volume prediction value, the spatiotemporal change rate of moisture content and the moisture abnormality range, wherein the monitoring result is used to characterize the danger level of the landslide potential area.

[0165] Optionally, the prediction module includes: a first acquisition unit, used to obtain mountain structure characteristics of the landslide hazard area, wherein the mountain structure characteristics include at least one of the following: mountain elevation, mountain slope, mountain aspect, vegetation index, precipitation, rock edge movement rate; a first prediction unit, used to input the mountain structure characteristics into a landslide volume prediction model, and use the landslide volume prediction model to predict the landslide volume in the landslide hazard area to obtain a landslide volume prediction value.

[0166] Optionally, the second determination module includes: a first determination unit, used to determine at least one key analysis area in the landslide hazard area, wherein at least one key analysis area is an area with abnormal surface temperature in the landslide hazard area; a second acquisition unit, used to obtain the surface temperature, atmospheric temperature, vegetation index and precipitation of at least one key analysis area at different times; a second prediction unit, used to input the surface temperature, atmospheric temperature, vegetation index and precipitation of at least one key analysis area at different times into a moisture prediction model, and use the moisture prediction model to predict the moisture status of each key analysis area at different times to obtain the moisture status of at least one key analysis area at different times; the second determination unit is used to determine the spatiotemporal moisture change rate and the moisture anomaly range based on the moisture status of at least one key analysis area at different times.

[0167] Optionally, the second determination unit is also used to determine the moisture change rate of at least one key analysis area based on the moisture state of at least one key analysis area at different times; determine the spatiotemporal moisture change rate based on the moisture change rates of multiple key analysis areas; compare the moisture change rate of at least one key analysis area with a preset change rate to determine whether at least one key analysis area is in an abnormal moisture state, wherein the abnormal moisture state is used to characterize that the moisture change rate is greater than the preset change rate; and determine the abnormal moisture range based on the range of the key analysis area in the abnormal moisture state.

[0168] Optionally, the first determination unit is also used to obtain satellite thermal infrared images of the landslide hazard area; process the satellite thermal infrared images to obtain the thermal infrared radiation brightness; use a single scattering inversion algorithm to process the thermal infrared radiation brightness to obtain surface temperature data of the landslide hazard area; use a clustering algorithm to identify abnormal data in the surface temperature data, and determine the area corresponding to the abnormal data as the key analysis area.

[0169] Optionally, the third determination module includes: a third determination unit, used to respectively determine the weights of the landslide volume prediction value, the spatiotemporal change rate of moisture, and the moisture abnormal range; a third prediction unit, used to determine the hazard coefficient of the landslide potential area based on the landslide volume prediction value, the spatiotemporal change rate of moisture, the moisture abnormal range, and the weight of the landslide volume prediction value, the weight of the spatiotemporal change rate of moisture, and the weight corresponding to the moisture abnormal range; a fourth determination unit, used to determine the monitoring results according to the hazard coefficient of the landslide potential area.

[0170] Optionally, the first determination module includes: a fifth determination unit, used to determine at least one slope abnormality area based on the mountain slope information of the area where the power grid is located; a fourth prediction unit, used to input the vegetation coverage type and precipitation distribution of at least one slope abnormality area into a mathematical model, and use the mathematical model to predict the mountain stability index of the at least one slope abnormality area to obtain the mountain stability index of at least one slope abnormality area; a sixth determination unit, used to determine the landslide hazard area in at least one slope abnormality area based on the mountain stability index of at least one slope abnormality area.

[0171] Optionally, the fifth determination unit is also used to divide the area where the power grid is located into multiple areas to be determined; obtain mountain slope information of the multiple areas to be determined; determine whether the mountain slope information of the multiple areas to be determined is within a preset slope range; and determine the areas to be determined whose mountain slope information is within the preset slope range as areas with abnormal slope.

[0172] Optionally, the sixth determination unit is also used to determine that the slope abnormality area whose mountain stability index is within a preset index range is a candidate landslide hazard area; determine the rock edge movement rate of the candidate landslide hazard area according to the bare rock distribution in the candidate landslide hazard area; when the rock edge movement rate of the candidate landslide hazard area is greater than the preset rate, determine the candidate landslide hazard area as a landslide hazard area.

[0173] Optionally, the third determination module is further used to determine a landslide response strategy based on the monitoring results; and perform emergency treatment on power grid equipment in the landslide hazard area according to the landslide response strategy.

[0174] Example 3

[0175] According to an embodiment of the present invention, there is also provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the landslide monitoring method in Embodiment 1 is executed when the program is running.

[0176] Example 4

[0177] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program runs, the device where the computer-readable storage medium is located is controlled to execute the landslide monitoring method in each embodiment of the present invention.

[0178] Example 5

[0179] The embodiments of the present application further provide a computer program product, including a computer program, which, when executed by a processor, implements the landslide monitoring method in each embodiment of the present invention.

[0180] Example 6

[0181] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the landslide monitoring method in each embodiment of the present invention is implemented.

[0182] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0183] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0184] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0185] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0186] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0187] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0188] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for monitoring landslide, characterized in that: include: Based on the mountain slope information, vegetation coverage type and precipitation distribution in the area where the power grid is located, determine the landslide hazard area, wherein the landslide hazard area is an area in the area where the power grid is located where the mountain stability is low and there is a risk of landslide; Predicting the landslide volume in the landslide hazard area to obtain a landslide volume prediction value; Determine the spatiotemporal change rate of moisture and the abnormal range of moisture in the landslide hazard area based on the moisture state of the landslide hazard area, wherein the moisture state at least includes the moisture content of the soil layer; A monitoring result is determined according to the predicted landslide volume, the spatiotemporal change rate of moisture, and the abnormal moisture range, wherein the monitoring result is used to characterize the danger level of the landslide potential area.

2. The landslide monitoring method according to claim 1, characterized in that: Predicting the landslide volume in the landslide hazard area to obtain a landslide volume prediction value includes: Acquire the mountain structure characteristics of the landslide hazard area, wherein the mountain structure characteristics include at least one of the following: mountain elevation, mountain slope, mountain aspect, vegetation index, precipitation, rock edge movement rate; The mountain structure characteristics are input into a landslide volume prediction model, and the landslide volume prediction model is used to predict the landslide volume of the landslide potential area to obtain a landslide volume prediction value.

3. The landslide monitoring method according to claim 1, characterized in that: Based on the moisture state of the landslide hazard area, determining the spatiotemporal change rate of moisture and the abnormal range of moisture in the landslide hazard area includes: Determine at least one key analysis area in the landslide hazard area, wherein the at least one key analysis area is an area in the landslide hazard area where the surface temperature is abnormal; Obtaining the surface temperature, atmospheric temperature, vegetation index and precipitation of the at least one key analysis area at different times; Inputting the surface temperature, atmospheric temperature, vegetation index and precipitation of the at least one key analysis area at different times into a moisture prediction model, and using the moisture prediction model to predict the moisture state of the at least one key analysis area at different times, to obtain the moisture state of the at least one key analysis area at different times; Based on the moisture status of the at least one key analysis area at different times, the spatiotemporal moisture change rate and the moisture anomaly range are determined.

4. The landslide monitoring method according to claim 3, characterized in that: Determining the spatiotemporal change rate of moisture and the abnormal range of moisture based on the moisture state of the at least one key analysis area at different times includes: Determining a moisture change rate of the at least one key analysis area based on the moisture state of the at least one key analysis area at different times; Determining the spatiotemporal change rate of moisture based on the moisture change rate of the at least one key analysis area; Comparing the moisture change rate of the at least one key analysis area with a preset change rate, determining whether the at least one key analysis area is in an abnormal moisture state, wherein the abnormal moisture state is used to indicate that the moisture change rate is greater than the preset change rate; The moisture abnormality range is determined according to the range of the key analysis area in the moisture abnormality state.

5. The landslide monitoring method according to claim 3, characterized in that: Determining at least one key analysis area in the landslide hazard area includes: Acquire satellite thermal infrared images of the landslide potential area; Processing the satellite thermal infrared image to obtain thermal infrared radiation brightness; Using a single scattering inversion algorithm to process the thermal infrared radiation brightness, obtaining surface temperature data of the landslide hazard area; A clustering algorithm is used to identify abnormal data in the surface temperature data, and an area corresponding to the abnormal data is determined as the key analysis area.

6. The method for monitoring landslide according to claim 1, characterized in that: The monitoring result is determined according to the predicted landslide volume, the spatiotemporal change rate of moisture and the abnormal moisture range, including: respectively determining the weights of the landslide volume prediction value, the spatiotemporal change rate of moisture, and the moisture anomaly range; Determine the risk factor of the landslide potential area based on the predicted landslide volume, the spatiotemporal change rate of moisture, the abnormal moisture range, and the weight of the predicted landslide volume, the weight of the spatiotemporal change rate of moisture, and the weight corresponding to the abnormal moisture range; The monitoring result is determined according to the risk factor of the landslide potential risk area.

7. The method for monitoring landslide according to claim 1, characterized in that: Determine the landslide risk area based on the mountain slope information, vegetation coverage type and precipitation distribution in the area where the power grid is located, including: Determine at least one area with abnormal slope based on the mountain slope information of the area where the power grid is located; Inputting the vegetation coverage type and precipitation distribution of the at least one slope abnormality area into a mathematical model, and using the mathematical model to predict the mountain stability index of the at least one slope abnormality area to obtain the mountain stability index of the at least one slope abnormality area; The landslide hazard area in the at least one slope abnormality area is determined according to the mountain stability index of the at least one slope abnormality area.

8. The method for monitoring landslide according to claim 7, characterized in that: Determining at least one area with abnormal slope based on the mountain slope information of the area where the power grid is located includes: Dividing the area where the power grid is located into a plurality of areas to be determined; Obtaining mountain slope information of the plurality of areas to be determined; Determining whether the mountain slope information of the plurality of areas to be determined is within a preset slope range; The area to be determined in which the mountain slope information is within the preset slope range is determined as the slope abnormality area.

9. The method for monitoring landslide according to claim 7, characterized in that: Determining the landslide hazard area in the at least one slope abnormality area according to the mountain stability index of the at least one slope abnormality area comprises: Determine the slope abnormality area whose mountain stability index is within the preset index range as a candidate landslide hazard area; Determining the rock edge movement rate of the candidate landslide hazard area according to the bare rock distribution of the candidate landslide hazard area; When the rock edge movement rate of the candidate landslide hazard area is greater than a preset rate, the candidate landslide hazard area is determined to be the landslide hazard area.

10. The method for monitoring landslide according to any one of claims 1 to 9, characterized in that: The method further comprises: determining a landslide response strategy based on the monitoring results; According to the landslide response strategy, emergency treatment is carried out on the power grid equipment in the landslide potential area.

Images