Snow layer stability monitoring method and system

Abstract

The invention provides a snow layer stability monitoring method and system. The method comprises the following steps: acquiring monitoring data sent by each multi-dimensional sensor in a multi-dimensional sensor array; obtaining snow layer state data according to the monitoring data; and determining a disaster risk according to the snow layer state data. According to the invention, the multi-dimensional sensor array comprising a plurality of multi-dimensional sensors is arranged, so that high-precision monitoring of the snow layer state can be realized, the snow layer state is determined based on the obtained snow layer state data, the disaster risk is judged, and an all-weather and gridding precise prevention and control solution is provided for an avalanche high-risk area.

Description

Technical Field

[0001] The present invention relates to the field of meteorological monitoring, and particularly to a method and system for monitoring the stability of a snow layer. Background Art

[0002] Currently, the prevention and control of avalanche disasters mainly rely on traditional geological surveys and manual inspections, combined with satellite remote sensing for large-scale monitoring. However, limited by factors such as cloud cover and poor cold resistance of equipment, these methods have significant deficiencies in data accuracy and timeliness, and it is difficult to meet the needs of refined prevention and control in high-risk sections. Especially in the high-altitude and cold environment, existing monitoring equipment often has difficulty in operating stably for a long time, resulting in discontinuous and inaccurate data, thus affecting the timeliness and reliability of avalanche warnings. Summary of the Invention

[0003] The main objective of the present invention is to propose a method and system for monitoring the stability of a snow layer, aiming to solve the problem of poor detection reliability of avalanches in the prior art.

[0004] To achieve the above objective, the present invention provides a method for monitoring the stability of a snow layer, and the method includes the steps of: Obtaining monitoring data sent by each multi-dimensional sensor in the multi-dimensional sensor array; Obtaining snow layer state data based on each of the monitoring data; Determining the disaster risk based on the snow layer state data.

[0005] Optionally, the obtaining snow layer state data based on each of the monitoring data includes: Performing time alignment on each of the monitoring data to obtain time monitoring data; Mapping each of the monitoring data into a preset data space to obtain space monitoring data; Determining the snow layer state data based on the time monitoring data and the space monitoring data.

[0006] Optionally, the snow layer state data includes a risk probability, and the determining the snow layer state data based on the time monitoring data and the space monitoring data includes: Obtaining a hybrid model, where the hybrid model includes a convolutional neural network layer, a long short-term memory network layer, and a fully connected layer; Inputting the space monitoring data into the convolutional neural network layer to obtain space features; Inputting the time monitoring data into the long short-term memory network layer to obtain time features; Concatenating the space features and the time features to obtain fusion features; Inputting the fusion features into the fully connected layer to obtain the risk probability.

[0007] Optionally, determining the disaster risk based on the snow layer state data includes: Determining a comprehensive risk index corresponding to the snow layer state data; Obtaining a risk division threshold, and determining the disaster risk corresponding to the comprehensive risk index according to the risk division threshold.

[0008] Optionally, the snow layer state data includes a risk probability and environmental parameters; determining the comprehensive risk index corresponding to the snow layer state data includes: Obtaining weights corresponding to the risk probability and the environmental parameters; Performing weighted calculation on the risk probability and the environmental parameters based on the weights to obtain the comprehensive risk index.

[0009] Optionally, obtaining the monitoring data sent by each multi-dimensional sensor in the multi-dimensional sensor array includes: Obtaining real-time disaster risk; Determining a target acquisition frequency corresponding to the real-time disaster risk, where the target acquisition frequency is positively correlated with the real-time disaster risk; Obtaining the monitoring data sent by each multi-dimensional sensor in the multi-dimensional sensor array at the target acquisition frequency.

[0010] Optionally, after determining the disaster risk based on the snow layer state data, it includes: Obtaining a terrain model corresponding to the multi-dimensional sensor array; Mapping the snow layer state data and the disaster risk into the terrain model for display.

[0011] Optionally, after determining the disaster risk based on the snow layer state data, it includes: Judging whether the disaster risk reaches a preset risk threshold; If the disaster risk reaches the preset risk threshold, obtaining historical snow layer state data; Predicting the avalanche prediction time according to the historical snow layer state data; Performing a warning operation based on the avalanche prediction time.

[0012] To achieve the above object, the present invention further provides a snow layer stability monitoring system, and the snow layer stability monitoring system includes: The snow layer stability monitoring system includes a multi-dimensional sensor array and a processing module; the multi-dimensional sensor array includes a plurality of multi-dimensional sensors, and each multi-dimensional sensor is communicatively connected to the processing module; wherein: The multi-dimensional sensor is used for monitoring snow layer parameters at the location where it is located to obtain monitoring data, and sending the monitoring data to the processing module; The processing module is configured to receive the monitoring data sent by each of the multi-dimensional sensors, obtain snow layer state data based on each of the monitoring data, and determine a disaster risk according to the snow layer state data.

[0013] Optionally, the multi-dimensional sensor includes a longitudinal anchor rod, and a plurality of temperature sensors are arranged on the longitudinal anchor rod, and the temperature sensors are arranged at a preset interval.

[0014] To achieve the above object, the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the steps of the snow layer stability monitoring method as described above are implemented.

[0015] To achieve the above object, the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the snow layer stability monitoring method as described above are implemented.

[0016] A snow layer stability monitoring method and system proposed by the present invention obtain monitoring data sent by each multi-dimensional sensor in a multi-dimensional sensor array; obtain snow layer state data based on each of the monitoring data; determine a disaster risk according to the snow layer state data. By setting up a multi-dimensional sensor array including a plurality of multi-dimensional sensors, high-precision monitoring of the snow layer state can be achieved, and then the snow layer state can be determined based on the obtained snow layer state data to judge the disaster risk, providing an all-weather and grid-based precise prevention and control solution for high-risk avalanche areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present invention and used together with the specification to explain the principles of the present invention.

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a schematic flowchart of the first embodiment of the snow layer stability monitoring method of the present invention; Figure 2 It is a three-dimensional view in the snow layer stability monitoring method of the present invention; Figure 3 It is an overall flowchart of the snow layer stability monitoring method of the present invention; Figure 4 It is a schematic diagram of the module structure of the electronic device of the present invention. Specific embodiments

[0020] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0021] The present invention provides a snow layer stability monitoring method, which is applied to a snow layer stability monitoring system. Refer to Figure 1 , Figure 1 It is a schematic flowchart of the first embodiment of the snow layer stability monitoring method of the present invention. The method includes the steps: Step S10, obtaining the monitoring data sent by each multi-dimensional sensor in the multi-dimensional sensor array; For the convenience of description, the snow layer stability monitoring system will be described first. The snow layer stability monitoring system includes: The snow layer stability monitoring system includes a multi-dimensional sensor array and a processing module; the multi-dimensional sensor array includes a plurality of multi-dimensional sensors, and each multi-dimensional sensor is communicatively connected to the processing module; wherein: The multi-dimensional sensor is used to monitor the snow layer parameters at its location to obtain monitoring data, and send the monitoring data to the processing module; The processing module is used to receive the monitoring data sent by each multi-dimensional sensor, obtain snow layer state data according to each monitoring data, and determine the disaster risk according to the snow layer state data.

[0022] The multi-dimensional sensor array is an array composed of a plurality of multi-dimensional sensors; the specific multi-dimensional sensors can be set according to actual needs, such as setting the horizontal interval and the vertical interval. The multi-dimensional sensors in the horizontal direction are arranged at the horizontal interval, and the multi-dimensional sensors in the vertical direction are arranged at the vertical interval.

[0023] Each multi-dimensional sensor monitors the snow layer state at its own location to obtain monitoring data; the snow layer state data can be obtained through the monitoring data obtained by each multi-dimensional sensor. The snow layer state data can reflect the snow layer state in the area where the multi-dimensional sensor array is located. Based on the snow layer state data, the disaster risk can be analyzed and determined; the disaster risk indicates the risk probability of an avalanche disaster.

[0024] The multi-dimensional sensor can monitor different types of parameters, which can be specifically set according to actual needs. For example, the multi-dimensional sensor includes a longitudinal anchor rod, and a plurality of temperature sensors are arranged on the longitudinal anchor rod, and the temperature sensors are arranged at a preset interval.

[0025] The multi-dimensional sensor is inserted into the snow layer through the longitudinal anchor rod; and a plurality of temperature sensors are arranged at a preset interval in the longitudinal direction on the longitudinal anchor rod, so that the temperature at different depths of the snow layer can be monitored.

[0026] In addition to the temperature sensors, other types of sensors can also be set to monitor other types of parameters, such as pressure sensors, snow depth sensors, piezoelectric sensors, weather stations, etc.; the pressure sensors can monitor the snow layer pressure, the snow depth sensors can monitor the snow layer depth, the weather stations can monitor meteorological parameters such as wind speed and precipitation, and the piezoelectric sensors can monitor the micro-deformation of the snow layer. It should be noted that the above sensor settings are only for illustrative purposes, and in actual applications, corresponding types of sensors can also be set according to the parameters to be monitored.

[0027] Step S20, obtaining snow layer state data according to each of the monitoring data; After determining the monitoring data, the real-time state of the snow layer is determined according to the monitoring data to obtain the snow layer state data; the snow layer state data can reflect the state of the snow layer in the area where the multi-dimensional sensor array is located.

[0028] The snow layer state data may include data indicating different snow layer states. For example, the data in the snow layer state data can indicate environmental parameters, risk probability, regional location information, the state of the snow layer itself, etc.

[0029] Step S30, determining the disaster risk according to the snow layer state data.

[0030] After determining the snow layer state data, the disaster risk is comprehensively determined through the snow layer state data, so as to judge the probability of an avalanche occurring in the current snow layer state.

[0031] In this embodiment, by setting a multi-dimensional sensor array including a plurality of multi-dimensional sensors, high-precision monitoring of the snow layer state can be realized, and then the snow layer state is determined based on the obtained snow layer state data to judge the disaster risk, providing an all-weather and grid-based precise prevention and control solution for high-risk avalanche areas.

[0032] Further, in the second embodiment of the snow layer stability monitoring method of the present invention proposed based on the first embodiment of the present invention, the step S20 includes the steps: Step S21, performing time alignment on each of the monitoring data to obtain time monitoring data; Step S22: Map each piece of monitoring data into a preset data space to obtain spatial monitoring data; Step S23: Determine the snow layer state data according to the time monitoring data and the spatial monitoring data.

[0033] The traditional monitoring method is single-point monitoring, that is, at a single location, a sensor is set to monitor specific parameters; while the monitoring data in this embodiment comes from a variety of sensors in a multi-dimensional sensor array; different sensors have different data collection times, locations, and collection frequencies; therefore, the spatio-temporal benchmarks of different types of data in the monitoring data are not unified. Therefore, it is difficult to capture the dynamic correlation of the snow layer state; while in this embodiment, the spatio-temporal alignment of the monitoring data solves the problem of spatial fragmentation of the monitoring data; the time-aligned data is unified in time and space. Therefore, it can reflect the distribution of the snow layer state in time and space, providing a data set with consistent spatio-temporal benchmarks for the assessment of disaster risks.

[0034] Specifically, in this embodiment, the monitoring data is time-aligned and space-aligned respectively.

[0035] Time alignment is used to unify each piece of data in the monitoring data in terms of time. In this embodiment, the heterogeneous data from different sensors in the monitoring data is specifically aligned by means of time linear interpolation; specifically:

[0036] Among them, x(t target ) is the target time interpolation; t target is the target time; (t1, x1), (t2, x2) are different known data; (t1, x1) is the x1 data collected at time t1, and (t2, x2) is the x2 data collected at time t2; it can be understood that (t1, x1), (t2, x2) are the same type of data detected by the same sensor, the difference lies in the different collection times, and the resulting target time difference also reflects this type of data.

[0037] For each type of data collected by each sensor, the data corresponding to the target time is generated by means of time linear interpolation, so that at each target time, each type of data collected by each sensor can be obtained, thus realizing the time alignment of various types of data; for example, the snow layer temperature at the deepest position on the first sensor is collected at the first moment and the second moment, while the wind speed on the second sensor is collected at the first moment, the third moment, and the second moment, where the third moment is between the first moment and the second moment. At this time, the target time difference corresponding to the third moment is obtained by time linear interpolation of the snow layer temperature at the deepest position collected by the first sensor based on the first moment and the second moment, so that the first sensor has corresponding collected data for the snow layer temperature at the deepest position at the first moment, the third moment, and the second moment, realizing time alignment with the wind speed data on the second sensor.

[0038] The time-monitoring data can be obtained by aggregating the data after time alignment; the rapid changes of various parameters can be tracked through the time-monitoring data.

[0039] Spatial alignment is used to unify the data in the monitoring data in space. In this embodiment, the heterogeneous data from different positions and different sensors in the monitoring data is aligned specifically by means of spatial interpolation; specifically:

[0040]

[0041] Among them, Z(s0) is the target position interpolation; Z(s i ) is the known parameter corresponding to the i-th point; d i is the distance between the position of the i-th known sensor and the target position; d j is the distance between the position of the j-th known sensor and the target position; λ i is the weight of the i-th point.

[0042] Spatial interpolation calculates the target position interpolation of the new position through the data of the known points, thus realizing the spatial alignment of different data; the goal of spatial alignment is to map the sensor data at different spatial positions to a unified three-dimensional grid or target point to form a spatially continuous data field; thus, the continuous change of the data in space can be reflected.

[0043] After the monitoring data is collected, in order to improve the data quality, noise reduction and temperature drift compensation can be performed on the monitoring data; specifically:

[0044]

[0045] Among them, x[n] is the sampling value of the original signal collected by the sensor at the nth discrete time point; x smooth [n] is the smoothed signal after the original signal x[n] passes through a moving average filter. After smoothing, x smooth [n] can more clearly reflect the continuous vibration energy of the snow layer fracture event; M is the window size; S comp is the compensated signal value; S raw is the original signal value; k is the temperature drift coefficient; T ref is the reference temperature.

[0046] The noise reduction process removes high-frequency noise through moving average filtering; the temperature drift compensation corrects the drift of the temperature sensor under extremely cold conditions of -25°C to ensure the measurement accuracy.

[0047] The spatial monitoring data can be obtained by aggregating the spatially aligned data.

[0048] Furthermore, the snow layer state data includes a risk probability, and the step S23 includes the steps of: Step S231, obtaining a hybrid model, where the hybrid model includes a convolutional neural network layer, a long short-term memory network layer, and a fully connected layer; Step S232, inputting the spatial monitoring data into the convolutional neural network layer to obtain spatial features; Step S233, inputting the time monitoring data into the long short-term memory network layer to obtain time features; Step S234, splicing the spatial features and the time features to obtain fused features; Step S235, inputting the fused features into the fully connected layer to obtain the risk probability.

[0049] The time monitoring data reflects the continuous changes of different types of data over time; the spatial monitoring data reflects the continuous changes of different types of data in space; different types of models have different advantages for different types of monitoring data. Therefore, in this embodiment, a hybrid model integrated with different types of models is used to determine the risk probability based on the time monitoring data and the spatial monitoring data.

[0050] Specifically, the hybrid model includes CNN (Convolutional Neural Networks), LSTM (Long Short-Term Memory network layer), and a fully connected layer.

[0051] The convolutional neural network layer is used to extract the spatial distribution laws of the temperature field and the pressure field. Therefore, the spatial monitoring data is input into the convolutional neural network layer for feature extraction to obtain spatial features. Specifically:

[0052] Among them, \(W\) is the convolutional kernel, \(b\) is the bias, \(\sigma\) is the activation function, and \(*\) represents the convolution operation; after convolution through the convolutional neural network layer, the spatial feature Feature is output spatial 。

[0053] The long short-term memory network layer is used to model the temporal correlation between the vibration signal energy and the meteorological parameters. Therefore, the time monitoring data is input into the long short-term memory network layer for feature extraction to obtain the time feature Feature temporal 。

[0054] By using the convolutional neural network layer and the long short-term memory network layer to respectively extract features from the spatial monitoring data and the time monitoring data, it is possible to learn the complex non-linear patterns of avalanche precursors from historical data; this fusion mechanism enables the warning model to not only reflect the physical mechanism but also adapt to the dynamic changes of the environment, reducing the false alarm rate.

[0055] After obtaining the spatial feature and the time feature, the time feature and the time feature are concatenated to obtain the fusion feature:

[0056] Among them, Feature fused is the fusion feature.

[0057] The fusion feature is input into the fully connected layer to output the risk probability through the fully connected layer:

[0058] Among them, \(P\) avalanche is the risk probability; \(\sigma\) is the Sigmoid activation function, and the output range is \([0, 1]\); \(b\) is a constant.

[0059] The risk probability is the probability output by the hybrid model to indicate the occurrence of an avalanche.

[0060] It can be understood that the training and the specific structure of the hybrid model can be set based on actual needs.

[0061] Furthermore, in the third embodiment of the snow layer stability monitoring method of the present invention proposed based on the first embodiment of the present invention, the step S30 includes the steps: Step S31, determining the comprehensive risk index corresponding to the snow layer state data; Step S32: Obtain the risk division threshold, and determine the disaster risk corresponding to the comprehensive risk index according to the risk division threshold.

[0062] The comprehensive risk index R is used to indicate the degree of disaster risk existing in the snow layer state.

[0063] The snow layer state data indicates various data reflecting the snow layer state. Therefore, the snow layer state can be reflected through the snow layer state data, and then the comprehensive risk index can be determined.

[0064] The risk division threshold is the threshold for dividing the disaster risk level. It can be understood that in different application environments, the situation of disaster risk corresponding to the snow layer state is different. Therefore, in this embodiment, the risk division threshold is set to specifically determine the relative relationship between the comprehensive risk index and the disaster risk in a specific environment, so as to determine the disaster risk corresponding to the comprehensive risk index.

[0065] The risk division threshold can be set based on the actual environment. For example, a physical model is established based on historical data. The physical model is based on existing physical laws, meteorological conditions (such as temperature, wind speed, snowfall), and terrain and other factors. Then, by combining historical data and avalanche records, the critical values between different disaster risks are obtained, and the critical values are used as the risk division threshold. Specifically, for example, analyze the value of the comprehensive risk index R corresponding to the occurrence of past disasters in the current environment, such as the current location and current weather conditions; obtain the maximum comprehensive risk index R1 under historical non-disaster conditions, and the comprehensive risk index R2 corresponding to medium and small-scale avalanche events; take R1×95% as the first risk division threshold T1, and take R2×75% as the second risk division threshold T2, where 95% and 75% can be set based on actual needs; the risk division threshold can be updated based on the actually accumulated historical data. For example, at the beginning and end of the snow season, the threshold needs to be dynamically adjusted according to the different snow layer characteristics.

[0066] At this time, T1 and T2 form three intervals, respectively corresponding to three levels of disaster risk, specifically as follows:

[0067] By comparing the comprehensive risk index R with the risk division threshold, the level corresponding to the current disaster risk can be determined.

[0068] It can be understood that the setting of the above risk division threshold is only for illustration, and the number and determination method of the specific risk division threshold can be set based on actual needs.

[0069] Furthermore, the snow layer state data includes risk probability and environmental parameters; the step S31 includes the steps of: Step S311: Obtain the weights corresponding to the risk probability and the environmental parameters; Step S312: Based on the weights, perform weighted calculation on the risk probability and the environmental parameters to obtain the comprehensive risk index.

[0070] The comprehensive risk index is obtained by integrating different types of parameters to comprehensively reflect the snow layer state.

[0071] The environmental parameters are detected by corresponding sensors, and the data types included in the specific environmental parameters can be set based on actual needs. The environmental parameters in this embodiment include the snow layer stability factor, temperature gradient, snowfall, wind speed, and slope; different environmental parameters are set corresponding weights based on their impacts on snow layer stability, and then the comprehensive risk index is calculated based on the corresponding weights:

[0072] Among them, S f is the snow layer stability factor; ∇T is the temperature gradient; Sd is the snowfall; Sw is the wind speed; θ is the slope; w1~w6 are the weights of the corresponding parameters.

[0073] The wind speed and snowfall can be detected by corresponding sensors.

[0074] The snow layer stability factor is used to reflect the snow layer stability. Whether the snow layer is stable depends on the comparison between the shear strength τ and shear stress σ of the snow cover s ; the shear strength of the snow can be expressed by the Mohr-Coulomb criterion:

[0075]

[0076] Among them, c is the cohesion, which depends on the type and temperature of the snow; ϕ is the internal friction angle, which depends on the particle characteristics of the snow; σ n is the normal stress, usually generated by the self-weight of the snow layer:

[0077] Among them, ρ is the snow density; ℎ is the snow layer thickness; 𝜃 is the slope, and the slope of the location can be measured and stored when setting up the multi-dimensional sensor array in the early stage, and the corresponding stored slope can be obtained when the slope needs to be acquired.

[0078] P(z) is the snow layer pressure distribution, specifically:

[0079]

[0080] Among them, w is the snow moisture content, detected by the corresponding sensor; z is the snow depth, detected by the corresponding sensor; P0 is the surface pressure of the snow layer, i.e., the atmospheric pressure; g is the acceleration due to gravity; S is the cross-sectional area of the snow layer, which can be equivalently taken as S = 0.01m 2 ; hs is the snow layer thickness; ρ Water is the density of water.

[0081]

[0082] The shear stress is caused by the gravitational component of the snow layer on the slope. When σ s > τ, the snow layer may slip and trigger an avalanche. The instability of the snow layer can be indicated by the critical slope, such as:

[0083] Among them, θ c is the critical slope. If the actual slope θ > θ c , the risk of snow layer instability increases.

[0084] The snow layer stability factors are:

[0085] The temperature gradient is used to indicate the temperature distribution in the snow layer. The temperature gradient includes the longitudinal gradient and the transverse gradient, which are:

[0086]

[0087] Among them, ∇T<N vertical is the longitudinal gradient; ∇T horizontal is the transverse gradient; ΔT vertical is the temperature difference between different snow layer depths in the longitudinal direction of the multi-dimensional sensor array; ΔT horizontal is the temperature difference between different snow layer depths in the transverse direction of the multi-dimensional sensor array; Δz is the setting distance of the multi-dimensional sensors in the longitudinal direction of the multi-dimensional sensor array; Δx is the setting distance of the multi-dimensional sensors in the transverse direction of the multi-dimensional sensor array.

[0088] The temperature difference is obtained from the temperature data between the longitudinal or transverse directions; for example, several m multi-dimensional sensors are arranged in a rectangular array on the high-risk avalanche slope, and snow temperature sensors are set on the multi-dimensional sensors, and the node spacing is set according to the slope characteristics. The UTM projection coordinate system is used to establish a spatial reference, and the geographical coordinates of the (i, j)th sensor are (x i，j , y i，j ), and the slope temperature field distribution T(x, y) is generated by spatial interpolation, and the temperature difference in the transverse direction is obtained through T(x, y); among them:

[0089]

[0090]

[0091] Among them, Δx and Δy are the setting intervals of the snow temperature sensor in the horizontal and vertical directions; λ k is the weight coefficient, and the sum of all weight coefficients is 1.

[0092] For the vertical direction, multiple platinum resistance temperature sensors are arranged at different depths on the vertical anchor rod of the multi-dimensional sensor. For example, a platinum resistance temperature sensor is arranged every 10 cm; the following can be obtained:

[0093] Among them, T h is the snow layer temperature at depth h.

[0094] The temperature gradient will affect the metamorphism process of snow and is a key factor for the stability of the snow layer. When ∇T > 10 °C / m, a fragile layer is likely to form in the snow layer, resulting in a decrease in the stability of the snow layer.

[0095] Furthermore, in the fourth embodiment of the snow layer stability monitoring method of the present invention proposed based on the first embodiment of the present invention, the step S10 includes the steps of: Step S11, obtaining the real-time disaster risk; Step S12, determining the target acquisition frequency corresponding to the real-time disaster risk, where the target acquisition frequency is positively correlated with the real-time disaster risk; Step S13, acquiring the monitoring data sent by each multi-dimensional sensor in the multi-dimensional sensor array at the target acquisition frequency.

[0096] The real-time disaster risk is the real-time determined disaster risk level; it can be understood that when the level of the real-time disaster risk is lower, it indicates that the snow layer state is more stable. At this time, the acquisition frequency of the monitoring data can be reduced, so as to reduce power consumption and keep the system running at low power to extend the battery life; while the higher the level of the real-time disaster risk, the more unstable the snow layer state is. Therefore, it is necessary to collect the monitoring data at a higher frequency to obtain the snow layer state faster and pay attention to the changes in the snow layer state in order to perform emergency operations.

[0097] The corresponding relationship between specific real-time disaster risks and the target acquisition frequency and emergency operations can be set based on actual needs. For example, when the level of real-time disaster risk is "low risk", the system samples data at a set first frequency to maintain low-power operation, continuously monitors and records; when the level of real-time disaster risk is "medium risk", data is sampled at a second frequency, which is greater than the first frequency, and the emergency department is notified to prepare emergency supplies; when the level of real-time disaster risk is "high risk", data is sampled at a third frequency, which is greater than the second frequency, and a comprehensive emergency plan is activated to evacuate people and close roads.

[0098] Specific emergency operations can be carried out by the monitoring center. For example, the snow layer stability detection system transmits the evaluation results and early warning information of real-time disaster risks to the monitoring center and relevant personnel in real time, and is linked with the emergency system to ensure that the early warning lead time is greater than 2 hours to meet the requirements of rapid response; the early warning information includes risk level, occurrence probability, expected events, etc.; specifically, it can be sent through a low-power wide-area network LoRa or satellite communication.

[0099] Further, in the fifth embodiment of the snow layer stability monitoring method of the present invention proposed based on the first embodiment of the present invention, after the step S30, the following steps are included: Step S40, obtaining the terrain model corresponding to the multi-dimensional sensor array; Step S50, mapping the snow layer state data and the disaster risk into the terrain model for display.

[0100] The terrain model is a model of the terrain where the multi-dimensional sensor array is set; the specific terrain model can be rendered based on the DEM (Digital Elevation Model) elevation data monitored at the location.

[0101] In this embodiment, the snow layer state data and the disaster risk are mapped into the terrain model to obtain a three-dimensional view, enabling three-dimensional visualization of the snow layer state, intuitively displaying the snow layer state and risk distribution, and facilitating the monitoring personnel to quickly identify high-risk areas; specifically:

[0102] Among them, D(x, y, z) is the three-dimensional tensor corresponding to the position of (x, y, z) coordinates. Obtaining the three-dimensional tensor through data of different types at the same position enables the display of the snow layer situation at a specific position.

[0103] The position corresponding to the disaster risk level in the terrain model can be marked, see Figure 2, if the disaster risk level is represented by a color gradient, red indicates high risk, yellow indicates medium risk, and green indicates low risk; the color marking can help observers intuitively understand the snow layer state and quickly locate high-risk areas. If a certain area shows a high temperature gradient and high vibration energy, combined with the image marked in red, it indicates that the avalanche risk in this area is extremely high, and key attention must be paid and preventive measures should be taken in advance.

[0104] Furthermore, in the sixth embodiment of the snow layer stability monitoring method of the present invention proposed based on the first embodiment of the present invention, after the step S30, the following steps are included: Step S60, determining whether the disaster risk reaches a preset risk threshold; Step S70, if the disaster risk reaches the preset risk threshold, obtaining historical snow layer state data; Step S80, predicting the avalanche prediction time according to the historical snow layer state data; Step S90, performing a warning operation based on the avalanche prediction time.

[0105] When the disaster risk reaches a certain level, it indicates that an avalanche may occur. Therefore, in order to be able to give an early warning of the avalanche, in this embodiment, when there is an avalanche risk, the avalanche time is predicted to obtain the avalanche prediction time, so that an early warning can be given based on the avalanche prediction time.

[0106] The preset risk threshold is used to indicate the threshold at which an avalanche may occur. Specifically, the preset risk threshold can be set based on the actual application scenario. For example, the preset risk threshold is set to medium risk. When the level of the disaster risk reaches medium risk, it is considered that there is an avalanche risk, and at this time, the historical snow layer state data is obtained.

[0107] The historical snow layer state data is the snow layer state data obtained by historical monitoring; the historical snow layer state data can reflect the changes in the snow layer state. Therefore, through the historical snow layer state data, the subsequent changes in the snow layer state can be predicted, so as to determine the avalanche prediction time t pred ; specifically, in this embodiment, the LSTM model is used to predict the avalanche prediction time:

[0108] Among them, X temporal is the historical snow layer state data; there is:

[0109] Among them, t N indicates the snow layer state data obtained by the Nth acquisition; the number of snow layer state data included in the historical snow layer state data can be set based on actual needs; T surface is the snow surface temperature, E totalis the vibration capability signal;

[0110] Among them, E i is the energy E of the i-th sensor. The piezoelectric sensor captures the vibration signal generated when the snow layer breaks and undergoes micro-deformation. In order to quantify the intensity of the vibration, the energy of the signal can be calculated. When a high energy value is detected, the surface may have broken snow. Further analysis of the characteristics of the snow layer fracture vibration signal is required. The Fourier transform can be used to convert the time domain signal into the frequency domain signal:

[0111] Among them, V 2 (t) is the square value of the vibration signal voltage output by the piezoelectric sensor at time t; T is the duration of the vibration signal;

[0112] x(t) is the time-domain vibration signal, and X(f) is the frequency-domain signal, where f is the frequency. Spectral analysis can identify specific frequency components of snow layer fractures, such as high-frequency vibrations corresponding to rapid fractures and low-frequency vibrations corresponding to slow creep.

[0113] w i is the corresponding weight;

[0114]

[0115]

[0116] Among them, w distance，i is the distance weight; d i is the distance from the i-th sensor to the target area, p is the attenuation coefficient (usually p=2); w quality，i is the quality weight, Q i is the sensor quality index, which is determined by the signal-to-noise ratio; α and β are adjustment coefficients, reflecting the priority between distance and quality. α can be 0.7 and β can be 0.3.

[0117]

[0118] Continuously monitor the energy of the vibration signal and calculate its mean μ and standard deviation σ within the sliding window to obtain the vibration energy threshold E threshold， k is an adjustable parameter; when the vibration energy E>E threshold When the fracture event occurs, it is determined and then analyzed comprehensively in combination with other parameters.

[0119] After predicting the avalanche time, the RAMMS (Rapid mass movement simulation) kinetic model can also be synchronously triggered; the DEM elevation model and snow layer state data are input into the RAMMS kinetic model to locate the coordinates of the avalanche starting area based on the peak vibration energy. The snow layer state data can include snowpack density ρ, cohesion c, friction angle ϕ, etc.; the RAMMS kinetic model outputs the avalanche flow trajectory and the maximum impact range in the form of a probability density map, and divides the core area (p≥10KPa) and the warning area (p≥5KPa) according to the damage intensity. Thus, the location of the avalanche can be determined to facilitate early warning.

[0120] The following is based on Figure 3 to illustrate the overall implementation process of the present invention: 1. Obtain snow layer state data and detect the DEM elevation data; 2. Perform data denoising and temperature drift compensation processing on the snow layer state data; 3. Perform spatio-temporal fusion on the processed snow layer state data and elevation data, specifically, obtain time monitoring data and spatial monitoring data after time alignment and spatial alignment; 4. Obtain the risk probability through a hybrid model based on the time monitoring data and spatial monitoring data; 5. Calculate the risk index based on the risk probability and determine the level of disaster risk; 6. Generate a 3D view based on the elevation data and issue an early warning based on the level of disaster risk.

[0121] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0122] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0123] The present application also provides a snow layer stability monitoring system for implementing the above snow layer stability monitoring method. The snow layer stability monitoring system includes a multi-dimensional sensor array and a processing module; the multi-dimensional sensor array includes a plurality of multi-dimensional sensors, and each of the multi-dimensional sensors is communicatively connected to the processing module; wherein: The multi-dimensional sensor is configured to monitor snow layer parameters at its location to obtain monitoring data, and send the monitoring data to the processing module; The processing module is configured to receive the monitoring data sent by each of the multi-dimensional sensors, obtain snow layer state data based on each of the monitoring data, and determine a disaster risk according to the snow layer state data.

[0124] By setting a multi-dimensional sensor array including a plurality of multi-dimensional sensors, the present snow layer stability monitoring system can achieve high-precision monitoring of the snow layer state, and then determine the snow layer state based on the obtained snow layer state data to judge the disaster risk, providing an all-weather and grid-based precise prevention and control solution for high-risk avalanche areas.

[0125] Further, the multi-dimensional sensor includes a longitudinal anchor rod, and a plurality of temperature sensors are arranged on the longitudinal anchor rod, and the temperature sensors are arranged at a preset interval.

[0126] The present application also provides an electronic device. Referring to Figure 4 , in terms of hardware structure, the electronic device may include components such as a communication module 10, a memory 20, and a processor 30. In the electronic device, the processor 30 is respectively connected to the memory 20 and the communication module 10, and a computer program is stored on the memory 20, and the computer program is simultaneously executed by the processor 30, and when the computer program is executed, the steps of the above method embodiment are implemented.

[0127] The communication module 10 can be connected to an external communication device through a network. The communication module 10 can receive requests sent by the external communication device, and can also send requests, instructions, and information to the external communication device. The external communication device can be other electronic devices, servers, or Internet of Things devices, such as a TV, etc.

[0128] A memory 20 can be used to store software programs and various data. The memory 20 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as obtaining monitoring data sent by each multi-dimensional sensor in a multi-dimensional sensor array), etc.; the data storage area can include a database, and the data storage area can store data or information created according to the use of the system, etc. In addition, the memory 20 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0129] A processor 30 is the control center of the electronic device. It uses various interfaces and circuits to connect all parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 20, and by calling data stored in the memory 20, it executes various functions of the electronic device and processes data, thereby monitoring the entire electronic device. The processor 30 can include one or more processing units; optionally, the processor 30 can integrate an application processor and a modulation and demodulation processor. Among them, the application processor mainly processes the operating system, user interface, and application programs, etc., and the modulation and demodulation processor mainly processes wireless communication. It can be understood that the above modulation and demodulation processor may not be integrated into the processor 30 either.

[0130] Although Figure 4 not shown, the above electronic device may further include a circuit control module, and the circuit control module is used to connect to a power source to ensure the normal operation of other components. Those skilled in the art can understand that Figure 4 the structure of the electronic device shown in does not constitute a limitation on the electronic device, and it may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0131] The present invention also proposes a computer-readable storage medium, on which a computer program is stored. The computer-readable storage medium can be Figure 4 the memory 20 in the electronic device, or can be at least one of ROM (Read-Only Memory), RAM (Random Access Memory), magnetic disk, and optical disc. The computer-readable storage medium includes several instructions for causing a terminal device having a processor (which can be a television, a car, a mobile phone, a computer, a server, a terminal, or a network device, etc.) to execute the methods described in various embodiments of the present invention.

[0132] In the present invention, the terms "first", "second", "third", "fourth", and "fifth" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0133] In the description of this specification, the description referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0134] Although the embodiments of the present invention have been shown and described above, the scope of protection of the present invention is not limited thereto. It can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, and substitutions to the above embodiments within the scope of the present invention, and these changes, modifications, and substitutions should all be covered by the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for monitoring the stability of a snow layer, characterized in that, The snow layer stability monitoring method includes: Obtaining the monitoring data sent by each multi-dimensional sensor in the multi-dimensional sensor array; Obtaining snow layer state data based on each of the monitoring data; Determining the disaster risk based on the snow layer state data.

2. The snow layer stability monitoring method according to claim 1, characterized in that, The obtaining of the snow layer state data based on each of the monitoring data includes: Performing time alignment on each of the monitoring data to obtain time monitoring data; Mapping each monitoring data into a preset data space to obtain space monitoring data; Determining the snow layer state data based on the time monitoring data and the space monitoring data.

3. The snow layer stability monitoring method according to claim 2, wherein, The snow layer state data includes a risk probability, and the determining of the snow layer state data based on the time monitoring data and the space monitoring data includes: Obtaining a hybrid model, where the hybrid model includes a convolutional neural network layer, a long short-term memory network layer, and a fully connected layer; Inputting the space monitoring data into the convolutional neural network layer to obtain space features; Inputting the time monitoring data into the long short-term memory network layer to obtain time features; Concatenating the space features and the time features to obtain fused features; Inputting the fused features into the fully connected layer to obtain the risk probability.

4. The snow layer stability monitoring method according to claim 1, characterized in that, The determining of the disaster risk based on the snow layer state data includes: Determining a comprehensive risk index corresponding to the snow layer state data; Obtaining a risk division threshold, and determining the disaster risk corresponding to the comprehensive risk index according to the risk division threshold.

5. The snow layer stability monitoring method according to claim 4, characterized in that, The snow layer state data includes a risk probability and environmental parameters; the determining of the comprehensive risk index corresponding to the snow layer state data includes: Obtaining the weights corresponding to the risk probability and the environmental parameters; Performing weighted calculation on the risk probability and the environmental parameters based on the weights to obtain the comprehensive risk index.

6. The snow layer stability monitoring method according to claim 1, characterized in that, The obtaining of the monitoring data sent by each multi-dimensional sensor in the multi-dimensional sensor array includes: Obtaining the real-time disaster risk; Determining a target acquisition frequency corresponding to the real-time disaster risk, where the target acquisition frequency is positively correlated with the real-time disaster risk; Obtaining the monitoring data sent by each multi-dimensional sensor in the multi-dimensional sensor array at the target acquisition frequency.

7. The snow layer stability monitoring method according to claim 1, characterized in that After determining the disaster risk based on the snow layer state data, it includes: Obtaining the terrain model corresponding to the multi-dimensional sensor array; Mapping the snow layer state data and the disaster risk into the terrain model for display.

8. The snow layer stability monitoring method according to claim 1, wherein After determining the disaster risk based on the snow layer state data, it includes: Judging whether the disaster risk reaches a preset risk threshold; If the disaster risk reaches the preset risk threshold, obtaining historical snow layer state data; Predicting the avalanche prediction time based on the historical snow layer state data; Performing a warning operation based on the avalanche prediction time.

9. A snow layer stability monitoring system, characterized in that, The snow layer stability monitoring system includes a multi-dimensional sensor array and a processing module; the multi-dimensional sensor array includes multiple multi-dimensional sensors, and each multi-dimensional sensor is communicatively connected to the processing module; where: The multi-dimensional sensor is used to monitor the snow layer parameters at the location to obtain monitoring data, and send the monitoring data to the processing module; The processing module is configured to receive the monitoring data sent by each of the multi-dimensional sensors, obtain snow layer state data based on each of the monitoring data, and determine a disaster risk according to the snow layer state data.

10. The snow layer stability monitoring system according to claim 9, characterized in that, The multi-dimensional sensor includes a longitudinal anchor rod, and a plurality of temperature sensors are arranged on the longitudinal anchor rod, and the temperature sensors are arranged at a preset interval.

Images