Snow water content prediction method and snow water content monitoring system

Abstract

This invention proposes a method and system for predicting snow moisture content. The method includes the following steps: acquiring detection data obtained by a snow moisture content sensor targeting a target snow layer; acquiring a trained moisture content prediction model; and inputting the detection data into the trained moisture content prediction model to obtain the predicted moisture content of the target snow layer. By setting up a snow simulation platform and training the moisture content prediction model based on the acquired training detection data, the moisture content prediction model can learn the relationship between the snow moisture content detection data and the actual moisture content. Therefore, by using the trained moisture content prediction model to predict moisture content based on the detection data from the snow moisture content sensor, the predicted moisture content can accurately reflect the moisture content of the target snow layer, improving the accuracy of snow layer moisture content detection in high-altitude and cold environments.

Description

Technical Field

[0001] This invention relates to the field of avalanche detection, and more particularly to a method for predicting snow moisture content and a snow moisture content monitoring system. Background Technology

[0002] Snow moisture content refers to the water content of the snow layer. It is one of the most important behavioral parameters determining avalanche occurrence and can indicate the stability of high-altitude snow structures. However, existing moisture content sensors are mainly used for soil moisture detection; for high-altitude and frigid environments, these sensors suffer from significant data drift and other problems. Therefore, how to accurately detect snow moisture content and provide crucial and reliable data support for avalanche early warning in high-altitude areas is an urgent problem to be solved. Summary of the Invention

[0003] The main objective of this invention is to propose a method for predicting snow moisture content and a snow moisture content monitoring system, aiming to solve the problem of how to accurately detect snow moisture content in the prior art.

[0004] To achieve the above objectives, the present invention provides a method for predicting snow moisture content, the method comprising the following steps:

[0005] Acquire detection data obtained by a snow moisture content sensor targeting the snow layer;

[0006] Obtain the completed moisture content prediction model, wherein the moisture content prediction model is trained by training detection data and actual moisture content, wherein the training detection data is the detection data detected by the snow moisture content sensor in the simulated snow layer of the snow simulation platform, and the actual moisture content is the moisture content of the simulated snow layer when the snow moisture content sensor is detected in the snow simulation platform;

[0007] The detection data is input into the trained moisture content prediction model to obtain the predicted moisture content of the target snow layer.

[0008] Optionally, inputting the detection data into the trained water content prediction model to obtain the predicted water content of the target snow layer includes:

[0009] Acquire multiple detection data points obtained by the snow moisture content sensor within the current time window;

[0010] Use the multiple detection data obtained within the current time window as input data;

[0011] The input data is fed into the trained water content prediction model to obtain the predicted water content of the target snow layer.

[0012] Optionally, the process of obtaining the trained moisture content prediction model includes:

[0013] Obtain the parameters of the target snow scene and control the snow simulation platform to simulate the snow layer based on the parameters of the target snow scene;

[0014] Acquire training detection data from the snow moisture content sensor in the simulated snow layer of the snow simulation platform;

[0015] Obtain the detection temperature and detection capacitance value from the training detection data, and obtain the actual moisture content corresponding to the training detection data;

[0016] The detection temperature and detection capacitance value are used as inputs, and the actual moisture content is used as the true value to generate training samples.

[0017] The moisture content prediction model is trained using the training samples to obtain the trained moisture content prediction model.

[0018] Optionally, obtaining the actual moisture content corresponding to the training detection data includes:

[0019] Obtain a measured snow sample from the simulated snow layer;

[0020] The measured snow sample is heated until the snow in the measured snow sample is completely melted to obtain a melt water sample;

[0021] The actual moisture content is calculated by comparing the mass of the meltwater sample and the mass of the measured snow sample.

[0022] Optionally, the step of acquiring the target snow scene parameters and controlling the snow simulation platform to perform snow layer simulation based on the target snow scene parameters includes:

[0023] Obtain the target snow layer parameters, target slope, target light radiation intensity, and target precipitation intensity from the target snow scene parameters;

[0024] Set the parameters of the snow simulation device in the snow simulation platform to the target snow layer parameters;

[0025] Set the tilt angle of the support plane in the snow accumulation simulation platform to the target slope;

[0026] Set the light radiation intensity of the heating irradiator in the snow simulation platform to the target light radiation intensity;

[0027] Set the precipitation intensity of the sprayer in the snow accumulation simulation platform to the target precipitation intensity.

[0028] To achieve the above objectives, the present invention also provides a snow moisture content monitoring system, which includes a snow moisture content sensor, a snow simulation platform, and a snow moisture content prediction device; wherein:

[0029] The snow accumulation simulation platform is used to simulate snow layers and obtain simulated snow layers;

[0030] The snow moisture content sensor is used to detect data in a simulated snow layer;

[0031] The snow moisture content prediction device is used to acquire detection data obtained by a snow moisture content sensor targeting a target snow layer; acquire a trained moisture content prediction model, wherein the moisture content prediction model is trained using training detection data and actual moisture content, the training detection data being the detection data detected by the snow moisture content sensor in a simulated snow layer on a snow simulation platform, and the actual moisture content being the moisture content of the simulated snow layer when the snow moisture content sensor detects it on the snow simulation platform; and input the detection data into the trained moisture content prediction model to obtain the predicted moisture content of the target snow layer.

[0032] Optionally, the snow simulation platform includes a support plane, a snow simulation device, and an environmental simulation device; wherein:

[0033] The snow simulation device is used to create a simulated snow layer on the supporting plane.

[0034] The environmental simulation device is used to simulate the environment where the simulated snow layer is located as the target environment.

[0035] Optionally, the environmental simulation device includes a heating irradiator and a sprayer; the heating irradiator and the sprayer are disposed above the supporting plane, wherein:

[0036] The heating irradiator is used to simulate sunlight exposure based on light radiation readings;

[0037] The sprayer is used to simulate precipitation based on precipitation intensity.

[0038] Optionally, the supporting plane is an adjustable ramp structure; wherein:

[0039] The supporting plane is used to provide an inclined plane for the target slope.

[0040] Optionally, the snow moisture content sensor includes a temperature sensor and a capacitance sensor.

[0041] This invention proposes a method and system for predicting snow moisture content. The method involves acquiring detection data obtained by a snow moisture content sensor targeting a target snow layer; acquiring a trained moisture content prediction model, wherein the prediction model is trained using training detection data and actual moisture content. The training detection data consists of data detected by the snow moisture content sensor in a simulated snow layer on a snow simulation platform, and the actual moisture content is the moisture content of the simulated snow layer when the snow moisture content sensor is detected on the snow simulation platform. The detection data is then input into the trained moisture content prediction model to obtain the predicted moisture content of the target snow layer. By setting up a snow cover simulation platform and simulating the snow layer through the platform, a snow moisture content sensor is used to detect the simulated snow layer. Based on the obtained training detection data, a moisture content prediction model is trained, enabling the model to learn the relationship between the snow moisture content detection data and the actual moisture content. Thus, the trained moisture content prediction model predicts the moisture content based on the detection data from the snow moisture content sensor, ensuring that the predicted moisture content accurately reflects the moisture content of the target snow layer and improving the accuracy of snow layer moisture content detection in high-altitude and cold environments. Attached Figure Description

[0042] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart illustrating the first embodiment of the snow moisture content prediction method of the present invention.

[0045] Figure 2 This is a schematic diagram illustrating the snow moisture content prediction method of the present invention.

[0046] Figure 3 This is a schematic diagram of the snow accumulation simulation platform of the present invention;

[0047] Figure 4 This is a schematic diagram of the snow moisture content sensor of the present invention;

[0048] Figure 5 This is a schematic diagram of the module structure of the electronic device of the present invention. Detailed Implementation

[0049] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0050] This invention provides a method for predicting snow moisture content, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the snow moisture content prediction method of the present invention. The method includes the following steps:

[0051] Step S10: Obtain the detection data obtained by the snow moisture content sensor for the target snow layer;

[0052] Snow moisture content sensors are used to detect the moisture content in snow layers to obtain data. This data is based on the moisture content of the snow layer and reflects its moisture content status. The specific data type can be set according to actual needs, such as capacitance or temperature values. Because water has a high dielectric constant, the higher the snow moisture content, the greater the capacitance value detected by the snow moisture content sensor. Therefore, detecting capacitance values ​​reflects the moisture content of the snow layer. Capacitance includes:

[0053]

[0054] Where C is the capacitance; 0 is the dielectric constant of vacuum, with a value of 8.854 × 10⁻⁶. -12 F m; r It is the relative permittivity; for water, r ≈ 80, the relative permittivity of dry air is close to 1; A is the area of ​​the electrode, in square meters (m²); d is the distance between the electrodes, in meters (m).

[0055] The target snow layer is the snow layer for which moisture content testing is actually required; such as snow layers located in high-altitude or frigid environments. For example, snow moisture content sensors are deployed in areas requiring avalanche detection. These sensors detect the target snow layer and obtain data; the data is then transmitted to a snow moisture content prediction device. The snow moisture content prediction device can be configured based on actual needs, such as a terminal device installed at the detection site. Communication between the snow moisture content sensor and the snow moisture content prediction device can be achieved via wired or wireless means.

[0056] Step S20: Obtain the trained moisture content prediction model, wherein the moisture content prediction model is trained using training detection data and actual moisture content. The training detection data is the detection data detected by the snow moisture content sensor in the simulated snow layer of the snow simulation platform, and the actual moisture content is the moisture content of the simulated snow layer when the snow moisture content sensor is detected in the snow simulation platform.

[0057] The moisture content prediction model is a model that predicts the moisture content of the snow layer based on the detection data of the snow moisture content sensor.

[0058] Since the detection data of the snow moisture content sensor is directly affected by the moisture content of the snow layer, it is possible to predict the moisture content of the snow layer based on the detection data. However, in practical applications, due to the harsh environment of high altitude and cold regions, it is difficult to overcome the challenge of accurately obtaining the relationship between the detection data and the moisture content of the snow layer in existing technologies.

[0059] In this embodiment, in order to accurately obtain the relationship between the detection data and the snow layer moisture content, a snow accumulation simulation platform is set up to simulate the snow layer environment and obtain a simulated snow layer. It can be understood that the simulated snow layer can be set based on the specific snow layer environment that needs to be simulated. Under the specific simulated snow layer, the snow moisture content sensor is set in the simulated snow layer to detect the moisture content of the simulated snow layer. Thus, the snow moisture content sensor can obtain the training detection data corresponding to the simulated snow layer.

[0060] It should be noted that the snow moisture content sensor used to obtain training detection data and the snow moisture content sensor used for detecting the target snow layer do not need to be the same sensor. When the snow moisture content sensors are set based on the same principle, different snow moisture content sensors can detect the moisture content of the snow layer based on the same principle to obtain detection data. Therefore, the relationship between the obtained detection data and the snow layer moisture content is the same or similar. Therefore, as long as the snow moisture content sensor set based on the same principle is used for obtaining training detection data and detecting the target snow layer, it is acceptable. For example, if the snow moisture content sensor detects the capacitance value of the target snow layer, it can be used in this application.

[0061] The snow cover simulation platform is designed to construct a snow layer scenario in order to determine the relationship between detection data and moisture content. Therefore, the snow moisture content sensor uses the training detection data obtained from the simulated snow layer to train the moisture content prediction model.

[0062] The actual moisture content is the actual moisture content of the simulated snow layer in the snow accumulation simulation platform. The training detection data indicates the detection status of the snow moisture content sensor under the actual moisture content of the simulated snow layer, while the actual moisture content indicates the actual moisture content of the simulated snow layer. Therefore, by using the training detection data and the actual moisture content, the correlation between the detection data of the snow moisture content sensor and the moisture content of the snow layer can be realized. Thus, by training the moisture content prediction model with the training detection data and the actual moisture content, the trained moisture content prediction model can learn the correlation between the detection data and the moisture content of the snow layer, thereby enabling the trained moisture content prediction model to predict the moisture content of the snow layer based on the detection data.

[0063] When specifically testing the moisture content prediction model, the corresponding training detection data and the actual moisture content are used as a set of training samples, and the moisture content prediction model is trained through multiple sets of training samples. It can be understood that the training detection data in a set of training samples is the detection data obtained when the simulated snow layer moisture content is the actual moisture content.

[0064] The specific training method for the moisture content prediction model can be set according to actual needs, such as model type, training completion conditions, loss function, etc.; model type, such as LSTM (Long Short-Term Memory).

[0065] Step S30: Input the detection data into the trained water content prediction model to obtain the predicted water content of the target snow layer.

[0066] Since the trained moisture content prediction model has learned the correlation between the detection data and the moisture content of the snow layer, after obtaining the detection data of the snow moisture content sensor for the target snow layer, the trained moisture content prediction model can predict the moisture content of the target snow layer based on the correlation between the detection data and the moisture content of the snow layer, and obtain the predicted moisture content.

[0067] This embodiment sets up a snow accumulation simulation platform and simulates the snow layer using the platform. Then, it detects the simulated snow layer using a snow moisture content sensor. Based on the obtained training detection data, it trains a moisture content prediction model, enabling the model to learn the relationship between the snow moisture content detection data and the actual moisture content. Thus, the trained moisture content prediction model predicts the moisture content based on the detection data from the snow moisture content sensor, ensuring that the predicted moisture content accurately reflects the moisture content of the target snow layer and improving the accuracy of snow layer moisture content detection in high-altitude and cold environments.

[0068] Furthermore, in the second embodiment of the snow moisture content prediction method of the present invention based on the first embodiment, step S30 includes the following steps:

[0069] Step S31: Obtain multiple detection data points obtained by the snow moisture content sensor within the current time window;

[0070] Step S32: Use the multiple detection data obtained within the current time window as input data;

[0071] Step S33: Input the input data into the trained water content prediction model to obtain the predicted water content of the target snow layer.

[0072] In practical applications, the moisture content of snow in high-altitude and frigid environments is affected by a variety of environmental factors. Therefore, in order to more accurately detect the moisture content, this embodiment introduces a time window, within which multiple detection data obtained by the snow moisture content sensor are acquired; and the input data for this period is obtained by combining the multiple detection data within the time window, and the moisture content is predicted based on the input data by the trained moisture content prediction model.

[0073] The length of the time window can be set according to actual needs, and the collection frequency of detection data within the time window can also be set according to actual needs.

[0074] To achieve more consistent data processing, the detection data within the time window can be normalized first; for example:

[0075]

[0076] Where Xg is the normalized detection data; X is the detection data before normalization; min(x) is the minimum value of the detection data within the time window; and max(x) is the maximum value of the detection data within the time window.

[0077] It should be noted that when the test data contains different types of data, such as both capacitance and temperature values, the capacitance values ​​in each test data set can be normalized, and the temperature values ​​in each test data set can also be normalized.

[0078] After normalizing the detection data, the input data can be generated:

[0079]

[0080] Where yt is the input data; t is the time; and Lw is the length of the time window.

[0081] The input data yt indicates that it includes all normalized detection data collected within the time window.

[0082] The predicted moisture content can be obtained by inputting the detection data into the trained moisture content prediction model.

[0083] It should be noted that when training the moisture content prediction model, the training detection data obtained within the time window can also be used as training input data. The method for generating training input data is the same as the method for generating input data mentioned above. After obtaining the training input data, the training input data and the actual moisture content of the simulated snow layer within the time window are used as a set of training samples, and the moisture content prediction model is trained using the training samples.

[0084] When setting the loss function, you can set it according to your actual needs, such as using the mean squared error as the loss function:

[0085]

[0086] Where yr is the actual water content; n is the number of training samples in a training batch.

[0087] Furthermore, in the third embodiment of the snow moisture content prediction method of the present invention based on the first embodiment of the present invention, the step S20 includes the following steps:

[0088] Step S40: Obtain the target snow scene parameters and control the snow simulation platform to simulate the snow layer based on the target snow scene parameters;

[0089] Step S50: Obtain training detection data detected by the snow moisture content sensor in the simulated snow layer of the snow simulation platform;

[0090] Step S60: Obtain the detection temperature and detection capacitance value from the training detection data, and obtain the actual moisture content corresponding to the training detection data;

[0091] Step S70: Use the detected temperature and detected capacitance value as inputs, and use the actual moisture content as the true value to generate training samples;

[0092] Step S80: Train the moisture content prediction model using the training samples to obtain the trained moisture content prediction model.

[0093] The target snow scene parameters are used to describe the scene to be simulated. These parameters can be set based on actual needs; the specific parameter types they indicate can also be set according to actual needs, such as snow thickness, snow distribution, the slope of the platform where the snow layer is located, solar radiation intensity, and precipitation intensity. Among these, snow thickness and snow distribution indicate the main structure of the snow layer; slope affects the infiltration path and retention capacity of snowmelt. For example, gentler slopes facilitate water infiltration and accumulation, thereby increasing local moisture content, while steeper slopes accelerate water expulsion. Furthermore, the settling and compaction rates of snow differ under different slopes, further altering the moisture content of the snow layer. Therefore, setting different slopes allows for the characterization of snow moisture content characteristics under different terrain scenarios; solar radiation intensity is used to simulate sunlight in the actual environment. The greater the intensity of solar radiation, the faster the snow melts, leading to a faster increase in the water content of the snow layer. Therefore, solar radiation intensity can characterize the water content of the snow layer. Precipitation intensity is used to simulate precipitation events in the real environment. It can be understood that when there is rainfall or snow with high water content, a large amount of liquid water will be injected into the snow layer in a short period of time, thereby rapidly increasing the water content in the snow layer. Therefore, precipitation intensity can also reflect the changing characteristics of the water content of the snow layer.

[0094] By setting different parameters, different snow-covered environments can be simulated. Therefore, in practical applications, the corresponding target snow scene parameters can be set for the specific environment to be simulated, and the snow simulation platform can be used to simulate the target snow scene parameters to achieve the simulation of the specific scene.

[0095] After simulating a specific scenario, training and detection data and actual moisture content can be obtained within that simulated scenario.

[0096] The training and detection data in this embodiment specifically includes the capacitance and temperature values ​​of the simulated snow layer.

[0097] Because water has a high dielectric constant, the higher the water content of the snow layer, the greater the capacitance value detected by the snow moisture content sensor. Therefore, the detection of capacitance value can reflect the water content of the snow layer.

[0098] Temperature changes affect the capacitance value detected by the snow moisture content sensor, especially in low-temperature environments where the capacitance value may be lower than expected. Therefore, in this embodiment, capacitance and temperature values ​​are collected simultaneously to correct the capacitance value using the temperature value. Specifically, a temperature compensation factor can be determined based on the temperature value to correct the capacitance value. The specific temperature-based correction can be set according to actual needs, such as determining the temperature compensation factor corresponding to different temperature values ​​based on experiments. For example, if the temperature compensation factor and capacitance value have a linear relationship:

[0099]

[0100] Among them, C t β is the capacitance value detected by the snow moisture sensor; β is the temperature compensation factor; T t T represents the current temperature. ref This is a reference temperature; the specific setting can be based on actual needs, such as setting it to a standard temperature, like 25℃; C tx This is the capacitance value obtained after compensation.

[0101] The water content of the snow layer can be expressed as:

[0102]

[0103] Where W is the water content; C0 is the capacitance when the snow layer has a water content of 0; C W This is the capacitance corresponding to the saturation of water in the snow layer, i.e., the theoretical maximum value.

[0104] Because the electrical conductivity of water in snow differs significantly from that of air, changes in the water content of the snow layer directly affect its capacitance.

[0105] Although the above formula allows the determination of snow moisture content by detecting the capacitance value of the snow layer, in practical applications, snow moisture content sensors are affected by various environmental factors and changes in the state of the snow layer itself, leading to deviations in the detected capacitance value and consequently, inaccuracies in moisture content determination. Therefore, to improve the accuracy of moisture content detection, this application establishes a moisture content prediction model and trains it by constructing training samples of detection data and actual moisture content under different scenarios. This allows the moisture content prediction model to learn the correlation between moisture content and capacitance value under different scenarios, thereby eliminating environmental biases and ensuring the accuracy of moisture content detection.

[0106] Similarly, in the detection of the target snow layer, the capacitance value and temperature value are detected simultaneously. After determining the temperature compensation factor through the temperature value, the capacitance value is compensated by the temperature compensation factor. The compensated capacitance value is then input into the trained moisture content prediction model to perform moisture content prediction.

[0107] Further, step S60 includes the following steps:

[0108] Step S61: Obtain a measured snow sample from the simulated snow layer;

[0109] Step S62: Heat the measured snow sample until the snow in the measured snow sample is completely melted to obtain a melt water sample;

[0110] Step S63: The actual moisture content is calculated by the mass of the melted water sample and the measured snow sample.

[0111] The measured snow samples are collected from the simulated snow layer as samples to detect the actual moisture content. In order to improve the efficiency of sample acquisition, in the actual simulation, different precipitation intensities can be sprayed at different locations in the simulated snow layer through a sprayer, so that different locations in the simulated snow layer have different moisture contents. Then, snow samples are collected and measured at multiple locations with different moisture contents. At the same time, snow moisture content sensors are set at multiple locations with different moisture contents, so that multiple training samples with different moisture contents can be obtained from a single simulation.

[0112] The actual moisture content is obtained through actual measurement.

[0113] By heating the snow sample, the original moisture in the snow sample evaporates as water vapor; simultaneously, during the heating process, some of the original snow melts into water. Once the snow in the snow sample has completely melted, the resulting water sample (melted water sample) is obtained. The mass of the melted water sample is the mass of the snow sample minus the mass of the original water. Therefore:

[0114]

[0115] Where Wt is the actual moisture content; M water For the mass of the dissolved water sample; M snow To measure the mass of the snow sample.

[0116] To further ensure the accuracy of the actual moisture content, multiple snow samples with the same moisture content can be collected at locations with the same moisture content, and the actual moisture content detected from these snow samples can be used as the actual moisture content of the corresponding training samples.

[0117] The specific process of obtaining the actual moisture content may include:

[0118] 1. Collect snow samples;

[0119] Multiple samplings were conducted at different locations on the platform's sloping surface, and a fixed volume of snow sample (V) was collected using containers such as snow sampling tubes. snow (L);

[0120] 2. Measure the initial mass of the snow sample;

[0121] Place the collected snow sample in a clean container and measure its total mass using an electronic scale. Record this mass value M. snow (g);

[0122] 3. Melted snow samples;

[0123] Place the training snow sample in a heating device, such as a warm water bath or electric hot plate, to ensure that the snow is completely melted into water; during the melting process, place a thermometer to monitor the temperature and ensure that the melting process proceeds smoothly;

[0124] 4. Measurement of meltwater quality;

[0125] After all the melted water has been collected, measure the volume V of the melted water using a measuring cup or other container. water (L), then, the mass M of the melted water was measured using a mass scale. water (g).

[0126] 5. Calculate the water content of the snow;

[0127] The actual water content is calculated based on the mass of the meltwater sample after melting and the initial mass of the training snow sample.

[0128] Further, step S40 includes the following steps:

[0129] Step S41: Obtain the target snow layer parameters, target slope, target light radiation intensity, and target precipitation intensity from the target snow scene parameters;

[0130] Step S42: Set the parameters of the snow simulation device in the snow simulation platform to the target snow layer parameters;

[0131] Step S43: Set the tilt angle of the support plane in the snow simulation platform to the target slope.

[0132] Step S44: Set the light radiation intensity of the heating irradiator in the snow simulation platform to the target light radiation intensity;

[0133] Step S45: Set the precipitation intensity of the sprayer in the snow accumulation simulation platform to the target precipitation intensity.

[0134] The target snow layer parameters can include snow layer thickness and snow layer distribution, which indicate the main structure of the snow layer.

[0135] The target slope affects the infiltration path and retention capacity of snowmelt. For example, gentler slopes facilitate water infiltration and accumulation, thereby increasing local moisture content, while steeper slopes accelerate water expulsion. In addition, the settlement and compaction rates of snow cover differ under different slopes, which further alters the moisture content of the snow layer. Therefore, setting different slopes can characterize the moisture content of snow layers under different terrain scenarios.

[0136] The target light radiation intensity is used to simulate sunlight in the actual environment. The greater the light radiation intensity, the faster the snow melts, resulting in a faster increase in the water content of the snow. Therefore, the light radiation intensity can be used to characterize the water content of the snow.

[0137] The target precipitation intensity is used to simulate precipitation events in the real environment. It can be understood that when there is rainfall or snow with high moisture content, a large amount of liquid water will be injected into the snow layer in a short period of time, thereby rapidly increasing the water content in the snow layer. Therefore, precipitation intensity can also reflect the changing characteristics of snow layer water content.

[0138] In this embodiment, by adjusting the target snow layer parameters, target slope, target light radiation intensity, and target precipitation intensity, diverse snow accumulation scenarios can be constructed.

[0139] The supporting plane is set as an adjustable slope structure, and the slope angle range can be set according to actual needs, such as 0~80°. By setting the slope angle of the supporting plane, it is possible to simulate snow accumulation environments with different slopes and simulate high-altitude terrain of plateau snow mountains, and to display different snow accumulation and sliding states. The specific adjustable slope structure can be set according to actual needs, such as using a mechanical device similar to a jack to precisely adjust the slope angle by raising one side.

[0140] The heating irradiator is used to simulate the radiative heating effect of snow caused by sunlight. Specifically, the heating irradiator can be a solar radiation irradiator array, which is installed above the supporting plane to achieve uniform energy radiation to the snow surface. By adjusting the power of the solar radiation irradiator array, the physical processes of high-altitude snow melting and hydrological seepage under different light intensities and durations can be simulated, and the simulation of snow moisture content change curves can be provided.

[0141] The sprayer is used to simulate precipitation in high-altitude environments. It can evenly spray water onto the snow surface to simulate the impact of rainfall on snow properties. The sprayer, located above the support plane, can adjust the particle size of the water mist, the spraying rate, and the duration to simulate the effects of different precipitation intensities on the humidity, density, and structural stability of the snow layer. It can also adjust the snow with different moisture contents under simulated warm and humidified precipitation weather in high-altitude areas.

[0142] See Figure 2 It should be noted that the relationship between moisture content and detection data may vary in different scenarios. Therefore, in order to enable the moisture content prediction model to support moisture content prediction in different scenarios, static environmental parameters can be added to the training samples. Static environmental parameters are used to indicate the environmental characteristics of the snow layer, such as slope, solar radiation intensity, and precipitation intensity.

[0143] Similarly, when predicting the water content of a target snow layer, the static environmental parameters corresponding to the target snow layer can be obtained. After fusing the static environmental parameters with the detection data using Fusion Operation, they can be input into the trained water content prediction model. This allows the water content prediction model to combine the actual scene of the target snow layer to predict the water content, further improving the accuracy of water content prediction. The static environmental parameters can be monitored by an environmental monitoring system, and specific parameters can be monitored by setting corresponding sensors.

[0144] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0145] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0146] This application also provides a snow moisture content monitoring system for implementing the above-described snow moisture content prediction method. The snow moisture content monitoring system includes a snow moisture content sensor, a snow simulation platform, and the snow moisture content prediction device described above; wherein:

[0147] The snow accumulation simulation platform is used to simulate snow layers and obtain simulated snow layers;

[0148] The snow moisture content sensor is used to detect data in a simulated snow layer;

[0149] A snow moisture content prediction device is used to acquire detection data obtained by a snow moisture content sensor detecting a target snow layer; acquire a trained moisture content prediction model, wherein the moisture content prediction model is trained using training detection data and actual moisture content, the training detection data being the detection data detected by the snow moisture content sensor in a simulated snow layer on a snow simulation platform, and the actual moisture content being the moisture content of the simulated snow layer when the snow moisture content sensor detects it on the snow simulation platform; and input the detection data into the trained moisture content prediction model to obtain the predicted moisture content of the target snow layer.

[0150] By setting up a snow cover simulation platform and simulating the snow layer through the platform, a snow moisture content sensor is used to detect the simulated snow layer. Based on the obtained training detection data, a moisture content prediction model is trained, enabling the model to learn the relationship between the snow moisture content detection data and the actual moisture content. Thus, the trained moisture content prediction model predicts the moisture content based on the detection data from the snow moisture content sensor, ensuring that the predicted moisture content accurately reflects the moisture content of the target snow layer and improving the accuracy of snow layer moisture content detection in high-altitude and cold environments.

[0151] Further, see Figure 3 The snow simulation platform includes a support plane, a snow simulation device, and an environmental simulation device; among which:

[0152] The snow simulation device is used to create a simulated snow layer on the supporting plane.

[0153] The environmental simulation device is used to simulate the environment where the simulated snow layer is located as the target environment.

[0154] In this embodiment, in order to accurately obtain the relationship between the detection data and the snow layer moisture content, a snow accumulation simulation platform is set up to simulate the snow layer environment and obtain a simulated snow layer. It can be understood that the simulated snow layer can be set based on the specific snow layer environment that needs to be simulated. Under the specific simulated snow layer, the snow moisture content sensor is set in the simulated snow layer to detect the moisture content of the simulated snow layer. Thus, the snow moisture content sensor can obtain the training detection data corresponding to the simulated snow layer.

[0155] The snow cover simulation platform is designed to construct a snow layer scenario in order to determine the relationship between detection data and moisture content. Therefore, the snow moisture content sensor uses the training detection data obtained from the simulated snow layer to train the moisture content prediction model.

[0156] The actual moisture content is the actual moisture content of the simulated snow layer in the snow accumulation simulation platform. The training detection data indicates the detection status of the snow moisture content sensor under the actual moisture content of the simulated snow layer, while the actual moisture content indicates the actual moisture content of the simulated snow layer. Therefore, by using the training detection data and the actual moisture content, the correlation between the detection data of the snow moisture content sensor and the moisture content of the snow layer can be realized. Thus, by training the moisture content prediction model with the training detection data and the actual moisture content, the trained moisture content prediction model can learn the correlation between the detection data and the moisture content of the snow layer, thereby enabling the trained moisture content prediction model to predict the moisture content of the snow layer based on the detection data.

[0157] The snow simulation device is used to generate snow layers; the environmental simulation device is used to simulate the environment in which the snow layers are located.

[0158] By setting up a snow cover simulation platform and simulating the snow layer through the platform, a snow moisture content sensor is used to detect the simulated snow layer. Based on the obtained training detection data, a moisture content prediction model is trained, enabling the model to learn the relationship between the snow moisture content detection data and the actual moisture content. Thus, the trained moisture content prediction model predicts the moisture content based on the detection data from the snow moisture content sensor, ensuring that the predicted moisture content accurately reflects the moisture content of the target snow layer and improving the accuracy of snow layer moisture content detection in high-altitude and cold environments.

[0159] Furthermore, the environmental simulation device includes a heating irradiator and a sprayer; the heating irradiator and the sprayer are disposed above the supporting plane, wherein:

[0160] The heating irradiator is used to simulate sunlight exposure based on light radiation readings;

[0161] The sprayer is used to simulate precipitation based on precipitation intensity.

[0162] The heating irradiator is used to simulate the radiative heating effect of snow caused by sunlight. Specifically, the heating irradiator can be a solar radiation irradiator array, which is installed above the supporting plane to achieve uniform energy radiation to the snow surface. By adjusting the power of the solar radiation irradiator array, the physical processes of high-altitude snow melting and hydrological seepage under different light intensities and durations can be simulated, and the simulation of snow moisture content change curves can be provided.

[0163] The sprayer is used to simulate precipitation in high-altitude environments. It can evenly spray water onto the snow surface to simulate the impact of rainfall on snow properties. The sprayer, located above the support plane, can adjust the particle size of the water mist, the spraying rate, and the duration to simulate the effects of different precipitation intensities on the humidity, density, and structural stability of the snow layer. It can also adjust the snow with different moisture contents under simulated warm and humidified precipitation weather in high-altitude areas.

[0164] Furthermore, the supporting plane is an adjustable ramp structure; wherein:

[0165] The supporting plane is used to provide an inclined plane for the target slope.

[0166] The supporting plane is set as an adjustable slope structure, and the slope angle range can be set according to actual needs, such as 0~80°. By setting the slope angle of the supporting plane, it is possible to simulate snow accumulation environments with different slopes and simulate high-altitude terrain of plateau snow mountains, and to display different snow accumulation and sliding states. The specific adjustable slope structure can be set according to actual needs, such as using a mechanical device similar to a jack to precisely adjust the slope angle by raising one side.

[0167] Further, see Figure 4 The snow moisture content sensor is equipped with a temperature sensor and a capacitance sensor.

[0168] Temperature sensors are used to monitor the temperature of the snow layer;

[0169] The capacitive sensor is used to detect the capacitance value of the snow layer; specifically, the probe of the snow moisture content sensor can be equipped with a capacitive sensing element; this probe is inserted into the snow layer and can detect the moisture content by the change in capacitance; the probe is made of antifreeze and low-temperature resistant material to ensure long-term stable operation in high-altitude and cold environments.

[0170] To further improve the reliability of snow moisture content sensors in high-altitude and frigid environments, specific features can be implemented, such as using a low-temperature resistant housing. For use in frigid environments, the sensor housing can be made of high-strength plastic to ensure it is not damaged by physical compression in low-temperature and humid conditions. Furthermore, a waterproof design can be adopted to ensure good sealing of the sensor housing, achieving an IP68 protection rating, preventing melted snow or rainwater from entering the sensor. This also avoids damage to the equipment caused by the freezing of melted water.

[0171] Understandably, snow moisture content sensors need to output detection data. Therefore, a communication structure needs to be set up on the snow moisture content sensor. The specific communication structure can be set according to actual needs. For example, if an analog signal output structure is set up, the snow moisture content sensor will output analog signals, such as voltage or current, which can represent the level of snow layer capacitance. The snow moisture content sensor transmits these data to external data acquisition equipment or control system. Alternatively, if a wireless communication module is set up, the snow moisture content sensor will be equipped with wireless communication capabilities, enabling it to upload data to a cloud platform or other devices in real time via a wireless network, facilitating remote monitoring and data analysis.

[0172] This application also provides an electronic device for implementing the above-described method for predicting snow moisture content, with reference to... Figure 5 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 connected to both the memory 20 and the communication module 10. The memory 20 stores a computer program, which is executed by the processor 30. When the computer program is executed, it implements the steps of the above-described method embodiments.

[0173] The communication module 10 can connect to external communication devices via a network. The communication module 10 can receive requests from the external communication devices and can also send requests, instructions, and information to the external communication devices. The external communication devices can be other electronic devices, servers, or IoT devices, such as televisions, etc.

[0174] The memory 20 can be used to store software programs and various data. The memory 20 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as acquiring detection data obtained by a snow moisture content sensor targeting a snow layer), etc.; the data storage area may include a database, and may store data or information created based on system usage. Furthermore, the memory 20 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0175] The processor 30 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 20, and by calling data stored in the memory 20, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. The processor 30 may include one or more processing units; optionally, the processor 30 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 30.

[0176] although Figure 5 Not shown, but the above-described electronic device may further include a circuit control module for connecting to a power supply to ensure the normal operation of other components. Those skilled in the art will understand that... Figure 5 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0177] The present invention also proposes a computer-readable storage medium having a computer program stored thereon. The computer-readable storage medium may be... Figure 5 The memory 20 in the electronic device may also be at least one of ROM (Read-Only Memory) / RAM (Random Access Memory), magnetic disk, optical disk, etc. The computer-readable storage medium includes a number of instructions to cause a terminal device with a processor (which may be a television, automobile, mobile phone, computer, server, terminal, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0178] In this 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. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0179] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0180] Although embodiments of the present invention have been shown and described above, the scope of protection of the present invention is not limited thereto. It is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, and substitutions to the above embodiments within the scope of the present invention, and such changes, modifications, and substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for predicting snow moisture content, characterized in that, The method for predicting snow moisture content includes: Acquire the detection data obtained by the snow moisture content sensor for the target snow layer, and obtain the static environmental parameters corresponding to the target snow layer; Obtain the completed moisture content prediction model, wherein the moisture content prediction model is trained by training detection data and actual moisture content, wherein the training detection data is the detection data detected by the snow moisture content sensor in the simulated snow layer of the snow simulation platform, and the actual moisture content is the moisture content of the simulated snow layer when the snow moisture content sensor is detected in the snow simulation platform; The detection data and the static environmental parameters are input into the trained water content prediction model to obtain the predicted water content of the target snow layer; The process of obtaining the trained moisture content prediction model includes: Obtain the parameters of the target snow scene and control the snow simulation platform to simulate the snow layer based on the parameters of the target snow scene; Acquire training detection data from the snow moisture content sensor in the simulated snow layer of the snow simulation platform; Obtain the detection temperature, detection capacitance value, and static environmental parameters from the training detection data, and obtain the actual moisture content corresponding to the training detection data; The detection temperature, detection capacitance value, and static environmental parameters are used as inputs, and the actual moisture content is used as the true value to generate training samples. The moisture content prediction model is trained using the training samples to obtain the trained moisture content prediction model.

2. The method for predicting snow moisture content as described in claim 1, characterized in that, The step of inputting the detection data into the trained water content prediction model to obtain the predicted water content of the target snow layer includes: Acquire multiple detection data points obtained by the snow moisture content sensor within the current time window; Use the multiple detection data obtained within the current time window as input data; The input data is fed into the trained water content prediction model to obtain the predicted water content of the target snow layer.

3. The method for predicting snow moisture content as described in claim 1, characterized in that, The step of obtaining the actual moisture content corresponding to the training detection data includes: Obtain a measured snow sample from the simulated snow layer; The measured snow sample is heated until the snow in the measured snow sample is completely melted to obtain a melt water sample; The actual moisture content is calculated by comparing the mass of the meltwater sample and the mass of the measured snow sample.

4. The method for predicting snow moisture content as described in claim 1, characterized in that, The step of acquiring the target snow scene parameters and controlling the snow simulation platform to simulate the snow layer based on the target snow scene parameters includes: Obtain the target snow layer parameters, target slope, target light radiation intensity, and target precipitation intensity from the target snow scene parameters; Set the parameters of the snow simulation device in the snow simulation platform to the target snow layer parameters; Set the tilt angle of the support plane in the snow accumulation simulation platform to the target slope; Set the light radiation intensity of the heating irradiator in the snow simulation platform to the target light radiation intensity; Set the precipitation intensity of the sprayer in the snow accumulation simulation platform to the target precipitation intensity.

5. A snow moisture content monitoring system, characterized in that, The snow moisture content monitoring system includes a snow moisture content sensor, a snow simulation platform, and a snow moisture content prediction device; wherein: The snow accumulation simulation platform is used to simulate snow layers and obtain simulated snow layers; The snow moisture content sensor is used to detect data in a simulated snow layer; The snow moisture content prediction device is used to acquire detection data obtained by a snow moisture content sensor targeting a target snow layer, acquire static environmental parameters corresponding to the target snow layer, acquire a trained moisture content prediction model, wherein the moisture content prediction model is trained using training detection data and actual moisture content, the training detection data being the detection data detected by the snow moisture content sensor in a simulated snow layer on a snow simulation platform, and the actual moisture content being the moisture content of the simulated snow layer when the snow moisture content sensor detects it on the snow simulation platform; and inputting the detection data and the static environmental parameters into the trained moisture content prediction model to obtain the predicted moisture content of the target snow layer. The process of obtaining the trained moisture content prediction model includes: Obtain the parameters of the target snow scene and control the snow simulation platform to simulate the snow layer based on the parameters of the target snow scene; Acquire training detection data from the snow moisture content sensor in the simulated snow layer of the snow simulation platform; Obtain the detection temperature, detection capacitance value, and static environmental parameters from the training detection data, and obtain the actual moisture content corresponding to the training detection data; The detection temperature, detection capacitance value, and static environmental parameters are used as inputs, and the actual moisture content is used as the true value to generate training samples. The moisture content prediction model is trained using the training samples to obtain the trained moisture content prediction model.

6. The snow moisture content monitoring system as described in claim 5, characterized in that, The snow simulation platform includes a support plane, a snow simulation device, and an environmental simulation device; wherein: The snow simulation device is used to create a simulated snow layer on the supporting plane. The environmental simulation device is used to simulate the environment where the simulated snow layer is located as the target environment.

7. The snow moisture content monitoring system as described in claim 6, characterized in that, The environmental simulation device includes a heating irradiator and a sprayer; the heating irradiator and the sprayer are disposed above the supporting plane, wherein: The heating irradiator is used to simulate sunlight exposure based on light radiation readings; The sprayer is used to simulate precipitation based on precipitation intensity.

8. The snow moisture content monitoring system as described in claim 6, characterized in that, The supporting plane is an adjustable ramp structure; wherein: The supporting plane is used to provide an inclined plane for the target slope.

9. The snow moisture content monitoring system as described in claim 8, characterized in that, The snow moisture content sensor is equipped with a temperature sensor and a capacitance sensor.

Images