Alpine sea of ​​cloud landscape prediction method, device, electronic device and storage medium

Abstract

The present invention relates to the field of landscape prediction technology, specifically a method, device, electronic device, and storage medium for predicting alpine sea of ​​clouds. The method comprises obtaining basic prediction data for a target area on a predicted day, wherein the basic prediction data includes a relative humidity factor, a temperature condition factor, an atmospheric stability factor, a wind speed factor, and a terrain lift factor; and inputting the basic prediction data into a sea of ​​clouds landscape prediction model to obtain the probability of a sea of ​​clouds occurring on the predicted day. The present invention does not restrict its application area and has low construction costs. Furthermore, the method can continuously update the basic prediction data for the target area on the predicted day, making it easier for tourists and photography enthusiasts to view the probability of a sea of ​​clouds occurring in real time and facilitate travel planning. This improves the tourist experience and enhances the quality of scenic area services.

Description

Technical Field

[0001] The present invention relates to the technical field of landscape prediction, and specifically to a method, device, electronic equipment and storage medium for predicting sea of ​​clouds landscape on a high mountain. Background Art

[0002] Sea of ​​clouds is a unique natural phenomenon, beloved by tourists and photography enthusiasts for its spectacular beauty and visual appeal. In alpine regions, the formation of sea of ​​clouds often depends on specific meteorological conditions and topographical features, and its timing and extent are highly uncertain. Therefore, accurate and real-time prediction of the appearance and duration of sea of ​​clouds is crucial for tourism development, ecological protection, and meteorological services.

[0003] Existing methods for predicting alpine sea of ​​clouds include:

[0004] (1) Traditional weather forecasting methods

[0005] Based on traditional statistics, whether a high mountain sea of ​​clouds will appear on the second day is judged. The appearance of sea of ​​clouds is affected by many factors such as temperature, humidity, wind speed, and atmospheric stability. In addition, the terrain and environment in mountainous areas are complex and changeable. This method of using non-real-time data for prediction is difficult to achieve accurate prediction. In addition, this method is difficult for ordinary users to understand the prediction results, and cannot provide intuitive phenological landscape information, resulting in poor user interactivity.

[0006] (2) Methods based on forecasting tools to assist forecasting

[0007] This method requires setting up a sea of ​​cloud landscape prediction tool in alpine scenic areas, but the development cost of this tool is high and it is not easy to promote.

[0008] (3) Methods for in-depth analysis of meteorological data

[0009] For example, the existing public patent document with publication number CN112987131B specifically discloses a method and system for forecasting sea of ​​clouds. Cloud cover data on a meteorological grid is obtained based on relative humidity and potential height meteorological data, and a meteorological grid is established. A geographic grid is established based on geographic height data, and the geographic height data on the geographic grid is matched to the meteorological grid to obtain geographic height data on the meteorological grid. Each meteorological grid point can obtain corresponding vertical multi-layer cloud cover characteristic data through the geographic height data, potential height data, and cloud cover data corresponding to the grid point. Finally, based on the vertical multi-layer cloud cover characteristic data, a sea of ​​clouds forecast result is obtained.

[0010] However, the above methods are difficult to develop and promote, or the analysis and processing process is relatively complicated. Therefore, there is an urgent need for a high mountain sea of ​​cloud landscape prediction method with low construction cost, no geographical restrictions, and suitable for promotion. Summary of the Invention

[0011] The present invention provides a method, device, electronic device and storage medium for predicting high mountain sea of ​​clouds landscape, which overcomes the shortcomings of the above-mentioned existing technologies and can effectively solve the problem that the existing technologies cannot effectively predict high mountain sea of ​​clouds landscape.

[0012] One of the technical solutions of the present invention is achieved through the following measures: a method for predicting high mountain sea of ​​clouds, comprising:

[0013] Obtain the forecast basic data for the target area on the forecast day, where the forecast basic data includes relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor;

[0014] Input the prediction basic data into the sea of ​​clouds landscape prediction model to obtain the probability of sea of ​​clouds occurring on the predicted day. The sea of ​​clouds landscape prediction model is as follows:

[0015] P cloud =α·H rel +β·T diff +γ·S stab +δ·W wind +∈·G topo +ζ

[0016] Among them, P cloud is the probability of sea of ​​clouds; H rel 、T diff 、S stab 、W wind , G topo are the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; α, β, γ, δ, ∈ are the weights of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; ζ is the deviation value.

[0017] The following are further optimizations and / or improvements to the above technical solutions:

[0018] The construction process of the above-mentioned sea of ​​cloud landscape prediction model includes:

[0019] Obtaining a number of historical influencing factor data, wherein the historical influencing factor data include meteorological factors and topographic factors when the sea of ​​clouds landscape appears in different regions, and meteorological factors and topographic factors when the sea of ​​clouds landscape does not appear;

[0020] The correlation between each meteorological factor and topographic factor in the historical influencing factor data and the occurrence of sea of ​​clouds was analyzed, and the five factors with the highest correlation were selected to form a key factor set. The five factors include relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and topographic lift factor.

[0021] Weight values ​​are assigned to the five factors, and a weighted sea of ​​clouds landscape prediction model is constructed as follows:

[0022] P cloud =α·H rel +β·T diff +γ·S stab +δ·W wind +∈·G topo +ζ

[0023] Among them, P cloud is the probability of sea of ​​clouds; H rel 、T diff 、S stab 、W wind , G topo are the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; α, β, γ, δ, ∈ are the weights of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; ζ is the deviation value.

[0024] The above-mentioned Pearson correlation coefficient analysis method is used to assign weight values ​​to the five types of factors.

[0025] The above also includes weight correction of the sea of ​​clouds landscape prediction model based on multiple prediction result data, including:

[0026] Collect all forecast result data within the set time interval, where the forecast result data includes the forecast basic data input and the corresponding actual sea of ​​clouds occurrence results;

[0027] The correlation analysis algorithm is used to analyze the correlation between the predicted basic data and the actual sea of ​​clouds occurrence results;

[0028] According to the results of correlation analysis, the weight values ​​of various factors in the sea of ​​cloud landscape prediction model are calibrated.

[0029] The process of obtaining the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor mentioned above includes:

[0030] Obtain meteorological data and calculate humidity factor, temperature condition factor, atmospheric stability factor, and wind speed factor as follows:

[0031] Humidity factor H rel As shown below:

[0032]

[0033] Where RH is relative humidity;

[0034] Temperature condition factor T diff As shown below:

[0035]

[0036] Among them, T surface is the actual temperature; T dew is the dew point temperature; T range is the temperature difference normalization coefficient;

[0037] Atmospheric stability S stab The factors are as follows:

[0038]

[0039] Where γ is the actual temperature lapse rate; γ dry is the dry adiabatic lapse rate;

[0040] Wind speed factor W wind As shown below:

[0041]

[0042] Where V is the wind speed; V opt is the optimal wind speed; σ is the wind speed width parameter; e is a constant term;

[0043] Obtain terrain data and calculate terrain lift factor G topo ;

[0044]

[0045] Among them, H mountain is the peak height; H cloud_base is the cloud base height; H range is the normalized height difference.

[0046] The second technical solution of the present invention is achieved by the following measures: a device for predicting sea of ​​clouds in high mountains, comprising:

[0047] A forecast data acquisition unit is configured to acquire forecast basic data for the target area on the forecast day, wherein the forecast basic data includes relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor;

[0048] The prediction unit inputs the prediction basic data into the sea of ​​clouds landscape prediction model to obtain the probability of sea of ​​clouds occurring on the predicted day. The sea of ​​clouds landscape prediction model is as follows:

[0049] P cloud =α·H rel +β·T diff +γ·S stab +δ·W wind +∈·G topo +ζ

[0050] Among them, P cloud is the probability of sea of ​​clouds; H rel 、T diff 、S stab 、W wind , G topo are the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; α, β, γ, δ, ∈ are the weights of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; ζ is the deviation value.

[0051] The following are further optimizations and / or improvements to the above technical solutions:

[0052] The above also includes model building units, including:

[0053] A historical data acquisition module acquires a number of historical influencing factor data, wherein the historical influencing factor data includes meteorological factors and topographic factors when the sea of ​​clouds appears in different regions, and meteorological factors and topographic factors when the sea of ​​clouds does not appear;

[0054] The factor screening module analyzes the correlation between each meteorological factor and the occurrence of sea of ​​clouds in the historical influencing factor data, and selects the five factors with the highest correlation to form a key factor set. The five factors include relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor.

[0055] The weight allocation module assigns weight values ​​to the five factors and constructs a cloud sea landscape prediction model based on the weighted method, as follows:

[0056] P cloud =α·H rel +β·T diff +γ·S stab +δ·W wind +∈·G topo +ζ

[0057] Among them, P cloud is the probability of sea of ​​clouds; H rel 、T diff 、S stab 、W wind , G topo are the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; α, β, γ, δ, ∈ are the weights of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; ζ is the deviation value.

[0058] The above also includes a weight correction unit, including:

[0059] The data collection module collects all the forecast result data within the set time interval, where the forecast result data includes the forecast basic data input and the corresponding actual sea of ​​clouds occurrence results;

[0060] The analysis module uses correlation analysis algorithms to analyze the correlation between the predicted basic data and the actual sea of ​​clouds occurrence results;

[0061] The correction module corrects the weight values ​​of various factors in the sea of ​​cloud landscape prediction model based on the correlation analysis results.

[0062] The third technical solution of the present invention is achieved through the following measures: an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement the steps in the high mountain cloud sea landscape prediction method.

[0063] The fourth technical solution of the present invention is achieved through the following measures: a storage medium, characterized in that a computer program that can be read by a computer is stored on the storage medium, and the computer program is configured to execute the steps in the high mountain sea of ​​cloud landscape prediction method when it is run.

[0064] The present invention establishes a sea of ​​clouds landscape prediction model and combines the sea of ​​clouds landscape prediction model with the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor of the prediction day to obtain the probability of sea of ​​clouds occurring. The greater the probability of sea of ​​clouds occurring, the greater the probability of high mountain sea of ​​clouds occurring. The method does not restrict the application area and has low construction cost. In addition, the method can continuously update the prediction basic data of the target area on the prediction day, making it convenient for tourists and photography enthusiasts to view the probability of sea of ​​clouds occurring in real time and facilitate their travel arrangements, thereby improving the tourists' experience and the service quality of the scenic area. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Attachment Figure 1 This is a flow chart of the method for predicting alpine sea of ​​clouds landscape provided by the present invention.

[0066] Attachment Figure 2 This is a flow chart of the method for constructing a sea of ​​cloud landscape prediction model provided by the present invention.

[0067] Attachment Figure 3 This is a flow chart of the weight correction method for the sea of ​​clouds landscape prediction model provided by the present invention.

[0068] Attachment Figure 4 This is the actual occurrence map of the high mountain sea of ​​clouds landscape provided by the present invention.

[0069] Attachment Figure 5 This is a structural schematic diagram of a device for predicting high mountain sea of ​​clouds landscape provided by the present invention.

[0070] Attachment Figure 6 This is a schematic structural diagram of another device for predicting sea of ​​clouds in high mountains provided by the present invention.

[0071] Attachment Figure 7 A schematic diagram of an implementation environment provided by the present invention. DETAILED DESCRIPTION

[0072] The present invention is not limited to the following embodiments, and specific implementation methods can be determined based on the technical solutions of the present invention and actual conditions.

[0073] Those skilled in the art will understand that, unless otherwise stated, in the embodiments of the present invention, a "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0074] In addition, in the embodiments of the present invention, “plurality” refers to two or more than two, and “first” and “second” are used for distinguishing descriptions and should not be understood as implying relative importance.

[0075] Embodiments of the present invention provide a method, device, electronic device, and storage medium for predicting high mountain sea of ​​clouds. The high mountain sea of ​​clouds prediction device can be integrated into a computer device, which can be a server or a terminal. Alternatively, the device can be executed jointly by a terminal and a server. The above examples should not be construed as limiting the present invention.

[0076] As attached Figure 7 As shown, taking the example of a terminal and a server jointly executing a high mountain sea of ​​cloud landscape prediction method, the terminal and the server are connected via a network, which can be a wired network or a wireless network connection, among which the ancient city wall data restoration method can be integrated in the terminal.

[0077] The terminal provides an interactive interface for viewing the high mountain sea of ​​cloud landscape forecast, allowing users to select a date and view the high mountain sea of ​​cloud landscape forecast results for that date. The terminal may include a mobile phone, wearable smart device, tablet computer, laptop computer, personal computer (PC), or vehicle-mounted computer, and the present invention does not limit this. The present invention does not limit the number of terminal devices.

[0078] The server provides various data processing and analysis processes in the high mountain sea of ​​clouds landscape prediction method, specifically including constructing a sea of ​​clouds landscape prediction model; obtaining basic prediction data for the target area on the predicted day, where the basic prediction data includes relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor; and inputting the basic prediction data into the sea of ​​clouds landscape prediction model to obtain the probability of sea of ​​clouds occurring on the predicted day. The server here can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms, but the present invention is not limited to this.

[0079] Based on this, the technical solution of the present invention will be introduced and explained with reference to several examples below.

[0080] Example 1: As shown in the attached Figure 1 As shown, the embodiment of the present invention discloses a method for predicting high mountain sea of ​​clouds, comprising:

[0081] Step S110, obtaining basic prediction data for the target area on the day to be predicted, wherein the basic prediction data includes relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor;

[0082] In this step, the five factors selected to predict the probability of sea of ​​clouds occurrence, namely relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor, are obtained by comprehensively analyzing the meteorological factors and terrain factors when sea of ​​clouds appear and when sea of ​​clouds do not appear in the historical sea of ​​clouds landscape data of different regions.

[0083] In this step, the basic forecast data for the target area on the forecast day is obtained through future meteorological data.

[0084] Step S120: Input the prediction basic data into the sea of ​​clouds landscape prediction model to obtain the probability of sea of ​​clouds occurring on the day to be predicted. The sea of ​​clouds landscape prediction model is as follows:

[0085] P cloud =α·H rel +β·T diff +γ·S stab +δ·W wind +∈·G topo +ζ

[0086] Among them, P cloud is the probability of sea of ​​clouds; H rel 、T diff 、S stab、W wind , G topo are the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain uplift factor respectively; α, β, γ, δ, ∈ are the weights of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain uplift factor respectively; ζ is the deviation value (generally taken as 0).

[0087] The embodiment of the present invention discloses a method for predicting a high mountain sea of ​​clouds landscape. A sea of ​​clouds landscape prediction model is established, and the probability of sea of ​​clouds occurring is obtained by combining the sea of ​​clouds landscape prediction model with the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor of the predicted day. The greater the probability of sea of ​​clouds occurring, the greater the probability of high mountain sea of ​​clouds landscape occurring. The method does not restrict the application area and has low construction cost. In addition, the method can continuously update the prediction basic data of the predicted day in the target area, making it convenient for tourists and photography enthusiasts to view the probability of sea of ​​clouds occurring in real time and facilitate their travel arrangements, thereby improving the tourists' experience and improving the service quality of the scenic area.

[0088] Example 2: This embodiment of the present invention discloses a method for predicting a high mountain sea of ​​clouds, which is a further optimization of the above embodiment. The process of obtaining the relative humidity factor, the temperature condition factor, the atmospheric stability factor, the wind speed factor, and the terrain lift factor includes:

[0089] (1) Obtain meteorological data and calculate humidity factor, temperature condition factor, atmospheric stability factor, and wind speed factor as follows:

[0090] (a) Humidity factor H rel (indicates the humidity of the atmosphere, ranging from 0 to 1) as follows:

[0091]

[0092] Where RH is relative humidity (%);

[0093] When the humidity is close to 100%, sea of ​​clouds is more likely to appear.

[0094] (b) Temperature condition factor T diff (indicates how close the air temperature is to the dew point temperature, ranging from 0 to 1) as shown below:

[0095]

[0096] Among them, T surface is the actual temperature (℃); T dew is the dew point temperature (℃); T range is the temperature difference normalization coefficient (can be set to 10℃);

[0097] When the temperature is close to the dew point, T diff Close to 1.

[0098] (c) Atmospheric stability S stab The factor (reflecting the stability of atmospheric stratification, ranging from 0 to 1) is as follows:

[0099]

[0100] Where, γ is the actual temperature lapse rate (℃ / km); γ dry is the dry adiabatic lapse rate, which can be set to 9.8°C / km;

[0101] When the above stratification is stable (temperature gradient is low), S stab Close to 1.

[0102] (d) Wind speed factor W wind (Indicates the effect of wind speed on the stability of the sea of ​​clouds, ranging from 0 to 1) as follows:

[0103]

[0104] Where, V is wind speed (m / s); V opt is the optimal wind speed, generally 2 to 5 m / s; σ is the wind speed width parameter; e is a constant term, which can be 1.

[0105] (2) Obtain terrain data and calculate the terrain lift factor G topo (reflects the effect of terrain on air rise, ranging from 0 to 1);

[0106]

[0107] Among them, H mountain is the peak height (m); H cloud_base is the cloud base height (m), which can be estimated by the moist adiabatic model; H range It is the standardized height difference, that is, the difference between the maximum and minimum heights of historical data.

[0108] Example 3: As shown in the attached Figure 2 The embodiment of the present invention discloses a method for predicting high mountain sea of ​​clouds landscape, which is a further optimization of the above embodiment. The process of constructing a sea of ​​clouds landscape prediction model includes:

[0109] Step S210, obtaining a number of historical influencing factor data, wherein the historical influencing factor data includes meteorological factors and topographic factors when the sea of ​​clouds appears in different regions, and meteorological factors and topographic factors when the sea of ​​clouds does not appear;

[0110] Step S220 , performing a correlation analysis between each meteorological factor and terrain factor in the historical influencing factor data and the presence of sea of ​​clouds, and selecting the five factors with the highest correlation to form a key factor set. The five factors include relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor.

[0111] In this embodiment, there is no limitation on the method of correlation analysis. Screening can be performed manually based on a table, or a correlation analysis algorithm can be introduced to perform correlation analysis.

[0112] Step S230: assign weights to the five factors and construct a cloud sea landscape prediction model based on the weighted values. The details are as follows:

[0113] P cloud =α·H rel +β·T diff +γ·S stab +δ·W wind +∈·C topo +ζ

[0114] Among them, P cloud is the probability of sea of ​​clouds; H rel 、T diff 、S stab 、W wind , G topo are the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; α, β, γ, δ, ∈ are the weights of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; ζ is the deviation value.

[0115] In this embodiment, the weight values ​​of the five factors may be assigned using, but not limited to, the Pearson correlation coefficient analysis method. The process of using the Pearson correlation coefficient analysis method specifically includes:

[0116] (1) Based on multiple historical influencing factor data, the correlation coefficient r between relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, terrain lift factor and the presence of sea of ​​clouds was calculated. The corresponding calculation formula is as follows:

[0117]

[0118] Among them, X i is the value of a factor in the i-th historical impact factor data; Y i is the cloud sea appearance result mark corresponding to the i-th historical impact factor data (1 indicates cloud sea appearance, 0 indicates no appearance); n is the number of historical impact factor data; is the mean of variables X and Y.

[0119] (2) The absolute values ​​of the correlation coefficients r of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor are normalized to ensure that the sum of all weights is 1.

[0120]

[0121] Among them, X 影响因子 Including relative humidity factor weight α, temperature factor weight β, atmospheric stability factor weight γ, wind speed factor weight δ, and terrain uplift factor weight ∈; x1, x2, x3, x4, and x5 are the correlation coefficients r for humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain uplift factor, respectively.

[0122] Furthermore, the cloud sea landscape prediction model can be verified using multiple historical influencing factor data. If the verification is unsuccessful, the adjustment factor type or weight is returned.

[0123] Example 4: As shown in the attached Figure 3 The embodiment of the present invention discloses a method for predicting sea of ​​clouds in high mountains, which is a further optimization of the above embodiment. The method further includes weight correction of the sea of ​​clouds prediction model based on multiple prediction result data, including:

[0124] Step S310: Collect all prediction result data within a set time interval, wherein the prediction result data includes the prediction basic data input and the corresponding actual sea of ​​clouds occurrence results;

[0125] Step S320: Use a correlation analysis algorithm to analyze the correlation between the predicted basic data and the actual sea of ​​clouds. The correlation process in this step can be completed by, but is not limited to, the Pearson correlation coefficient analysis method.

[0126] Step S330: Correcting the weight values ​​of various factors in the sea of ​​cloud landscape prediction model according to the correlation analysis results.

[0127] Example 5: The method disclosed in the above embodiment is used to predict the probability of sea of ​​clouds on a certain day to verify the method disclosed in the present invention, as follows:

[0128] (1) Constructing a sea of ​​cloud landscape prediction model

[0129] (a) Obtain 5 sets of meteorological monitoring data values ​​for the target area described in Table 1.

[0130] Table 1 Meteorological monitoring data

[0131]

[0132] (b) Assign weight values ​​to the five factors. The assignment results are shown in Table 2.

[0133] Table 2 Weight analysis table

[0134] factor Correlation coefficient r Correlation Impact weight of sea of ​​clouds <![CDATA[Relative humidity X1]]> 0.79 There is a strong positive correlation with the occurrence of sea of ​​clouds 0.23 <![CDATA[Temperature gradient X2]]> -0.65 There is a strong negative correlation with the occurrence of sea of ​​clouds 0.19 <![CDATA[Atmospheric stability X3]]> 0.72 There is a strong positive correlation with the occurrence of sea of ​​clouds 0.21 <![CDATA[Wind speed X4]]> -0.45 Moderate negative correlation with sea of ​​clouds 0.13 <![CDATA[Terrain uplift X5]]> 0.8 There is a strong positive correlation with the occurrence of sea of ​​clouds 0.24

[0135] (2) Obtain the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor of the target area on a certain day in summer, as follows:

[0136] Expected humidity RH about 90%

[0137] Expected temperature T surface About 21°, the dew point temperature T dew About 20°

[0138] The actual temperature lapse rate is expected to be about γ about 3℃ / km, and the dry adiabatic lapse rate is taken as a constant γ dry About 9.8℃ / km

[0139] The forecast wind speed V is about 3m / s, and the optimal wind speed V opt About 3m / s, σ=2

[0140] Peak height H mountain About 1350m, cloud base height H cloud_base About 1000m, standardized height difference H range About 500m

[0141] The corresponding relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor are as follows:

[0142] Humidity factor (H rel ):0.9

[0143] Temperature condition factor (T diff ):0.9

[0144] Atmospheric stability factor (S stab ):0.69

[0145] Wind speed factor (W wind ):1

[0146] Terrain lift factor (G topo ):0.7

[0147] Bias term (ζ): set to 0

[0148] (3) By bringing the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor into the cloud sea landscape prediction model, the probability of cloud sea occurrence on the predicted day is obtained to be 82.09%, which is a high probability of cloud sea occurrence.

[0149] (4) The actual mountain sea of ​​clouds on that day is as follows Figure 4 As shown, attached Figure 4 The appearance of a sea of ​​clouds landscape indicates that the method disclosed in the present invention is effective.

[0150] Example 6: As shown in the attached Figure 5 As shown, the embodiment of the present invention discloses a device for predicting high mountain sea of ​​clouds, comprising:

[0151] A forecast data acquisition unit is configured to acquire forecast basic data for the target area on the forecast day, wherein the forecast basic data includes relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor;

[0152] The prediction unit inputs the prediction basic data into the sea of ​​clouds landscape prediction model to obtain the probability of sea of ​​clouds occurring on the predicted day. The sea of ​​clouds landscape prediction model is as follows:

[0153] P cloud =α·H rel +β·T diff +γ·S stab +δ·W wind +∈·C topo +ζ

[0154] Among them, P cloud is the probability of sea of ​​clouds; H rel 、T diff 、S stab 、W wind , G topo are the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; α, β, γ, δ, ∈ are the weights of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; ζ is the deviation value.

[0155] Example 7: As shown in the attached Figure 6 As shown, the embodiment of the present invention discloses a device for predicting sea of ​​clouds in high mountains, which is a further optimization of the above embodiment, and further includes:

[0156] Model building unit, including:

[0157] A historical data acquisition module acquires a number of historical influencing factor data, wherein the historical influencing factor data includes meteorological factors and topographic factors when the sea of ​​clouds appears in different regions, and meteorological factors and topographic factors when the sea of ​​clouds does not appear;

[0158] The factor screening module analyzes the correlation between each meteorological factor and the occurrence of sea of ​​clouds in the historical influencing factor data, and selects the five factors with the highest correlation to form a key factor set. The five factors include relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor.

[0159] The weight allocation module assigns weight values ​​to the five factors and constructs a cloud sea landscape prediction model based on the weighted method, as follows:

[0160] P cloud =α·H rel +β·T diff +γ·S stab +δ·W wind +∈·G topo +ζ

[0161] Among them, P cloud is the probability of sea of ​​clouds; H rel 、T diff 、S stab 、W wind , G topo are the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; α, β, γ, δ, ∈ are the weights of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; ζ is the deviation value.

[0162] Weight correction unit, including:

[0163] The data collection module collects all the forecast result data within the set time interval, where the forecast result data includes the forecast basic data input and the corresponding actual sea of ​​clouds occurrence results;

[0164] The analysis module uses correlation analysis algorithms to analyze the correlation between the predicted basic data and the actual sea of ​​clouds occurrence results;

[0165] The correction module corrects the weight values ​​of various factors in the sea of ​​cloud landscape prediction model based on the correlation analysis results.

[0166] Embodiment 8: The embodiment of the present invention discloses a storage medium, on which a computer program readable by a computer is stored, and the computer program is configured to execute a method for predicting a high mountain sea of ​​clouds landscape when running.

[0167] The above-mentioned storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory, a mobile hard disk, a magnetic disk, or an optical disk.

[0168] Embodiment 9: An embodiment of the present invention discloses an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement a method for predicting high mountain sea of ​​clouds landscape.

[0169] The processor may be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an ASIC, an FPGA, or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the present disclosure. It may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and so on. Memory may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memories, removable hard drives, magnetic disks, or optical disks.

[0170] It will be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention may be implemented in various computer languages, for example, the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0171] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0172] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1The function specified in one or more boxes.

[0173] The above content is only a specific implementation method of the present invention, which has strong adaptability and implementation effect, but the scope of protection of the present invention is not limited to this. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope covered by the present invention.

Claims

1. A method for predicting high mountain sea of ​​clouds, characterized in that: include: Obtain the forecast basic data for the target area on the forecast day, where the forecast basic data includes relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor; Input the prediction basic data into the sea of ​​clouds landscape prediction model to obtain the probability of sea of ​​clouds occurring on the predicted day. The sea of ​​clouds landscape prediction model is as follows: P cloud =α·H rel +β·T diff +γ·S stab +δ·W wind +∈·G topo +g Among them, P cloud is the probability of sea of ​​clouds; H rel 、T diff 、S stab 、W wind , G topo are the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; α, β, γ, δ, ∈ are the weights of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; ζ is the deviation value; where: The process of obtaining the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor includes: Obtain meteorological data and calculate humidity factor, temperature condition factor, atmospheric stability factor, and wind speed factor as follows: Humidity factor H rel As shown below: Where RH is relative humidity; Temperature condition factor T diff As shown below: Among them, T surface is the actual temperature; T dew is the dew point temperature; T range is the temperature difference normalization coefficient; Atmospheric stability S stab The factors are as follows: Where γ is the actual temperature lapse rate; γ dry is the dry adiabatic lapse rate; Wind speed factor W wind As shown below: Where V is the wind speed; V opt is the optimal wind speed; σ is the wind speed width parameter; e is a constant term; Obtain terrain data and calculate terrain lift factor G topo ; Among them, H mountain is the peak height; H cloud_base is the cloud base height; H range is the normalized height difference.

2. The method for predicting alpine sea of ​​clouds according to claim 1, wherein: The process of constructing the sea of ​​clouds landscape prediction model includes: Obtaining a number of historical influencing factor data, wherein the historical influencing factor data include meteorological factors and topographic factors when the sea of ​​clouds landscape appears in different regions, and meteorological factors and topographic factors when the sea of ​​clouds landscape does not appear; The correlation between each meteorological factor and topographic factor in the historical influencing factor data and the occurrence of sea of ​​clouds was analyzed, and the five factors with the highest correlation were selected to form a key factor set. The five factors include relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and topographic lift factor. Weight values ​​are assigned to the five factors, and a weighted sea of ​​clouds landscape prediction model is constructed as follows: P cloud =α·H rel +β·T diff +γ·S stab +δ·W wind +∈·G topo +g Among them, P cloud is the probability of sea of ​​clouds; H rel 、T diff 、S stab 、W wind , G topo are the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; α, β, γ, δ, ∈ are the weights of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; ζ is the deviation value.

3. The method for predicting alpine sea of ​​clouds according to claim 2, wherein: The Pearson correlation coefficient analysis method was used to assign weight values ​​to the five factors.

4. The method for predicting alpine sea of ​​clouds according to any one of claims 1 to 3, wherein: It also includes weight correction of the cloud sea landscape prediction model based on multiple prediction result data, including: Collect all forecast result data within the set time interval, where the forecast result data includes the forecast basic data input and the corresponding actual sea of ​​clouds occurrence results; The correlation analysis algorithm is used to analyze the correlation between the predicted basic data and the actual sea of ​​clouds occurrence results; According to the results of correlation analysis, the weight values ​​of various factors in the sea of ​​cloud landscape prediction model are calibrated.

5. A device for predicting high mountain sea of ​​clouds using the method according to any one of claims 1 to 4, characterized in that: include: A forecast data acquisition unit is configured to acquire forecast basic data for the target area on the forecast day, wherein the forecast basic data includes relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor; The prediction unit inputs the prediction basic data into the sea of ​​clouds landscape prediction model to obtain the probability of sea of ​​clouds occurring on the predicted day. The sea of ​​clouds landscape prediction model is as follows: P cloud =α·H rel +β·T diff +γ·S stab +δ·W wind +∈·C topo +g Among them, P cloud is the probability of sea of ​​clouds; H rel 、T diff 、S stab 、W wind , G topo are the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; α, β, γ, δ, ∈ are the weights of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; ζ is the deviation value.

6. The device for predicting alpine sea of ​​clouds according to claim 5, characterized in that: Also included are model building units, including: A historical data acquisition module acquires a number of historical influencing factor data, wherein the historical influencing factor data includes meteorological factors and topographic factors when the sea of ​​clouds appears in different regions, and meteorological factors and topographic factors when the sea of ​​clouds does not appear; The factor screening module analyzes the correlation between each meteorological factor and the occurrence of sea of ​​clouds in the historical influencing factor data, and selects the five factors with the highest correlation to form a key factor set. The five factors include relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor. The weight allocation module assigns weight values ​​to the five factors and constructs a cloud sea landscape prediction model based on the weighted method, as follows: P cloud =α·H rel +β·T diff +γ·S stab +δ·W wind +∈·C topo +g Among them, P cloud is the probability of sea of ​​clouds; H rel 、T diff 、S stab 、W wind , G topo are the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; α, β, γ, δ, ∈ are the weights of the relative humidity factor, temperature condition factor, atmospheric stability factor, wind speed factor, and terrain lift factor respectively; ζ is the deviation value.

7. The device for predicting mountain sea of ​​clouds according to claim 5, characterized in that: Also included is a weight correction unit, including: The data collection module collects all the forecast result data within the set time interval, where the forecast result data includes the forecast basic data input and the corresponding actual sea of ​​clouds occurrence results; The analysis module uses correlation analysis algorithms to analyze the correlation between the predicted basic data and the actual sea of ​​clouds occurrence results; The correction module corrects the weight values ​​of various factors in the sea of ​​cloud landscape prediction model based on the correlation analysis results.

8. The device for predicting sea of ​​clouds in high mountains according to claim 6, characterized in that: Also included is a weight correction unit, including: The data collection module collects all the forecast result data within the set time interval, where the forecast result data includes the forecast basic data input and the corresponding actual sea of ​​clouds occurrence results; The analysis module uses correlation analysis algorithms to analyze the correlation between the predicted basic data and the actual sea of ​​clouds occurrence results; The correction module corrects the weight values ​​of various factors in the sea of ​​cloud landscape prediction model based on the correlation analysis results.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the steps in the method according to any one of claims 1 to 5.

10. A storage medium, characterized in that: The storage medium stores a computer program that can be read by a computer, and the computer program is configured to execute the steps of the method according to any one of claims 1 to 5 when run.

Images