Wind and light resource prediction method and device based on topographic climate characteristics, medium and equipment

Abstract

The invention discloses a wind and light resource prediction method and device based on terrain and climate characteristics, a medium and equipment. Historical climate data is interpolated to a spatial resolution consistent with that of topographic data, and global spatial autocorrelation analysis is combined, so that topographic-climate coupling characteristics of resource distribution and a self-aggregation rule of wind and light resources are accurately captured. And identifying key environment factors for driving resource distribution heterogeneity and local correlation coefficients of the key environment factors by utilizing correlation analysis, and carrying out partitioning, so that wind and light resource forming mechanisms in each sub-region tend to be consistent. On the basis, a model is independently trained for each same proton region, so that the model can be more focused on learning a unique rule of resource evolution along with time in the specific environment. The prediction model can accurately capture the internal association between the sub-region wind and light resources and the environmental factors, and finally output target time period prediction data is closer to reality. Therefore, the capturing of the fluctuation characteristics of the wind and light resources is more accurate and robust, and the accurate prediction of the future wind and light resources is realized.

Description

Technical Field

[0001] This application relates to the field of new energy technology, and in particular to a method, apparatus, medium and equipment for predicting wind and solar resources based on topographic and climatic characteristics. Background Technology

[0002] With the continuous growth in demand for new energy sources, accurate assessment and forecasting of wind and solar energy resources have become crucial for ensuring the rational utilization of new energy and the stable operation of the power grid. Existing wind and solar resource forecasting methods mainly rely on meteorological observation data and historical statistical models, employing traditional time series analysis or simple numerical simulations. While these methods can reflect resource trends to some extent, they fail to fully consider the significant impacts of topographic features such as undulation, slope, and orientation, as well as multidimensional climate parameters, on local wind speed and irradiance distribution, resulting in insufficient forecast accuracy. Summary of the Invention

[0003] In view of this, this application provides a method, apparatus, medium and equipment for predicting wind and solar resources based on topographic and climatic characteristics, in order to solve the problem of inaccurate wind and solar resource assessment caused by failure to consider topography and climate change in related technologies.

[0004] According to one aspect of this application, a method for predicting wind and solar resources based on topographic and climatic characteristics is provided, comprising: Acquire topographic data, historical climate data, and historical landscape data of the area to be analyzed; Based on the historical climate data with the same spatial resolution as the terrain data, a first spatial distribution feature of climate and terrain is generated through interpolation. The second spatial distribution characteristics of the historical landscape resource data were determined using a global spatial autocorrelation analysis algorithm. The historical landscape resource data is correlated with the topographic data and the historical climate data to determine the local correlation coefficient and key influencing factors between the historical landscape resource data and environmental factors, wherein the key influencing factors include at least one environmental factor. Based on the first spatial distribution characteristics, the second spatial distribution characteristics, the local correlation coefficient, and the key influencing factors, the area to be analyzed is divided into multiple sub-regions, wherein the wind and solar resource data of all points in the same sub-region are dominated by the same influencing factors. Based on the historical landscape resource data generated within the sub-region, a long short-term memory neural network model is trained to construct a landscape resource prediction model for the sub-region. The wind and solar resource prediction model is used to predict wind and solar resource data for the target period.

[0005] Optionally, acquiring the topographic data, historical climate data, and wind and solar resource data of the area to be analyzed includes: Collect digital elevation data of the area to be analyzed, as well as historical climate data and historical wind and light resource data of different stations in the area to be analyzed. The historical climate data includes temperature, humidity, wind speed, and wind direction, and the historical wind and light resource data includes irradiance, sunshine duration, wind speed, and wind power density. The terrain data is extracted based on the digital elevation data, wherein the terrain data includes slope value and aspect value.

[0006] Optionally, the generation of a first spatial distribution feature of climate and topography based on the historical climate data with the same spatial resolution as the topographic data through interpolation processing includes: Create a target grid based on the spatial resolution of the terrain data; The historical climate data collected from different stations are fitted to construct a semi-variogram model, wherein the semi-variogram model includes a spherical model, an exponential model, or a Gaussian model. The weight of the target station is calculated based on the semi-variogram model, wherein the target station is located within the grid range of the target grid; Based on the weights, the climate element values ​​of the center point of the grid cell within the grid range are calculated by weighted average. The climate element values, slope values, and aspect values ​​in the terrain data are used as the first spatial distribution features.

[0007] Optionally, determining the second spatial distribution characteristics of the historical landscape resource data using a global spatial autocorrelation analysis algorithm includes: Map the historical landscape resource data onto the target grid; The Moran's I index value of the historical landscape resource data was calculated using a global spatial autocorrelation analysis algorithm. Based on the comparison between the Moran's I index value and the index threshold, the second spatial distribution characteristics of the historical landscape resource data are determined. The global spatial autocorrelation analysis algorithm is expressed as follows: ; In the formula, I This is Moran's I exponent value. x i , x j For the historical landscape resource data in the i-th and j-th grid cells, This is the average value of historical landscape resource data. ω ijThis is the spatial weight matrix. n is the number of elements in the spatial weight matrix.

[0008] Optionally, the step of performing correlation analysis between the historical landscape resource data and the topographic data and the historical climate data to determine the local correlation coefficient between the historical landscape resource data and the topographic and climatic conditions includes: A geographic weighted regression model is constructed based on the historical landscape resource data, the topographic data, and the historical climate data; Solve the geographically weighted regression model to obtain the local correlation coefficient; The basic form of the geographically weighted regression model is as follows: y i = β 0( u i , v i )+ β 1( u i , v i ) x i + ε i ; In the formula, ( u i , v i Let be the coordinates of the i-th grid cell. x i For the wind and solar resource data in the i-th grid cell, y i For the terrain or climate data in the i-th grid cell, β 0( u i , v i ) represents the intercept of the i-th grid cell. β 1( u i , v i ) represents the local correlation coefficient of the i-th grid cell. ε i This is the error term.

[0009] Optionally, the step of performing correlation analysis between the historical landscape resource data and the topographic data and the historical climate data to determine the key influencing factors of the historical landscape resource data includes: Based on the historical landscape resource data, the topographic data, and the historical climate data, a covariance matrix is ​​constructed. The covariance matrix is ​​subjected to eigenvalue decomposition to obtain eigenvalues; The variance contribution rate and cumulative variance contribution rate of the environmental factors are calculated based on the aforementioned eigenvalues. The environmental factors corresponding to the feature values ​​whose cumulative variance contribution rate is greater than the contribution rate threshold are taken as the key influencing factors.

[0010] Optionally, the wind and solar resource prediction method based on topographic and climatic characteristics further includes: Calculate the comprehensive impact of the aforementioned key influencing factors on the distribution of wind and solar resources; The impact of environmental factors on the distribution of wind and solar resources is determined based on the comprehensive impact value.

[0011] Optionally, the wind and solar resource prediction method based on topographic and climatic characteristics further includes: Based on the first spatial distribution characteristics and the second spatial distribution characteristics, a wind and solar resource distribution map and a topographic and climatic characteristic map are generated; The map showing the distribution of the wind and solar resources and the map showing the topographic and climatic characteristics are displayed.

[0012] According to another aspect of this application, a wind and solar resource prediction device based on topographic and climatic characteristics is provided, comprising: The data acquisition module is used to acquire topographic data, historical climate data, and historical landscape resource data of the area to be analyzed. The data processing module is configured to generate a first spatial distribution feature of climate and topography based on the historical climate data with the same spatial resolution as the topographic data, through interpolation processing; and, The second spatial distribution characteristics of the historical landscape resource data were determined using a global spatial autocorrelation analysis algorithm; and, The historical scenic resource data is correlated with the topographic data and the historical climate data to determine the local correlation coefficients and key influencing factors between the historical scenic resource data and environmental factors, wherein the key influencing factors include at least one environmental factor; and, Based on the first spatial distribution characteristics, the second spatial distribution characteristics, the local correlation coefficient, and the key influencing factors, the area to be analyzed is divided into multiple sub-regions, wherein the wind and solar resource data of all points in the same sub-region are dominated by the same influencing factors. The model training module is used to train the long short-term memory neural network model based on the historical landscape resource data generated in the sub-region, and to construct a landscape resource prediction model for the sub-region. The prediction module is used to predict wind and solar resource data for a target period using the wind and solar resource prediction model.

[0013] Optionally, the data acquisition module is specifically used to collect digital elevation data of the area to be analyzed, as well as historical climate data and historical wind and light resource data of different stations within the area to be analyzed. The historical climate data includes temperature, humidity, wind speed, and wind direction, while the historical wind and light resource data includes irradiance, sunshine duration, wind speed, and wind power density. The module also extracts topographic data based on the digital elevation data, wherein the topographic data includes slope and aspect values.

[0014] Optionally, the data processing module is specifically used to create a target grid based on the spatial resolution of the terrain data; fit the historical climate data collected from different stations to construct a semi-variogram model, wherein the semi-variogram model includes a spherical model, an exponential model, or a Gaussian model; calculate the weight of the target station based on the semi-variogram model, wherein the target station is located within the grid range of the target grid; calculate the climate element value of the center point of the grid cell in the grid range by weighted averaging based on the weight; and use the climate element value, the slope value, and the aspect value in the terrain data as the first spatial distribution feature.

[0015] Optionally, the data processing module is specifically used to map the historical landscape resource data onto the target grid; calculate the Moran's I index value of the historical landscape resource data using a global spatial autocorrelation analysis algorithm; and determine the second spatial distribution characteristics of the historical landscape resource data based on the comparison result between the Moran's I index value and the index threshold; wherein, the global spatial autocorrelation analysis algorithm is expressed as: In the formula, I This is Moran's I exponent value. x i , x j For the historical landscape resource data in the i-th and j-th grid cells, This is the average value of historical landscape resource data. ω ij This is the spatial weight matrix. n is the number of elements in the spatial weight matrix.

[0016] Optionally, the data processing module is specifically used to construct a geographic weighted regression model based on the historical landscape resource data, the topographic data, and the historical climate data; solve the geographic weighted regression model to obtain the local correlation coefficient; wherein, the basic form of the geographic weighted regression model is: y i = β 0( u i , vi )+ β 1( u i , v i ) x i + ε i In the formula, ( u i , v i Let be the coordinates of the i-th grid cell. x i For the wind and solar resource data in the i-th grid cell, y i For the terrain or climate data in the i-th grid cell, β 0( u i , v i ) represents the intercept of the i-th grid cell. β 1( u i , v i ) represents the local correlation coefficient of the i-th grid cell. ε i This is the error term.

[0017] Optionally, the data processing module is specifically used to construct a covariance matrix based on the historical landscape resource data, the topographic data, and the historical climate data; perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues; calculate the variance contribution rate and cumulative variance contribution rate of environmental factors based on the eigenvalues; and take the environmental factors corresponding to the eigenvalues ​​whose cumulative variance contribution rate is greater than the contribution rate threshold as the key influencing factors.

[0018] Optionally, the data processing module is further configured to calculate the comprehensive impact value of the key influencing factors on the distribution of wind and solar resources; and determine the impact of environmental factors on the distribution of wind and solar resources based on the comprehensive impact value.

[0019] Optionally, the data processing module is specifically used to generate a wind and solar resource distribution map and a topographic and climate characteristic map based on the first spatial distribution characteristics and the second spatial distribution characteristics; The wind and solar resource prediction device based on topographic and climatic characteristics also includes: The display module is used to display the distribution map of the wind and solar resources and the topographic and climatic characteristics map.

[0020] According to another aspect of this application, a readable storage medium is provided having a program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method for predicting wind and solar resources based on terrain and climate characteristics.

[0021] According to another aspect of this application, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-described method for predicting wind and solar resources based on terrain and climate characteristics.

[0022] By employing the aforementioned technical solution, historical climate data is interpolated to a spatial resolution consistent with topographic data, and combined with global spatial autocorrelation analysis, the topographic-climate coupling characteristics (first spatial distribution characteristics) and the inherent aggregation patterns of wind and solar resources (second spatial distribution characteristics) of resource distribution are accurately captured. Correlation analysis is used to identify key environmental factors driving the heterogeneity of resource distribution and their local correlation coefficients, thus partitioning the region and ensuring that the formation mechanisms of wind and solar resources within each sub-region are more consistent. Based on this, a Long Short-Term Memory (LSTM) neural network model is independently trained for each homogeneous sub-region, enabling the model to focus more on learning the unique patterns of resource evolution over time under that specific environment. This allows the prediction model to accurately capture the intrinsic correlation between wind and solar resources and environmental factors in sub-regions, resulting in more accurate predictions for the target time period. It overcomes the shortcomings of traditional global unified models in representing local characteristics, and leverages the advantages of LSTM in capturing temporal dependencies. Thus, driven by both physical mechanisms and data, it overcomes the limitations of traditional prediction methods that ignore the complexity of terrain and the singularity of climate factors, making the capture of the fluctuation characteristics of wind and solar resources more accurate and robust, and achieving more reliable and accurate predictions of future wind and solar resources.

[0023] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating the wind and solar resource prediction method based on topographic and climatic characteristics provided in an embodiment of this application is shown. Figure 2 This paper shows a structural block diagram of a wind and solar resource prediction device based on topographic and climatic characteristics provided in an embodiment of this application. Figure 3A schematic diagram of the electronic structure of a computer device provided in an embodiment of this application is shown. Detailed Implementation

[0025] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0026] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0027] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “attached” to another element, it can be directly connected or attached to the other element, or there may be intermediate elements. Furthermore, “connected” or “attached” as used herein can include wireless connections or wireless interconnections. The term “and / or” as used herein includes all or any unit and all combinations of one or more associated listed items.

[0028] Exemplary embodiments according to this application will now be described in more detail with reference to the accompanying drawings. However, these exemplary embodiments may be implemented in many different forms and should not be construed as being limited to the embodiments set forth herein. It should be understood that these embodiments are provided so that the disclosure of this application is thorough and complete, and that the concept of these exemplary embodiments is fully conveyed to those skilled in the art.

[0029] This embodiment provides a method for predicting wind and solar resources based on topographic and climatic characteristics, such as... Figure 1 As shown, the method includes: Step 101: Obtain topographic data, historical climate data, and historical landscape resource data for the area to be analyzed.

[0030] Historical climate data includes temperature, humidity, wind speed, and wind direction. Historical wind and solar resource data includes irradiance, sunshine duration, wind speed, and wind power density. Topographic data includes slope and aspect values.

[0031] It is understandable that after the system obtains terrain data, historical climate data, and historical scenery resource data, it can preprocess them to improve data quality. Among them, the preprocessing includes: data cleaning, outlier removal, missing value filling, etc.

[0032] Specifically, the box plot method can be used to remove outliers. For example, for temperature, humidity, wind speed, and irradiance data, for daily climate data and scenery resource data, calculate the upper quartile QU, the lower quartile QL, and the interquartile range IQR. The outlier range: outlier < QL - 1.5IQR, or, outlier > QU + 1.5IQR. In addition, for humidity, wind speed, and irradiance data, a criterion can be set: outlier < 0. For wind direction data, data outside 0~360° are all outliers.

[0033] In an actual application scenario, step 101 specifically includes: collecting digital elevation data of the area to be analyzed, and historical climate data and historical scenery resource data of different stations in the area to be analyzed; extracting terrain data based on the digital elevation data.

[0034] Among them, the station is a meteorological station for collecting climate data and historical scenery resource data. Digital elevation data is elevation data at a spatial resolution.

[0035] Exemplarily, obtain elevation data with a spatial resolution of 30m×30m as digital elevation data. Obtain climate data and scenery resource data with a 15-minute resolution for at least twenty different stations in the area to be analyzed during the same period. Preprocess the collected terrain data, historical climate data, and historical scenery resource data, use the box plot method to remove outliers, use linear interpolation to fill in missing values, and unify the time steps of the climate data and scenery resource data, and save the preprocessed data as an Excel file for later use.

[0036] Among them. The sunshine duration calculation formula is: ; ; In the formula, SD is the sunshine duration, with the unit of hour; TSI is the irradiance; is the time interval. For the 15-minute resolution data here, should be 0.25 hours; T is the total duration. If calculating the annual sunshine duration, it is 8760×4 = 35040.

[0037] The wind power density calculation formula is: ; ; In the formula, P is the wind power density; v is the wind speed; ρ is the air density, p is the air pressure, Rs The specific gas constant is taken as 287.05 J / (kg·K); T is the absolute temperature.

[0038] For slope and aspect calculation: using 3×3 grid elevation data, calculate the slope and aspect data of the grid at the center. Let the elevation data in the nine grids be a, b, c, d, e, f, g, h, and i, and their positions be: ; The elevation of the grid to be calculated at the center is e, the elevation of the grid to the north is b, the elevation of the grid to the east is f, the east-west direction is the x-axis, the north-south direction is the y-axis, and the vertical direction is the z-axis.

[0039] The formula for calculating slope is: ; ; Slope = ; The formula for calculating slope aspect is: ; ; In the formula, ATAN2 is a two-parameter arctangent function that determines the quadrant based on the signs of x and y. aspect_temp is the initial azimuth angle, ranging from -180° to 180°, where 0° represents due east. However, the slope aspect is generally defined as due north, so aspect_temp needs to be converted to the slope aspect using the following formula: Slope aspect = ; Step 102: Based on historical climate data with the same spatial resolution as the terrain data, the first spatial distribution features of climate and terrain are generated through interpolation.

[0040] In this embodiment, the use of the same resolution eliminates matching biases caused by differences in data spatial scale, while interpolation fills in the gaps in climate data in sparse areas of meteorological stations. This transforms climate characteristics from discrete station data into continuous spatial data, forming a complete feature matrix that spatially corresponds one-to-one with the topographic data. This provides a highly consistent spatial feature basis for subsequent correlation analysis to accurately locate the relationship between wind and solar resources and environmental factors, and to scientifically zon according to the influencing mechanism. Consequently, it allows model training to better fit the actual regional situation, ultimately improving the reliability of prediction results and providing precise support for wind and solar energy development.

[0041] In practical application scenarios, step 102 specifically includes: creating a target grid based on the spatial resolution of the terrain data; fitting historical climate data collected from different stations to construct a semi-variogram model; calculating the weights of the target stations based on the semi-variogram model; calculating the climate element values ​​of the center points of the grid cells within the grid range based on the weights through weighted averaging; and using the climate element values, slope values, and aspect values ​​in the terrain data as the first spatial distribution features.

[0042] The semi-variogram model includes a spherical model, an exponential model, or a Gaussian model, and this application does not specifically limit the model. The target site is located within the grid range of the target grid. It can be understood that the grid range can be the range of a single grid cell or the range of multiple grid cells combined.

[0043] In this embodiment, a high spatial resolution target grid is constructed based on topographic data. A semi-variogram model is used to spatially fit historical climate data from different stations, and the weights of other known stations are scientifically calculated. Based on this weighted average method, the climate element values ​​at the grid center points are estimated to efficiently fill data gaps in sparse areas of the stations, generating continuous and accurate climate element values ​​at the grid cell center points. Finally, these climate elements are combined with slope and aspect in the terrain to form a comprehensive spatial distribution feature. This achieves the organic integration of multi-source environmental data while ensuring the spatial correspondence and integrity of the data, thus enhancing the quality of the spatial foundation data for wind and solar resource prediction.

[0044] Step 103: Use the global spatial autocorrelation analysis algorithm to determine the second spatial distribution characteristics of historical landscape resource data.

[0045] In this embodiment, spatial autocorrelation analysis is used to analyze historical wind and solar resource data, quantifying the clustering or dispersion of wind and solar resource distribution as a second spatial distribution characteristic. This reveals the spatial distribution patterns of resources under different terrain and climate conditions, as well as anomalous areas and trends, which helps improve the accuracy of resource assessment.

[0046] In practical application scenarios, step 103 specifically includes: mapping historical landscape resource data onto a target grid; calculating Moran's I index value of the historical landscape resource data using a global spatial autocorrelation analysis algorithm; and determining the second spatial distribution characteristics of the historical landscape resource data based on the comparison between the Moran's I index value and the index threshold.

[0047] The global spatial autocorrelation analysis algorithm is expressed as follows: ; In the formula, I This is Moran's I exponent value. x i ,x j For the historical landscape resource data in the i-th and j-th grid cells, This is the average value of historical landscape resource data. ω ij This is the spatial weight matrix. n is the number of elements in the spatial weight matrix.

[0048] In this embodiment, the Moran's I index is used to quantify the spatial aggregation or dispersion of wind and solar resources. By comparing the Moran's I index with a threshold, a Moran's I index value > the threshold indicates positive spatial autocorrelation, showing a spatial aggregation pattern; the larger the Moran's I index value, the stronger the aggregation. A Moran's I index value < 0 indicates negative spatial autocorrelation, showing a spatial dispersion / uniform pattern; the smaller the Moran's I index value, the stronger the dispersion. A Moran's I index value ≈ 0 indicates no spatial autocorrelation, indicating a random spatial distribution.

[0049] In one embodiment, after step 103, the wind and solar resource prediction method based on topographic and climatic characteristics further includes: generating a wind and solar resource distribution map and a topographic and climatic characteristic map based on a first spatial distribution feature and a second spatial distribution feature; and displaying the wind and solar resource distribution map and the topographic and climatic characteristic map.

[0050] In this embodiment, based on the spatial distribution of actually measured wind and solar resource values ​​and the clustering or dispersion patterns obtained through spatial autocorrelation analysis, a wind and solar resource distribution map and a topographic and climatic characteristic map are generated. This clearly reflects the richness of wind and solar resources and their spatial coupling relationship with topographic (e.g., slope, aspect) and climatic (e.g., temperature, humidity, wind speed) conditions, facilitating an understanding of the formation mechanism of resource distribution. It helps governments and enterprises to gain a deeper understanding of the potential of wind and solar resources and environmental impact factors, effectively achieving sustainable management and rational allocation of resources.

[0051] Step 104: Perform correlation analysis between historical landscape resource data and topographic data and historical climate data to determine the local correlation coefficient and key influencing factors between historical landscape resource data and environmental factors.

[0052] Key influencing factors include at least one environmental factor, which may be a topographic or climatic factor. The local correlation coefficient characterizes the relationship between topography or climate and wind and solar resources. A positive local correlation coefficient indicates a positive correlation between topographic or climatic data and wind and solar resource data; a negative local correlation coefficient indicates a negative correlation.

[0053] This embodiment can capture the local differences in the impact of topographic factors such as terrain undulation, slope, and aspect, as well as climatic factors such as temperature, humidity, and wind speed, on wind and solar resources. Furthermore, by identifying key influencing factors, it helps to clarify the dominant conditions for the formation and distribution of wind and solar resources in different regions, thereby improving the responsiveness and prediction accuracy to the spatial dynamic changes of wind and solar resources.

[0054] In one embodiment, step 104 involves performing correlation analysis between historical scenic resource data and topographic and historical climate data to determine the local correlation coefficients between historical scenic resource data and topographic and climatic conditions. Specifically, this includes: constructing a geographic weighted regression model based on historical scenic resource data, topographic data, and historical climate data; and solving the geographic weighted regression model to obtain the local correlation coefficients. This allows for accurate capture of the local correlation differences between scenic resources and environmental factors, avoiding the obscuring of regional specificity by global analysis.

[0055] The geographically weighted regression model is expressed as follows: y i = β 0( u i , v i )+ β 1( u i , v i ) x i + ε i ; In the formula, ( u i , v i Let be the coordinates of the i-th grid cell. x i For the wind and solar resource data in the i-th grid cell, y i For the terrain or climate data in the i-th grid cell, β 0( u i , v i ) represents the intercept of the i-th grid cell. β 1( u i , v i ) represents the local correlation coefficient of the i-th grid cell. ε i This is the error term.

[0056] In one embodiment, step 104 involves performing correlation analysis between historical landscape resource data and topographic data and historical climate data to determine the key influencing factors of the historical landscape resource data. Specifically, this includes: constructing a covariance matrix based on historical landscape resource data, topographic data, and historical climate data; performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues; calculating the variance contribution rate and cumulative variance contribution rate of environmental factors based on the eigenvalues; and identifying the environmental factors corresponding to eigenvalues ​​with a cumulative variance contribution rate greater than a contribution rate threshold as key influencing factors.

[0057] In this embodiment, multi-dimensional environmental factors are transformed into quantifiable variance contribution indicators through covariance matrix construction and eigenvalue decomposition. The key influencing factors screened by the cumulative variance contribution rate threshold screening mechanism can accurately eliminate secondary factors and provide independent and most representative input variables to focus on key influencing factors. This avoids redundant data interference while ensuring that no key factors are omitted.

[0058] For example, topographic data, historical climate data, and historical landscape data are standardized and formed into an n-row, p-column data matrix Z, where n is the number of samples, i.e., the number of grid cells in the studied area, and p is the number of variables, i.e., the number of environmental factors under study.

[0059] The covariance matrix is ​​constructed from the data matrix and represented as follows: ; In the formula, n is the number of samples; Z is the data matrix; and C is the covariance matrix.

[0060] Perform eigenvalue decomposition on the covariance matrix: C = V Λ V T ; In the formula, V Λ is the eigenvector matrix, where each column is an eigenvector representing the direction of the influencing factor; Λ is the eigenvalue matrix, where the off-diagonal elements are 0 and the diagonal elements are eigenvalues ​​representing the variance contribution of the influencing factor.

[0061] Sort the eigenvalues ​​from largest to smallest, and calculate the variance contribution rate and cumulative variance contribution rate for each influencing factor: Variance contribution rate = ; Cumulative variance contribution rate = ; In the formula, λ i Let be the i-th eigenvalue.

[0062] When the cumulative variance contribution rate reaches the required threshold, the influencing factor corresponding to that feature value can be selected as the key influencing factor.

[0063] In one embodiment, after step 104, the wind and solar resource prediction method based on topographic and climatic characteristics further includes: calculating the comprehensive impact value of key influencing factors on the distribution of wind and solar resources; and determining the impact of environmental factors on the distribution of wind and solar resources based on the comprehensive impact value.

[0064] In this embodiment, the combined impact of key influencing factors on the distribution of wind and solar resources is calculated, and the influence of environmental factors is determined based on this. This integrates the effects of multiple environmental variables on wind and solar resources, clarifying the dominant factors and their relative importance. This achieves a clear identification and spatial visualization of the dominant driving forces of resource distribution, helping to guide the scientific layout and efficient utilization of wind and solar resources.

[0065] For example, the eigenvalues ​​and eigenvectors obtained after eigenvalue decomposition of the covariance matrix are used to construct the loading matrix D. Based on the loading matrix, the specific data type corresponding to the principal components can be determined. ; In the formula, V is the eigenvector matrix; Λ is the eigenvalue matrix.

[0066] The overall influence is specifically defined as follows: Overall Influence = ; S=ZV ; ; In the formula, Z For data matrices; V The eigenvector matrix, S This is the score matrix of influencing factors; S i Let i be the score of the i-th influencing factor. λ i Let i be the i-th eigenvalue; ω i Let be the weight of the i-th influencing factor.

[0067] It is evident that the higher the variance contribution rate and cumulative variance contribution rate, the greater the overall influence, indicating that the influencing factor has a greater impact on the distribution of wind and solar resource data.

[0068] Step 105: Based on the first spatial distribution characteristics, the second spatial distribution characteristics, the local correlation coefficient, and the key influencing factors, the region to be analyzed is divided into multiple sub-regions.

[0069] Within the same sub-region, the wind and solar resource data of all locations are governed by the same influencing factors.

[0070] Step 106: Train the long short-term memory neural network model based on the historical landscape resource data generated within the sub-region to construct a landscape resource prediction model for the sub-region.

[0071] For example, wind speed and irradiance are selected as output features, and topographic and climate data that significantly influence wind speed and irradiance are selected as input features for the model. The required training and testing data are preprocessed. The preprocessed historical data is divided into training, validation, and testing sets. The LSTM model is trained using the training set, the validation set is used to adjust hyperparameters, and the testing set is used to evaluate model performance. Specifically, root mean square error (RMSE) and mean absolute error (MAE) are used as model performance evaluation metrics, and their calculation formulas are as follows: ; .

[0072] Step 107: Predict wind and solar resource data for the target period using the wind and solar resource prediction model.

[0073] The wind and solar resource prediction method based on topographic and climatic characteristics provided in this application accurately captures the topographic-climate coupling characteristics (first spatial distribution characteristics) and the inherent aggregation patterns of wind and solar resources (second spatial distribution characteristics) by interpolating historical climate data to a spatial resolution consistent with topographic data and combining it with global spatial autocorrelation analysis. It utilizes correlation analysis to identify key environmental factors driving the heterogeneity of resource distribution and their local correlation coefficients, thus partitioning the region and ensuring that the formation mechanism of wind and solar resources within each sub-region tends to be consistent. Based on this, a Long Short-Term Memory (LSTM) neural network model is independently trained for each homogeneous sub-region, enabling the model to focus more on learning the unique patterns of resource evolution over time under that specific environment. This allows the prediction model to accurately capture the intrinsic correlation between wind and solar resources and environmental factors in the sub-region, resulting in target-period prediction data that is closer to reality. It overcomes the shortcomings of traditional global unified models in representing local characteristics, and leverages the advantages of LSTM in capturing temporal dependencies. Thus, driven by both physical mechanisms and data, it overcomes the limitations of traditional prediction methods that ignore the complexity of terrain and the singularity of climate factors, making the capture of the fluctuation characteristics of wind and solar resources more accurate and robust, and achieving more reliable and accurate predictions of future wind and solar resources.

[0074] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0075] The wind and solar resource prediction method based on terrain and climate characteristics provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0076] Furthermore, such as Figure 2 As shown, as a specific implementation of the above-mentioned wind and solar resource prediction method based on topographic and climatic characteristics, this application provides a wind and solar resource prediction device 200 based on topographic and climatic characteristics. The wind and solar resource prediction device 200 based on topographic and climatic characteristics includes: a data acquisition module 201, a data processing module 202, a model training module 203, and a prediction module 204.

[0077] Among them, the data acquisition module 201 is used to acquire topographic data, historical climate data and historical landscape resource data of the area to be analyzed; The data processing module 202 is used to generate a first spatial distribution feature of climate and topography based on historical climate data with the same spatial resolution as the topographic data through interpolation; and to determine a second spatial distribution feature of historical landscape resource data using a global spatial autocorrelation analysis algorithm; and to perform correlation analysis between the historical landscape resource data and the topographic data and the historical climate data respectively to determine the local correlation coefficient and key influencing factors between the historical landscape resource data and environmental factors, wherein the key influencing factors include at least one environmental factor; and to divide the area to be analyzed into multiple sub-regions based on the first spatial distribution feature, the second spatial distribution feature, the local correlation coefficient, and the key influencing factors, wherein the landscape resource data of all points in the same sub-region are dominated by the same influencing factor; The model training module 203 is used to train the long short-term memory neural network model based on the historical landscape resource data generated in the sub-region, and to build a landscape resource prediction model for the sub-region. The prediction module 204 is used to predict wind and solar resource data for a target period through a wind and solar resource prediction model.

[0078] Furthermore, the data acquisition module 201 is specifically used to collect digital elevation data of the area to be analyzed, as well as historical climate data and historical wind and light resource data of different stations within the area to be analyzed. The historical climate data includes temperature, humidity, wind speed, and wind direction, while the historical wind and light resource data includes irradiance, sunshine duration, wind speed, and wind power density. Based on the digital elevation data, topographic data is extracted, including slope and aspect values.

[0079] Further, the data processing module 202 is specifically used to create a target grid based on the spatial resolution of the terrain data; fit historical climate data collected from different stations to construct a semi-variogram model, wherein the semi-variogram model includes a spherical model, an exponential model, or a Gaussian model; calculate the weights of the target stations based on the semi-variogram model, wherein the target stations are located within the grid range of the target grid; calculate the climate element values ​​of the center points of the grid cells within the grid range by weighted averaging based on the weights; and use the climate element values, slope values, and aspect values ​​in the terrain data as the first spatial distribution features.

[0080] Further, the data processing module 202 is specifically used to map historical landscape resource data onto a target grid; calculate the Moran's I index value of the historical landscape resource data using a global spatial autocorrelation analysis algorithm; and determine the second spatial distribution characteristics of the historical landscape resource data based on the comparison between the Moran's I index value and the index threshold; wherein, the global spatial autocorrelation analysis algorithm is expressed as: In the formula, I This is Moran's I exponent value. x i , x j For the historical landscape resource data in the i-th and j-th grid cells, This is the average value of historical landscape resource data. ω ij This is the spatial weight matrix. n is the number of elements in the spatial weight matrix.

[0081] Furthermore, the data processing module 202 is specifically used to construct a geographic weighted regression model based on historical landscape resource data, topographic data, and historical climate data; solve the geographic weighted regression model to obtain local correlation coefficients; wherein, the basic form of the geographic weighted regression model is: y i = β 0( u i , v i )+ β 1( u i ,v i ) x i + ε i In the formula, ( u i , v i Let be the coordinates of the i-th grid cell. x i For the wind and solar resource data in the i-th grid cell, y i For the terrain or climate data in the i-th grid cell, β 0( u i , v i ) represents the intercept of the i-th grid cell. β 1( u i , v i ) represents the local correlation coefficient of the i-th grid cell. ε i This is the error term.

[0082] Furthermore, the data processing module 202 is specifically used to construct a covariance matrix based on historical wind and light resource data, topographic data, and historical climate data; perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues; calculate the variance contribution rate and cumulative variance contribution rate of environmental factors based on the eigenvalues; and take the environmental factors corresponding to the eigenvalues ​​with a cumulative variance contribution rate greater than the contribution rate threshold as key influencing factors.

[0083] Furthermore, the data processing module 202 is also used to calculate the comprehensive impact value of key influencing factors on the distribution of wind and solar resources; and to determine the impact of environmental factors on the distribution of wind and solar resources based on the comprehensive impact value.

[0084] Furthermore, the data processing module 202 is specifically used to generate a wind and solar resource distribution map and a topographic and climatic feature map based on the first spatial distribution features and the second spatial distribution features; the wind and solar resource prediction device 200 based on topographic and climatic features also includes: a display module (not shown in the figure) for displaying the wind and solar resource distribution map and the topographic and climatic feature map.

[0085] Specific limitations regarding the wind and solar resource forecasting device based on topographic and climatic characteristics can be found in the limitations of the wind and solar resource forecasting method based on topographic and climatic characteristics mentioned above, and will not be repeated here. Each module in the aforementioned wind and solar resource forecasting device based on topographic and climatic characteristics can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0086] Based on the above, Figure 1 Accordingly, embodiments of this application also provide a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method. Figure 1 The method for predicting wind and solar resources based on topographic and climatic characteristics is shown.

[0087] Based on this understanding, the technical solution of this application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or portable hard drive), and includes several instructions to cause a computer device (such as a personal computer, server, or network device) to execute the methods described in the various implementation scenarios of this application.

[0088] Based on the above, Figure 1 The method shown, and Figure 2 The virtual device embodiment shown is designed to achieve the above objectives, such as... Figure 3 As shown in the figure, this application embodiment also provides a computer device 300, which includes a processor 301 and a memory 302. The memory 302 stores a program or instructions that can run on the processor 301. When the program or instructions are executed by the processor 301, they implement the above-mentioned... Figure 1 The method for predicting wind and solar resources based on topographic and climatic characteristics is shown.

[0089] The memory 302 can be used to store software programs and various data. The memory 302 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 302 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 302 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0090] Processor 301 may include one or more processing units; optionally, processor 301 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 301.

[0091] Computer equipment can specifically include personal computers, servers, network devices, etc.

[0092] Optionally, the computer device may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Bluetooth interfaces, Wi-Fi interfaces), etc.

[0093] Those skilled in the art will understand that the computer device structure provided in this embodiment does not constitute a limitation on the computer device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0094] Through the above description of the implementation methods, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms, or by hardware to acquire topographic data, historical climate data, and historical scenic resource data of the area to be analyzed; based on historical climate data with the same spatial resolution as the topographic data, the first spatial distribution characteristics of climate and topography are generated by interpolation processing; the second spatial distribution characteristics of historical scenic resource data are determined by using a global spatial autocorrelation analysis algorithm; the historical scenic resource data are correlated with the topographic data and historical climate data respectively to determine the local correlation coefficient and key influencing factors between the historical scenic resource data and environmental factors, wherein the key influencing factors include at least one environmental factor; based on the first spatial distribution characteristics, the second spatial distribution characteristics, the local correlation coefficient, and the key influencing factors, the area to be analyzed is divided into multiple sub-regions, wherein the scenic resource data of all points in the same sub-region are dominated by the same influencing factors; the long short-term memory neural network model is trained based on the historical scenic resource data generated in the sub-region to construct a scenic resource prediction model for the sub-region; and the scenic resource prediction model is used to predict the scenic resource data for the target period. This application's embodiments, by interpolating historical climate data to a spatial resolution consistent with topographic data and combining it with global spatial autocorrelation analysis, accurately capture the topographic-climate coupling characteristics (first spatial distribution characteristics) and the inherent aggregation patterns of wind and solar resources (second spatial distribution characteristics) of resource distribution. Correlation analysis is used to identify key environmental factors driving the heterogeneity of resource distribution and their local correlation coefficients, thus partitioning the region and ensuring that the formation mechanisms of wind and solar resources within each sub-region are consistent. Based on this, a Long Short-Term Memory (LSTM) neural network model is independently trained for each homogeneous sub-region, enabling the model to focus more on learning the unique patterns of resource evolution over time under that specific environment. This allows the prediction model to accurately capture the intrinsic correlation between wind and solar resources and environmental factors in sub-regions, resulting in more realistic target-period prediction data. This approach overcomes the shortcomings of traditional global unified models in representing local characteristics while leveraging the advantages of LSTM in capturing temporal dependencies. Driven by both physical mechanisms and data, it overcomes the limitations of traditional prediction methods that ignore topographic complexity and the singularity of climate factors, making the capture of wind and solar resource fluctuation characteristics more accurate and robust, and achieving more reliable and accurate predictions of future wind and solar resources.

[0095] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing this application. Those skilled in the art will understand that the modules in the apparatus of the embodiment can be distributed within the apparatus of the embodiment as described, or can be modified to be located in one or more apparatuses different from this embodiment. The modules of the above-described embodiment can be combined into one module, or further divided into multiple sub-modules.

[0096] The serial numbers in this application are for descriptive purposes only and do not represent the superiority or inferiority of any particular implementation scenario. The above disclosures are merely a few specific implementation scenarios of this application; however, this application is not limited thereto, and any variations conceived by those skilled in the art should fall within the protection scope of this application.

Claims

1. A method for predicting wind and solar resources based on topographic and climatic characteristics, characterized in that, The method includes: Acquire topographic data, historical climate data, and historical landscape data of the area to be analyzed; Based on the historical climate data with the same spatial resolution as the terrain data, a first spatial distribution feature of climate and terrain is generated through interpolation. The second spatial distribution characteristics of the historical landscape resource data were determined using a global spatial autocorrelation analysis algorithm. The historical landscape resource data is correlated with the topographic data and the historical climate data to determine the local correlation coefficient and key influencing factors between the historical landscape resource data and environmental factors, wherein the key influencing factors include at least one environmental factor. Based on the first spatial distribution characteristics, the second spatial distribution characteristics, the local correlation coefficient, and the key influencing factors, the area to be analyzed is divided into multiple sub-regions, wherein the wind and solar resource data of all points in the same sub-region are dominated by the same influencing factors. Based on the historical landscape resource data generated within the sub-region, a long short-term memory neural network model is trained to construct a landscape resource prediction model for the sub-region. The wind and solar resource prediction model is used to predict wind and solar resource data for the target period.

2. The wind and solar resource prediction method based on topographic and climatic characteristics according to claim 1, characterized in that, The acquisition of topographic data, historical climate data, and wind and solar resource data of the area to be analyzed includes: Collect digital elevation data of the area to be analyzed, as well as historical climate data and historical wind and light resource data of different stations in the area to be analyzed. The historical climate data includes temperature, humidity, wind speed and wind direction, and the historical wind and light resource data includes irradiance, sunshine duration, wind speed and wind power density. Topographic data is extracted from digital elevation data, including slope and aspect values.

3. The wind and solar resource prediction method based on topographic and climatic characteristics according to claim 1, characterized in that, The historical climate data, based on the same spatial resolution as the terrain data, is used to generate a first spatial distribution feature of climate and terrain through interpolation processing, including: Create a target grid based on the spatial resolution of the terrain data; The historical climate data collected from different stations are fitted to construct a semi-variogram model, wherein the semi-variogram model includes a spherical model, an exponential model, or a Gaussian model. The weight of the target station is calculated based on the semi-variogram model, wherein the target station is located within the grid range of the target grid; Based on the weights, the climate element values ​​of the center point of the grid cell within the grid range are calculated by weighted average. The climate element values, slope values, and aspect values ​​in the terrain data are used as the first spatial distribution features; The method of determining the second spatial distribution characteristics of the historical landscape resource data using a global spatial autocorrelation analysis algorithm includes: Map the historical landscape resource data onto the target grid; The Moran's I index value of the historical landscape resource data was calculated using a global spatial autocorrelation analysis algorithm. Based on the comparison between the Moran's I index value and the index threshold, the second spatial distribution characteristics of the historical landscape resource data are determined. The global spatial autocorrelation analysis algorithm is expressed as follows: ; In the formula, I This is Moran's I exponent value. x i , x j For the historical landscape resource data in the i-th and j-th grid cells, This is the average value of historical landscape resource data. ω ij This is the spatial weight matrix. n is the number of elements in the spatial weight matrix.

4. The wind and solar resource prediction method based on topographic and climatic characteristics according to claim 3, characterized in that, The step of performing correlation analysis between the historical landscape resource data and the topographic data and the historical climate data to determine the local correlation coefficient between the historical landscape resource data and the topographic and climatic conditions includes: A geographic weighted regression model is constructed based on the historical landscape resource data, the topographic data, and the historical climate data; Solve the geographically weighted regression model to obtain the local correlation coefficient; The geographically weighted regression model is expressed as follows: y i = β 0( u i , v i )+ β 1( u i , v i ) x i + ε i ; In the formula, ( u i , v i Let be the coordinates of the i-th grid cell. x i For the wind and solar resource data in the i-th grid cell, y i For the terrain or climate data in the i-th grid cell, β 0( u i , v i ) represents the intercept of the i-th grid cell. β 1( u i , v i ) represents the local correlation coefficient of the i-th grid cell. ε i This is the error term.

5. The wind and solar resource prediction method based on topographic and climatic characteristics according to claim 1, characterized in that, The step involves performing correlation analysis between the historical landscape resource data and the topographic data and the historical climate data, respectively, to determine the key influencing factors of the historical landscape resource data, including: Based on the historical landscape resource data, the topographic data, and the historical climate data, a covariance matrix is ​​constructed. The covariance matrix is ​​subjected to eigenvalue decomposition to obtain eigenvalues; The variance contribution rate and cumulative variance contribution rate of the environmental factors are calculated based on the aforementioned eigenvalues. The environmental factors corresponding to the feature values ​​whose cumulative variance contribution rate is greater than the contribution rate threshold are taken as the key influencing factors.

6. The wind and solar resource prediction method based on topographic and climatic characteristics according to claim 1, characterized in that, The method further includes: Calculate the comprehensive impact of the aforementioned key influencing factors on the distribution of wind and solar resources; The impact of environmental factors on the distribution of wind and solar resources is determined based on the comprehensive impact value.

7. The wind and solar resource prediction method based on topographic and climatic characteristics according to any one of claims 1 to 6, characterized in that, The method further includes: Based on the first spatial distribution characteristics and the second spatial distribution characteristics, a wind and solar resource distribution map and a topographic and climatic characteristic map are generated; The map showing the distribution of the wind and solar resources and the map showing the topographic and climatic characteristics are displayed.

8. A wind and solar resource prediction device based on topographic and climatic characteristics, characterized in that, The device includes: The data acquisition module is used to acquire topographic data, historical climate data, and historical landscape resource data of the area to be analyzed. The data processing module is configured to generate a first spatial distribution feature of climate and topography based on historical climate data with the same spatial resolution as the topographic data, through interpolation processing; and, The second spatial distribution characteristics of the historical landscape resource data were determined using a global spatial autocorrelation analysis algorithm; and, The historical scenic resource data is correlated with the topographic data and the historical climate data to determine the local correlation coefficients and key influencing factors between the historical scenic resource data and environmental factors, wherein the key influencing factors include at least one environmental factor; and, Based on the first spatial distribution characteristics, the second spatial distribution characteristics, the local correlation coefficient, and the key influencing factors, the area to be analyzed is divided into multiple sub-regions, wherein the wind and solar resource data of all points in the same sub-region are dominated by the same influencing factors. The model training module is used to train the long short-term memory neural network model based on the historical landscape resource data generated in the sub-region, and to construct a landscape resource prediction model for the sub-region. The prediction module is used to predict wind and solar resource data for a target period using the wind and solar resource prediction model.

9. A readable storage medium having a program or instructions stored thereon, characterized in that, When the program or instructions are executed by the processor, they implement the wind and solar resource prediction method based on terrain and climate characteristics as described in any one of claims 1 to 7.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the wind and solar resource prediction method based on topographic and climatic characteristics as described in any one of claims 1 to 7.

Images