A wind field downscaling simulation prediction system and method based on machine learning

Abstract

The present invention provides a machine learning-based wind farm downscaling simulation and prediction system and method, wherein the system includes: a first forecast data acquisition subsystem for acquiring low-resolution model wind farm grid forecast data; a live data acquisition subsystem for acquiring live data; a downscaling model construction subsystem for constructing a downscaling model based on machine learning technology; and a second forecast data acquisition subsystem for performing downscaling corrections based on the downscaling model, the low-resolution model wind farm grid forecast data, and live data, to output high-resolution model wind farm grid forecast data. The machine learning-based wind farm downscaling simulation and prediction system and method of the present invention optimize and adjust physical parameters in the WRF model by combining the output of the hourly 5-kilometer resolution WRF model. Historical data and real-time monitoring data are used to dynamically adjust the parameters of the WRF model, resulting in a more refined wind farm forecast and a smaller computational load.

Description

Technical Field

[0001] The present invention relates to the field of machine learning technology, and in particular to a wind field downscaling simulation and prediction system and method based on machine learning. Background Art

[0002] Currently, most wind forecast products are derived from regional or global-scale numerical weather prediction models. However, dynamical-based forecasts inherently suffer from initial condition biases and inherent model uncertainties, hindering the ability of these models to capture small-scale atmospheric features and microscale turbulent motion. Accurate wind forecasts over complex terrain have long been a challenge and a key focus in wind energy and meteorological research. While attempts to use dynamical downscaling methods to obtain higher-resolution wind products and correct for wind speed biases have achieved some success in specific case studies, they currently cannot meet the demands of refined forecasts due to the high computational resources required.

[0003] The invention patent with application number: CN202011237572.3 discloses an automated operation system for mesoscale wind energy resource analysis, including parameter configuration script file, mesoscale model WRF pre-processing WPS operation script file, mesoscale model WRF operation script, data assimilation script file, model post-processing data assimilation script file, model product generation LRPP script file, and operation control script file; it avoids the complex job process control software such as rocoto, ECflow, Airflow commonly used in meteorological business, and uses simple bash scripts to implement job submission, operation, monitoring, and compensation functions; all parameter configurations are set in the parameter configuration script file, and the remaining scripts adopt a modular approach to realize arbitrary operation; it realizes the division of the regional range with a large number of grid points into several relatively small grid point areas for mesoscale simulation, and performs regional splicing in the product stage, but the above-mentioned existing technology only realizes the automated operation of model simulation, and does not evaluate or improve or enhance the model simulation effect.

[0004] In addition, the hourly grid-corrected forecast products generated by the forecast correction technical solutions in other existing technologies cannot be completely consistent with the extreme value grid-corrected forecast products. Secondly, the error direction of the hourly numerical model products at the start of forecast time zero and the hourly multi-source grid fusion products may be opposite to the error direction of the hourly numerical model products at future forecast times. If the correction scheme is not appropriate, the error will increase. In addition, dynamic downscaling consumes huge computing resources because all grid points at all forecast times need to be modeled, which greatly reduces the efficiency of rolling correction of numerical model products and temporarily cannot meet the needs of refined forecasting.

[0005] In view of this, there is an urgent need for a wind field downscaling simulation and prediction system and method based on machine learning to at least address the above-mentioned deficiencies. Summary of the Invention

[0006] One objective of this invention is to provide a machine learning-based wind downscaling simulation and forecasting system and method. This system optimizes and adjusts physical parameters within the WRF model using the hourly 5-kilometer resolution output, achieving a mapping from low-resolution to high-resolution. Historical data and real-time monitoring data are used to dynamically adjust WRF model parameters, helping the model better simulate local wind field variations, resulting in more refined wind forecasts and less computational effort.

[0007] An embodiment of the present invention provides a wind field downscaling simulation and prediction system based on machine learning, comprising:

[0008] The first forecast data acquisition subsystem is used to obtain 5km*5km model wind field grid forecast data;

[0009] A live data acquisition subsystem, used to acquire live data;

[0010] Downscaling model construction subsystem, used to build downscaling models based on machine learning technology;

[0011] The second forecast data acquisition subsystem is used to perform downscaling correction based on the 5km*5km model wind field grid forecast data and actual data based on the downscaling model, and output 1km*1km model wind field grid forecast data.

[0012] Preferably, the first forecast data acquisition subsystem acquires 5km*5km model wind field grid forecast data, including:

[0013] Configure simulation domain parameters;

[0014] After completing the configuration of the simulation domain parameters, run the WPS program;

[0015] After the WPS program is executed, the WRF model is used to perform meteorological simulation;

[0016] When the WRF model performs meteorological simulations, data assimilation is performed;

[0017] After data assimilation, UPP / LRPP is run to obtain the output 5km*5km model wind field grid forecast data.

[0018] Preferably, the downscaling model construction subsystem constructs a downscaling model based on machine learning technology, including:

[0019] Build a downscaling model based on gradient boosting decision tree;

[0020] The input of the downscaling model is the wind field features extracted from the WRF model output. Through the wind field features, the GBDT model learns the mapping relationship between the low-resolution model output and the high-resolution wind field observation data. The basic form of the model prediction is:

[0021]

[0022] Among them, F(x) is the final model prediction output, M is the total number of decision trees, and h m (x) is the mth decision tree, α m is the learning rate of m decision trees, and x is the input wind field feature;

[0023] Among them, the GBDT model learns the model by minimizing the loss function, and the loss function is:

[0024]

[0025] Among them, y i is the actual observed wind speed of the i-th data sample, F(x i ) is the wind speed predicted by the model for the i-th data sample, where n is the number of data samples;

[0026] The GBDT model fits a new decision tree by using negative gradients. The formula for calculating the negative gradient in the mth round is as follows:

[0027]

[0028] After fitting the new decision tree, the overall model is updated according to the update formula, which is specifically:

[0029] F m (x) = F m-1 (x)+α m h m (x)

[0030] When the preset number of trees M is reached or the negative gradient converges, the GBDT model completes learning and obtains the final downscaling model.

[0031] Preferably, the live data acquisition subsystem acquires live data, including:

[0032] Get the set of live data monitoring nodes;

[0033] Determining a first monitoring site of a live data monitoring node;

[0034] Obtaining a monitoring value of a live data monitoring node corresponding to a first monitoring site;

[0035] If the number of monitoring values of the live data monitoring node corresponding to the first monitoring site is greater than or equal to the preset target number, the corresponding first monitoring site is used as the second monitoring site; otherwise, the first monitoring site is used as the third monitoring site;

[0036] Based on the preset outlier elimination rule, the outliers of the second monitoring site are eliminated, and the average value of the monitoring values of the remaining live data monitoring nodes is calculated, and the average value is used as the live data of the second monitoring site;

[0037] Calculate the simulated value of the third monitoring station based on the average value of the second monitoring station;

[0038] Attempt to obtain a monitoring value of a live data monitoring node at a third monitoring site, and if the acquisition attempt is successful, calculate a deviation between the monitoring value of the corresponding live data monitoring node and a simulated value;

[0039] If the deviation value is less than or equal to the preset deviation value threshold, the monitoring value of the corresponding live data monitoring node is used as the live data of the third monitoring site;

[0040] If the deviation values are all greater than the preset deviation value threshold, the simulated values are used as the actual data of the third monitoring site;

[0041] Calculating the simulated value of the third monitoring station according to the average value of the second monitoring station includes:

[0042] Construct a spatial wind field model based on the wind field characteristics of the first monitoring station;

[0043] Construct the input matrix based on the average value of the second monitoring station;

[0044] Determine the dynamic simulation model of the spatial wind field based on the spatial wind field model and spatial wind field mechanism knowledge information;

[0045] Input the input matrix into the spatial wind field dynamic simulation model to obtain the output matrix;

[0046] According to the simulation result interpretation template corresponding to the output matrix, the simulation value of the third monitoring station is determined.

[0047] An embodiment of the present invention provides a wind field downscaling simulation and prediction system based on machine learning, further comprising:

[0048] Environmental early warning subsystem, used to provide environmental early warning based on 1km*1km model wind field grid forecast data;

[0049] The environmental warning subsystem provides environmental warnings based on 1km*1km wind grid forecast data, including:

[0050] According to the simulation domain parameters, the distribution information of wind farm-related pollution sources is obtained;

[0051] Extracting wind farm-associated pollution source characteristics based on a wind farm-associated pollution source characterization template and distribution information of wind farm-associated pollution sources, wherein the wind farm-associated pollution source characteristics include: type, location, and mobility characteristics of wind farm-associated pollution sources;

[0052] Based on the diffusion description model, the pollution source diffusion description is determined according to the characteristics of wind field-associated pollution sources and the 1km*1km model wind field grid forecast data;

[0053] Obtain the pollution level evaluation template corresponding to the pollution source;

[0054] Predict the pollution level in the pre-diffusion area based on the pollution source diffusion description and pollution level evaluation template;

[0055] Obtaining the preset pollution level index of the pre-diffusion area;

[0056] If the pollution level is greater than the pollution level index, an environmental warning is generated for the corresponding pre-diffusion area.

[0057] An embodiment of the present invention provides a wind field downscaling simulation prediction method based on machine learning, comprising:

[0058] Step 1: Obtain 5km*5km model wind field grid forecast data;

[0059] Step 2: Get live data;

[0060] Step 3: Build a downscaling model based on machine learning technology;

[0061] Step 4: Based on the downscaling model, downscaling correction is performed according to the 5km*5km model wind field grid forecast data and the actual data, and the 1km*1km model wind field grid forecast data is output.

[0062] Preferably, step 1: obtaining 5km*5km model wind field grid forecast data includes:

[0063] Configure simulation domain parameters;

[0064] After completing the configuration of the simulation domain parameters, run the WPS program;

[0065] After the WPS program is executed, the WRF model is used to perform meteorological simulation;

[0066] When the WRF model performs meteorological simulations, data assimilation is performed;

[0067] After data assimilation, UPP / LRPP is run to obtain the output 5km*5km model wind field grid forecast data.

[0068] Preferably, step 3: constructing a downscaling model based on machine learning technology includes:

[0069] Build a downscaling model based on gradient boosting decision tree;

[0070] The input of the downscaling model is the wind field features extracted from the WRF model output. Through the wind field features, the GBDT model learns the mapping relationship between the low-resolution model output and the high-resolution wind field observation data. The basic form of the model prediction is:

[0071]

[0072] Among them, F(x) is the final model prediction output, M is the total number of decision trees, and h m (x) is the mth decision tree, α m is the learning rate of m decision trees, and x is the input wind field feature;

[0073] Among them, the GBDT model learns the model by minimizing the loss function, and the loss function is:

[0074]

[0075] Among them, y i is the actual observed wind speed of the i-th data sample, F(x i ) is the wind speed predicted by the model for the i-th data sample, where n is the number of data samples;

[0076] The GBDT model fits a new decision tree by using negative gradients. The formula for calculating the negative gradient in the mth round is as follows:

[0077]

[0078] After fitting the new decision tree, the overall model is updated according to the update formula, which is specifically:

[0079] F m (x) = F m-1 (x)+α m h m (x)

[0080] When the preset number of trees M is reached or the negative gradient converges, the GBDT model completes learning and obtains the final downscaling model.

[0081] Preferably, step 2: obtaining live data includes:

[0082] Get the set of live data monitoring nodes;

[0083] Determining a first monitoring site of a live data monitoring node;

[0084] Obtaining a monitoring value of a live data monitoring node corresponding to a first monitoring site;

[0085] If the number of monitoring values of the live data monitoring node corresponding to the first monitoring site is greater than or equal to the preset target number, the corresponding first monitoring site is used as the second monitoring site; otherwise, the first monitoring site is used as the third monitoring site;

[0086] Based on the preset outlier elimination rule, the outliers of the second monitoring site are eliminated, and the average value of the monitoring values of the remaining live data monitoring nodes is calculated, and the average value is used as the live data of the second monitoring site;

[0087] Calculate the simulated value of the third monitoring station based on the average value of the second monitoring station;

[0088] Attempt to obtain a monitoring value of a live data monitoring node at a third monitoring site, and if the acquisition attempt is successful, calculate a deviation between the monitoring value of the corresponding live data monitoring node and a simulated value;

[0089] If the deviation value is less than or equal to the preset deviation value threshold, the monitoring value of the corresponding live data monitoring node is used as the live data of the third monitoring site;

[0090] If the deviation values are all greater than the preset deviation value threshold, the simulated values are used as the actual data of the third monitoring site;

[0091] Calculating the simulated value of the third monitoring station according to the average value of the second monitoring station includes:

[0092] Construct a spatial wind field model based on the wind field characteristics of the first monitoring station;

[0093] Construct the input matrix based on the average value of the second monitoring station;

[0094] Determine the dynamic simulation model of the spatial wind field based on the spatial wind field model and spatial wind field mechanism knowledge information;

[0095] Input the input matrix into the spatial wind field dynamic simulation model to obtain the output matrix;

[0096] According to the simulation result interpretation template corresponding to the output matrix, the simulation value of the third monitoring station is determined.

[0097] An embodiment of the present invention provides a wind field downscaling simulation prediction method based on machine learning, further comprising:

[0098] Provide environmental warning based on 1km*1km model wind field grid forecast data;

[0099] Among them, environmental early warning is carried out based on 1km*1km model wind field grid forecast data, including:

[0100] According to the simulation domain parameters, the distribution information of wind farm-related pollution sources is obtained;

[0101] Extracting wind farm-associated pollution source characteristics based on a wind farm-associated pollution source characterization template and distribution information of wind farm-associated pollution sources, wherein the wind farm-associated pollution source characteristics include: type, location, and mobility characteristics of wind farm-associated pollution sources;

[0102] Based on the diffusion description model, the pollution source diffusion description is determined according to the characteristics of wind field-associated pollution sources and the 1km*1km model wind field grid forecast data;

[0103] Obtain the pollution level evaluation template corresponding to the pollution source;

[0104] Predict the pollution level in the pre-diffusion area based on the pollution source diffusion description and pollution level evaluation template;

[0105] Obtaining the preset pollution level index of the pre-diffusion area;

[0106] If the pollution level is greater than the pollution level index, an environmental warning is generated for the corresponding pre-diffusion area.

[0107] The beneficial effects of the present invention are:

[0108] This method optimizes and adjusts the physical parameters in the WRF model by combining the hourly 5-kilometer resolution of the WRF model output, achieving a mapping from low-resolution to high-resolution. Historical data and real-time monitoring data are used to dynamically adjust the WRF model parameters, helping the model better simulate local wind field variations, resulting in more refined wind forecasts and less computational effort.

[0109] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in this application document.

[0110] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0111] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0112] Figure 1 Schematic diagram of a wind field downscaling simulation and prediction system based on machine learning in an embodiment of the present invention;

[0113] Figure 2 Schematic diagram of a wind field downscaling simulation and prediction method based on machine learning in an embodiment of the present invention. DETAILED DESCRIPTION

[0114] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0115] The embodiment of the present invention provides a wind field downscaling simulation and prediction system based on machine learning, such as Figure 1 Shown, including:

[0116] The first forecast data acquisition subsystem 1 is used to obtain 5km*5km model wind field grid forecast data;

[0117] Live data acquisition subsystem 2, used to acquire live data;

[0118] Downscaling model construction subsystem 3, used to construct a downscaling model based on machine learning technology;

[0119] The second forecast data acquisition subsystem 4 is used to perform downscaling correction based on the 5km*5km model wind field grid forecast data and the actual data based on the downscaling model, and output the 1km*1km model wind field grid forecast data;

[0120] The first forecast data acquisition subsystem acquires 5km*5km model wind field grid forecast data, including:

[0121] Configure simulation domain parameters; where simulation domain parameters are: parameters of the defined wind farm simulation area;

[0122] After completing the configuration of the simulation domain parameters, run the WPS program;

[0123] After the WPS program is executed, the WRF model is used to perform meteorological simulation;

[0124] When the WRF model performs meteorological simulations, data assimilation is performed;

[0125] After data assimilation, UPP / LRPP is run to obtain the output 5km*5km model wind field grid forecast data.

[0126] The working principle and beneficial effects of the above technical solution are:

[0127] To improve the accuracy of the WRF model's wind field forecasts, a machine learning-based downscaling correction method was introduced, with the Gradient Boosting Data Transfer (GBDT) as the core algorithm. The input to the downscaling model mainly includes a variety of wind-related features extracted from the WRF model output, including temperature, humidity, surface type, and other information, which helps the model better understand the spatiotemporal distribution of wind fields under different conditions. The output of the WRF model is used as the input to the model, and the wind field data from the observation station is used as the label / target output. The Gradient Boosting Data Transfer (GBDT) is selected to establish a downscaling model, and the machine learning model is trained to learn the mapping relationship from coarse resolution to high resolution. For the trained model, an independent historical dataset is used to verify the model and evaluate the model's predictive performance.

[0128] In the process of building a downscaling model based on the gradient boosted decision tree (GBDT), the model input is mainly the wind field-related features extracted from the WRF model output. Through the input features, the GBDT model learns the mapping relationship between the low-resolution model output and the high-resolution wind field observation data. The basic form of the model prediction is:

[0129]

[0130] Among them, F(x) is the final model prediction output, M is the total number of decision trees, and h m (x) is the mth decision tree, x is the input wind field feature, α m The weights (or learning rates) of the m decision trees control the impact of each tree on the final prediction;

[0131] The model is learned by minimizing the loss function. Typically, GBDT uses the squared error loss function, which is defined as follows:

[0132]

[0133] Among them, y i is the actual observed wind speed of the ith data sample (station monitoring data), F(x i ) is the wind speed predicted by the model for the i-th data sample, where n is the number of data samples;

[0134] GBDT fits a new decision tree by using negative gradients. The gradient of each round is calculated as the negative gradient of the current model with respect to the loss function. For the squared error loss function, the residual (negative gradient) of the mth round is calculated as follows:

[0135]

[0136] The update rule of each round of GBDT is to fit a new decision tree h based on the residual m (x), and then update the overall model by the following formula:

[0137] F m (x) = F m-1 (x)+α m h m (x)

[0138] During the GBDT downscaling process, different features are used to learn the spatiotemporal distribution of wind speed through a decision tree. Each tree constructs nodes based on the splitting of different features. The splitting feature for each node is selected by maximizing the reduction in prediction error. Feature selection is performed based on information gain, and then the decision tree is recursively constructed. The feature with the highest information gain value is considered the optimal feature. In other words, the greater the information gain, the higher it should be placed in the decision tree.

[0139] In this way, GBDT learns the mapping relationship from low-resolution model output to high-resolution wind field observation data.

[0140] Finally, the model is further optimized through an iterative process. Initial results are evaluated using root mean square error (RMSE) and bias, followed by multiple rounds of iteration. After each round, the model's output is evaluated and further adjustments are made based on the evaluation until the preset number of trees, M, is reached or the residuals converge. Multiple rounds of training and adjustments are repeated to continuously improve the forecast results. As the number of model iterations increases, the wind speed within the region can achieve a more natural transition. By gradually fitting the residuals and iterating through multiple rounds, the model's fitting capabilities are optimized, and by learning from the spatiotemporal characteristics of historical data, the model gradually approaches the true observed values.

[0141] During validation, we used the RMSE (root mean square error) and Bias (bias) metrics to measure the model's prediction performance. If the model validation results indicated a high prediction error (e.g., an excessively large RMSE or a systematic bias in the Bias), we further adjusted the model by modifying feature selection based on information gain and removing variables with no significant correlation to wind speed forecasts to further improve model accuracy.

[0142] This paper constructs a 1-kilometer-resolution wind forecast model based on WRF model simulation results combined with machine learning methods. Based on this wind forecast model, an automated wind forecast simulation and forecasting system, controlled by a Linux-based bash script, is developed. This system automates the operation of the wind forecast system, facilitating scientific research and business development applications. By combining the hourly 5-kilometer-resolution WRF model output, the physical parameters in the WRF model (such as meteorological elements and topography) are optimized and adjusted to achieve a mapping from low to high resolution. Historical data and real-time monitoring data are used to dynamically adjust the WRF model parameters, helping the model better simulate local wind field variations, refine wind forecasts, and reduce computational complexity.

[0143] In one embodiment, the live data acquisition subsystem acquires live data, including:

[0144] Obtaining a set of live data monitoring nodes; wherein the live data monitoring nodes are network nodes of different types of live data monitoring parties, such as: a globally distributed ground weather station network, a local automated weather monitoring station;

[0145] Determine a first monitoring site of the live data monitoring node; wherein the first monitoring site is: a meteorological monitoring point of the live data monitoring node;

[0146] Obtaining a monitoring value of a live data monitoring node corresponding to a first monitoring site; wherein the number of monitoring values of the live data monitoring node corresponding to the first monitoring site may be one or more; the monitoring value of the live data monitoring node is a meteorological measurement value of the live data monitoring node corresponding to the first monitoring site, such as wind speed and precipitation;

[0147] If the number of monitoring values of the live data monitoring node corresponding to the first monitoring site is greater than or equal to a preset target number, the corresponding first monitoring site is used as the second monitoring site; otherwise, the first monitoring site is used as the third monitoring site; wherein the preset target number is manually pre-set, for example: 3;

[0148] Based on a preset outlier elimination rule, the outliers of the second monitoring site are eliminated, and the average value of the monitoring values of the remaining live data monitoring nodes is calculated, and the average value is used as the live data of the second monitoring site; wherein, the outliers of the second monitoring site are eliminated based on the preset outlier elimination rule, including: traversing the monitoring values of the live data monitoring nodes of the second monitoring site, calculating the difference data between the monitoring value of the live data monitoring node being traversed and the monitoring values of other live data monitoring nodes corresponding to the second monitoring site, if the data characteristics of the difference data meet the outlier difference data characteristics (each corresponding calculated difference is greater than a preset difference threshold), then the monitoring value of the live data monitoring node being traversed is used as an outlier;

[0149] Calculate the simulated value of the third monitoring station based on the average value of the second monitoring station;

[0150] Attempt to obtain a monitoring value of a live data monitoring node at a third monitoring site, and if the acquisition attempt is successful, calculate a deviation between the monitoring value of the corresponding live data monitoring node and a simulated value;

[0151] If the deviation value is less than or equal to a preset deviation value threshold, the monitoring value of the corresponding live data monitoring node is used as the live data of the third monitoring site; wherein the preset deviation value threshold is manually pre-set;

[0152] If the deviation values are all greater than the preset deviation value threshold, the simulated values are used as the actual data of the third monitoring site;

[0153] Calculating the simulated value of the third monitoring station according to the average value of the second monitoring station includes:

[0154] Constructing a spatial wind field model based on the wind field characteristics of the first monitoring station; wherein the spatial wind field model is: a three-dimensional model of the simulation area constructed based on the wind field characteristics;

[0155] According to the average value of the second monitoring station, the input matrix is constructed; the input matrix is: the wind speed description matrix of the known simulation points in the spatial wind field model;

[0156] Determine a spatial wind field dynamic simulation model based on the spatial wind field model and spatial wind field mechanism knowledge information; wherein the spatial wind field dynamic simulation model is: a mathematical model that describes and simulates the distribution and changes of wind in space;

[0157] Input the input matrix into the spatial wind field dynamic simulation model to obtain the output matrix; wherein the output matrix is: the wind speed description matrix of all simulation points in the spatial wind field model;

[0158] According to the simulation result interpretation template corresponding to the output matrix, the simulation value of the third monitoring station is determined.

[0159] The working principle and beneficial effects of the above technical solution are:

[0160] The present invention connects to live data monitoring nodes of different node types to obtain the live data monitoring node monitoring value corresponding to the first monitoring site. One first monitoring site may correspond to one or more live data monitoring node monitoring values. The monitoring methods of live data monitoring nodes of different node types are different. Therefore, in order to further improve the accuracy of the measurement value, if the number of live data monitoring node monitoring values corresponding to the first monitoring site is greater than or equal to a preset target number, it will be used as the second monitoring site.

[0161] Traversing the monitoring values of the live data monitoring nodes of the second monitoring site, calculating the difference data between the monitoring value of the live data monitoring node being traversed and the monitoring values of other live data monitoring nodes corresponding to the second monitoring site, if each corresponding calculated difference is greater than a preset difference threshold, treating the monitoring value of the live data monitoring node being traversed as an outlier, eliminating the outlier of the second monitoring site, and calculating the average value of the monitoring values of the remaining live data monitoring nodes;

[0162] A spatial wind field model is constructed based on the wind field characteristics of the first monitoring station, and then a wind speed description matrix of the known simulation points in the spatial wind field model is constructed based on the average value of the second monitoring station; a spatial wind field dynamic simulation model is determined based on the spatial wind field model and the spatial wind field mechanism knowledge information. The spatial wind field dynamic simulation model can simulate the wind field based on the wind data of each known point. The description rules of the output matrix are the same as those of the input matrix. Each matrix element position corresponds to a point in the simulation area, and the element value at the matrix element position is the wind speed and wind direction; the simulation result interpretation template is a template for interpreting the output matrix.

[0163] An attempt is made to obtain the monitoring value of the live data monitoring node of the third monitoring site. If the attempt is successful, the deviation value between the monitoring value of the corresponding live data monitoring node and the simulation value is calculated. If the deviation value is less than or equal to the preset deviation value threshold, the monitoring value of the corresponding live data monitoring node is used as the live data of the third monitoring site; if the deviation values are all greater than the preset deviation value threshold, the simulation value is used as the live data of the third monitoring site, thereby improving the reliability and accuracy of obtaining the live data of the third monitoring site with fewer monitoring data sources.

[0164] An embodiment of the present invention provides a wind field downscaling simulation and prediction system based on machine learning, further comprising:

[0165] Environmental early warning subsystem, used to provide environmental early warning based on 1km*1km model wind field grid forecast data;

[0166] The environmental warning subsystem provides environmental warnings based on 1km*1km wind grid forecast data, including:

[0167] Obtain wind farm-associated pollution source distribution information based on simulation domain parameters. This information is the pollution source distribution information for the actual area corresponding to the simulation domain parameters, such as where chemical plants and thermal power plants are located.

[0168] Extracting wind farm-associated pollution source characteristics based on a wind farm-associated pollution source characterization template and wind farm-associated pollution source distribution information, wherein the wind farm-associated pollution source characterization template is a template for extracting wind farm-associated pollution source characteristics against the wind farm-associated pollution source distribution information, for example, an information extraction template for extracting wind farm-associated pollution source type information from the wind farm-associated pollution source distribution information; the wind farm-associated pollution source characteristics include: wind farm-associated pollution source type (e.g., PM10, PM2.5), location, and movement characteristic information (e.g., particle velocity);

[0169] Based on the diffusion description model, the pollution source diffusion description is determined according to the characteristics of wind farm-associated pollution sources and the 1km*1km model wind farm grid forecast data. The diffusion description model is constructed through machine learning based on the pollution diffusion law description information described by pollution control personnel. The pollution source diffusion description is: the pollution source diffusion description semantics determined by combining the 1km*1km model wind farm grid forecast data and the characteristics of wind farm-associated pollution sources.

[0170] Obtaining a pollution level evaluation template corresponding to the pollution source; wherein the pollution level evaluation template includes: a preset description of the pollutant type, a description of the pollution behavior, and a description of the pollutant level;

[0171] The pollution level of the pre-diffusion area is predicted based on the pollution source diffusion description and the pollution level evaluation template. When predicting the pollution level of the pre-diffusion area based on the pollution source diffusion description and the pollution level evaluation template, if the pollutant type described in the pollution source diffusion description is consistent with the pollutant type described in the pollution level evaluation template, the pollution behavior similarity between the pollution behavior described in the pollution source diffusion description and the pollution behavior described in the pollution level evaluation template is calculated, and the pollutant level with the greatest pollution behavior similarity is used as the predicted pollution level. The pre-diffusion area is determined based on the geographical parameters described in the pollution source diffusion description.

[0172] Obtaining the preset pollution level index of the pre-diffusion area;

[0173] If the pollution level is greater than the pollution level index, an environmental warning is generated for the corresponding pre-diffusion area.

[0174] The working principle and beneficial effects of the above technical solution are:

[0175] The present invention obtains the distribution information of wind farm-associated pollution sources, and characterizes the distribution information of wind farm-associated pollution sources to obtain the type, location and mobility characteristic information of wind farm-associated pollution sources; introduces a diffusion description model constructed by machine learning based on the pollution diffusion law description information described by pollution control personnel, and determines the pollution source diffusion description according to the wind farm-associated pollution source characteristics and 1km*1km model wind farm grid forecast data; then, the pollution source diffusion description is compared with the pollution level evaluation template to predict the pollution level of the pre-diffusion area; if the pollution level is greater than the pollution level index preset in the pre-diffusion area, an environmental warning is generated, thereby improving the warning accuracy and timeliness.

[0176] The embodiment of the present invention provides a wind field downscaling simulation prediction method based on machine learning, such as Figure 2 Shown, including:

[0177] Step 1: Obtain 5km*5km model wind field grid forecast data;

[0178] Step 2: Get live data;

[0179] Step 3: Build a downscaling model based on machine learning technology;

[0180] Step 4: Based on the downscaling model, downscaling correction is performed according to the 5km*5km model wind field grid forecast data and the actual data, and the 1km*1km model wind field grid forecast data is output.

[0181] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A wind field downscaling simulation and prediction system based on machine learning, characterized in that: include: The first forecast data acquisition subsystem is used to obtain 5km*5km model wind field grid forecast data; A live data acquisition subsystem, used to acquire live data; Downscaling model construction subsystem, used to build downscaling models based on machine learning technology; The second forecast data acquisition subsystem is used to perform downscaling correction based on the 5km*5km model wind field grid forecast data and the actual data based on the downscaling model, and output the 1km*1km model wind field grid forecast data; The downscaling model construction subsystem builds a downscaling model based on machine learning technology, including: Build a downscaling model based on gradient boosting decision tree; The input of the downscaling model is the wind field features extracted from the WRF model output. Through the wind field features, the GBDT model learns the mapping relationship between the low-resolution model output and the high-resolution wind field observation data. The basic form of the model prediction is: in, is the final model prediction output, is the total number of decision trees, It is A decision tree, yes The learning rate of the decision tree, is the input wind field characteristics; Among them, the GBDT model learns the model by minimizing the loss function, and the loss function is: in, It is The actual observed wind speed of the data sample is It is The wind speed predicted by the model for data samples is is the number of data samples, It is Wind field characteristics of data samples; The GBDT model fits a new decision tree using negative gradients. The formula for calculating the round negative gradient is as follows: After fitting the new decision tree, the overall model is updated according to the update formula, which is specifically: in, It is The wheel model predicts wind speed, It is The previous round The wheel model predicts wind speed; When the preset number of trees is reached Or when the negative gradient converges, the GBDT model completes learning and obtains the final downscaling model.

2. The wind field downscaling simulation and prediction system based on machine learning according to claim 1, characterized in that: The first forecast data acquisition subsystem acquires 5km*5km model wind field grid forecast data, including: Configure simulation domain parameters; After completing the configuration of the simulation domain parameters, run the WPS program; After the WPS program is executed, the WRF model is used to perform meteorological simulation; When the WRF model performs meteorological simulations, data assimilation is performed; After data assimilation, UPP / LRPP is run to obtain the output 5km*5km model wind field grid forecast data.

3. The wind field downscaling simulation and prediction system based on machine learning according to claim 1, characterized in that: The live data acquisition subsystem acquires live data, including: Get the set of live data monitoring nodes; Determining a first monitoring site of a live data monitoring node; Obtaining a monitoring value of a live data monitoring node corresponding to a first monitoring site; If the number of monitoring values of the live data monitoring node corresponding to the first monitoring site is greater than or equal to the preset target number, the corresponding first monitoring site is used as the second monitoring site; otherwise, the first monitoring site is used as the third monitoring site; Based on the preset outlier elimination rule, the outliers of the second monitoring site are eliminated, and the average value of the monitoring values of the remaining live data monitoring nodes is calculated, and the average value is used as the live data of the second monitoring site; Calculate the simulated value of the third monitoring station based on the average value of the second monitoring station; Attempt to obtain a monitoring value of a live data monitoring node at a third monitoring site, and if the acquisition attempt is successful, calculate a deviation between the monitoring value of the corresponding live data monitoring node and a simulated value; If the deviation value is less than or equal to the preset deviation value threshold, the monitoring value of the corresponding live data monitoring node is used as the live data of the third monitoring site; If the deviation values are all greater than the preset deviation value threshold, the simulated values are used as the actual data of the third monitoring site; Calculating the simulated value of the third monitoring station according to the average value of the second monitoring station includes: Construct a spatial wind field model based on the wind field characteristics of the first monitoring station; Construct the input matrix based on the average value of the second monitoring station; Determine the dynamic simulation model of the spatial wind field based on the spatial wind field model and spatial wind field mechanism knowledge information; Input the input matrix into the spatial wind field dynamic simulation model to obtain the output matrix; According to the simulation result interpretation template corresponding to the output matrix, the simulation value of the third monitoring station is determined.

4. The wind field downscaling simulation and prediction system based on machine learning according to claim 1, characterized in that: Also includes: Environmental early warning subsystem, used to provide environmental early warning based on 1km*1km model wind field grid forecast data; The environmental warning subsystem provides environmental warnings based on 1km*1km wind grid forecast data, including: According to the simulation domain parameters, the distribution information of wind farm-related pollution sources is obtained; Extracting wind farm-associated pollution source characteristics based on a wind farm-associated pollution source characterization template and distribution information of wind farm-associated pollution sources, wherein the wind farm-associated pollution source characteristics include: type, location, and mobility characteristics of wind farm-associated pollution sources; Based on the diffusion description model, the pollution source diffusion description is determined according to the characteristics of wind field-associated pollution sources and the 1km*1km model wind field grid forecast data; Obtain the pollution level evaluation template corresponding to the pollution source; Predict the pollution level in the pre-diffusion area based on the pollution source diffusion description and pollution level evaluation template; Obtaining the preset pollution level index of the pre-diffusion area; If the pollution level is greater than the pollution level index, an environmental warning is generated for the corresponding pre-diffusion area.

5. A wind field downscaling simulation prediction method based on machine learning, characterized in that: include: Step 1: Obtain 5km*5km model wind field grid forecast data; Step 2: Get live data; Step 3: Build a downscaling model based on machine learning technology; Step 4: Based on the downscaling model, perform downscaling correction based on the 5km*5km model wind field grid forecast data and the actual data, and output the 1km*1km model wind field grid forecast data; Step 3: Building a downscaling model based on machine learning technology includes: Build a downscaling model based on gradient boosting decision tree; The input of the downscaling model is the wind field features extracted from the WRF model output. Through the wind field features, the GBDT model learns the mapping relationship between the low-resolution model output and the high-resolution wind field observation data. The basic form of the model prediction is: in, is the final model prediction output, is the total number of decision trees, It is A decision tree, yes The learning rate of the decision tree, is the input wind field characteristics; Among them, the GBDT model learns the model by minimizing the loss function, and the loss function is: in, It is The actual observed wind speed of the data sample is It is The wind speed predicted by the model for data samples is is the number of data samples, It is Wind field characteristics of data samples; The GBDT model fits a new decision tree using negative gradients. The formula for calculating the round negative gradient is as follows: After fitting the new decision tree, the overall model is updated according to the update formula, which is specifically: in, It is The wheel model predicts wind speed, It is The previous round The wheel model predicts wind speed; When the preset number of trees is reached Or when the negative gradient converges, the GBDT model completes learning and obtains the final downscaling model.

6. The wind field downscaling simulation prediction method based on machine learning according to claim 5, characterized in that: Step 1: Obtain 5km*5km model wind field grid forecast data, including: Configure simulation domain parameters; After completing the configuration of the simulation domain parameters, run the WPS program; After the WPS program is executed, the WRF model is used to perform meteorological simulation; When the WRF model performs meteorological simulations, data assimilation is performed; After data assimilation, UPP / LRPP is run to obtain the output 5km*5km model wind field grid forecast data.

7. The wind field downscaling simulation prediction method based on machine learning according to claim 5, characterized in that: Step 2: Obtain live data, including: Get the set of live data monitoring nodes; Determining a first monitoring site of a live data monitoring node; Obtaining a monitoring value of a live data monitoring node corresponding to a first monitoring site; If the number of monitoring values of the live data monitoring node corresponding to the first monitoring site is greater than or equal to the preset target number, the corresponding first monitoring site is used as the second monitoring site; otherwise, the first monitoring site is used as the third monitoring site; Based on the preset outlier elimination rule, the outliers of the second monitoring site are eliminated, and the average value of the monitoring values of the remaining live data monitoring nodes is calculated, and the average value is used as the live data of the second monitoring site; Calculate the simulated value of the third monitoring station based on the average value of the second monitoring station; Attempt to obtain a monitoring value of a live data monitoring node at a third monitoring site, and if the acquisition attempt is successful, calculate a deviation between the monitoring value of the corresponding live data monitoring node and a simulated value; If the deviation value is less than or equal to the preset deviation value threshold, the monitoring value of the corresponding live data monitoring node is used as the live data of the third monitoring site; If the deviation values are all greater than the preset deviation value threshold, the simulated values are used as the actual data of the third monitoring site; Calculating the simulated value of the third monitoring station according to the average value of the second monitoring station includes: Construct a spatial wind field model based on the wind field characteristics of the first monitoring station; Construct the input matrix based on the average value of the second monitoring station; Determine the dynamic simulation model of the spatial wind field based on the spatial wind field model and spatial wind field mechanism knowledge information; Input the input matrix into the spatial wind field dynamic simulation model to obtain the output matrix; According to the simulation result interpretation template corresponding to the output matrix, the simulation value of the third monitoring station is determined.

8. The wind field downscaling simulation prediction method based on machine learning according to claim 5, characterized in that: Also includes: Provide environmental warning based on 1km*1km model wind field grid forecast data; Among them, environmental early warning is carried out based on 1km*1km model wind field grid forecast data, including: According to the simulation domain parameters, the distribution information of wind farm-related pollution sources is obtained; Extracting wind farm-associated pollution source characteristics based on a wind farm-associated pollution source characterization template and distribution information of wind farm-associated pollution sources, wherein the wind farm-associated pollution source characteristics include: type, location, and mobility characteristics of wind farm-associated pollution sources; Based on the diffusion description model, the pollution source diffusion description is determined according to the characteristics of wind field-associated pollution sources and the 1km*1km model wind field grid forecast data; Obtain the pollution level evaluation template corresponding to the pollution source; Predict the pollution level in the pre-diffusion area based on the pollution source diffusion description and pollution level evaluation template; Obtaining the preset pollution level index of the pre-diffusion area; If the pollution level is greater than the pollution level index, an environmental warning is generated for the corresponding pre-diffusion area.

Images