53 results about "Numerical weather prediction models" patented technology

The invention discloses a photovoltaic power generation power prediction method and system based on multi-source data fusion. The method comprises the steps of obtaining historical operation data of a target photovoltaic power station and historical meteorological data corresponding to the historical operation data; based on the historical operation data and the historical meteorological data, constructing and training a historical deviation mode correction downscaling model, and correcting future coarse resolution meteorological forecast data provided by a numerical weather forecast model to obtain refined meteorological forecast data of a target photovoltaic power station site scale; on the basis of the refined meteorological prediction data, utilizing a physical-statistical coupling prediction model to predict the future generation power of the target photovoltaic power station; according to the historical deviation mode correction downscaling model, a targeted correction function is established by analyzing a systematic deviation mode between a theoretical prediction value and an actual observation value in historical data, and conversion from coarse resolution prediction to site scale microscopic meteorology is realized, so that the photovoltaic power generation power prediction precision is improved.

The invention relates to a meteorological deduction method and device fusing physical constraints and a neural network, and the method comprises the steps: obtaining multi-source meteorological data, and constructing a spatial-temporal feature input tensor; the spatio-temporal feature input tensor is subjected to standardization processing and then input into a deep learning network model, and a future weather prediction result is obtained; the model extracts time sequence evolution features and space attention features through a neural network module and a space attention module respectively, and integrates the time sequence evolution features and the space attention features in a splicing form; for a forecast task of a future gamma day, a deep learning network model and a physical mode are adopted for prediction respectively, and a splicing time point is determined according to an error minimum principle, so that splicing of prediction results is carried out; when the physical mode is used for prediction, the improved regional numerical weather prediction model is used as a basis, atmospheric basic equation sets are integrated, and weather prediction at future moments is carried out. Compared with the prior art, the method has the advantages that the atmospheric physical law and data driving advantages are fused, and the extreme weather prediction precision and stability are improved.

The invention relates to the technical field of data assimilation processing, in particular to a WRFDA assimilation method, system and device based on GIIRS data. The method comprises the following steps: acquiring GIIRS data, extracting data from the GIIRS data, and merging and checking the data to obtain checked GIIRS observation information; performing deviation correction on the background field data of the numerical weather forecasting mode by using an RTTOV rapid radiation transmission mode to obtain simulation data after stable deviation correction; performing cloud pollution screening on the GIIRS observation information after inspection and the simulation data after deviation correction to obtain GIIRS observation information without cloud pollution; wRFDA numerical assimilation is carried out on the GIIRS observation information without cloud pollution, an initial field file is obtained, and the initial field file is used for adjusting and optimizing an output weather forecast result. According to the method, a more accurate initialization file is obtained, and the simulation accuracy of the typhoon precipitation area is more accurately improved.

The invention discloses a solar power generation prediction method, device and equipment. The method comprises the following steps: acquiring current irradiance data of a meteorological station in a current irradiation period; the current irradiance data are input into an irradiance prediction model, next irradiance data of the next irradiation period output by the irradiance prediction model is obtained, and the irradiance prediction model is obtained through model optimization based on a land assimilation model and a numerical weather prediction model in combination with machine learning optimization adjustment logic; and according to the next irradiance data, the weather forecast data and the ambient air data, predicting the power generation output power of solar power generation. Through the method, the irradiance prediction model obtained by combining the land assimilation model and the numerical weather prediction model with the machine learning optimization adjustment logic optimization model is used for irradiance prediction, the accuracy of irradiance prediction is improved, and the power generation output power of solar power generation can be predicted more accurately.

The invention relates to the technical field of aerospace meteorology, and particularly discloses a domestic numerical weather forecast mode-based evaporation waveguide height determination method, which comprises the following steps of: obtaining meteorological coupling data output by a domestic numerical weather forecast mode CMA-MESO; determining parameters according to the meteorological coupling data and a turbulent flux algorithm COARE; constructing a temperature vertical profile and a specific humidity vertical profile according to the parameters, the Monin-Obchhoff similarity theory and an NPS model; constructing a modified refractive index profile according to the temperature vertical profile and the specific humidity vertical profile; and determining the height of the evaporation waveguide according to the height corresponding to the lowest point of the corrected refractive index profile. The method is suitable for determining the evaporation waveguide height in a domestic business meteorological mode.

The invention discloses a distributed ground-based radar atmospheric refraction error calculation method for celestial body observation. According to the method, a local numerical weather forecast model is corrected by using real-time surface meteorological parameters, atmospheric refractive index profile data containing elevation meteorological information is obtained, a geometric elevation angle of a celestial body target is taken as a standard, and a neutral atmospheric refractive index error is searched in combination with a corrected data source and a ray tracing method, so that the atmospheric refractive index is obtained. And finally, neutral atmospheric refraction error calculation and correction are realized. The effectiveness of the algorithm is verified through simulation.

The invention belongs to the technical field of agricultural remote sensing and monitoring, and provides an agricultural medium-short-term water shortage intelligent estimation method based on remote sensing, which comprises the steps of data collection and preprocessing, crop spatial distribution and current growth cycle extraction in a research area, medium-short-term meteorological element prediction based on a WRF model, and medium-short-term crop evapotranspiration prediction and medium-short-term agricultural water deficit dynamic intelligent estimation are realized. According to the method, the time-space continuous monitoring advantage of the remote sensing image is fully utilized, and rapid identification and early warning of the water shortage condition of the crops in a large range are achieved; meanwhile, by means of simulation of a numerical weather forecasting model on complex meteorological conditions, the future weather trend is effectively predicted, and a scientific basis is provided for agricultural water resource management.

The invention discloses a weather forecasting method and system, a readable storage medium and a program product. The weather forecasting method comprises the following steps: downloading a global analysis field and a global forecasting field; operating an artificial intelligence meteorological large model, and outputting global forecast data based on the global analysis field; operating a numerical weather forecast model, and generating a regional meteorological field based on the global forecast field; interpolating the global forecast data into the regional meteorological field to generate an interpolated regional meteorological field; operating the numerical weather forecast model, and generating an initial field and a boundary field of a corresponding region based on the interpolated regional meteorological field; and operating the numerical weather forecasting model, and performing ensemble forecasting based on the initial field and the boundary field. Therefore, the artificial intelligence large model can be applied in the numerical mode, the advantages of the two models are combined, and the accuracy of weather forecast is improved.

The invention discloses an algorithm and a system based on a wind-solar power joint prediction model, and relates to the technical field of new energy power systems, the prediction power of a physical model is obtained by combining the output of a small-scale numerical weather prediction model in an initialization stage through a photovoltaic model and a Betz limit model, and the prediction power of the physical model is obtained in a stable stage. CNN-LSTM is adopted to predict photovoltaic power, TCN-GRU is adopted to predict wind power, similarity scores of a time sequence feature vector and a space feature vector are calculated through an attention mechanism, weights of the time sequence feature vector and the space feature vector are dynamically adjusted, weighted prediction results are fused to obtain predicted power of a neural network layer, and the predicted power of the neural network layer is obtained. And dynamically determining a weight ratio of the physical model to the neural network layer based on the prediction error, and generating a final wind-solar power prediction value. According to the invention, a cooperation mechanism of the physical model and the neural network is constructed, and the accuracy of wind-solar power joint prediction is improved.

The invention discloses a multi-source real-time correction method and device based on a GFDL-VortexTracker recognition result, and relates to the field of meteorological data processing, and the method comprises the steps: S1, obtaining mode data and multi-source observation data of an output field of a numerical weather prediction mode; s2, performing initial recognition on the mode data of the output field through a GFDL-VortexTracker algorithm to obtain a mode priori recognition result; s3, performing strong constraint correction on the authoritative live path data by using the mode prior recognition result to obtain a strong constraint correction result; s4, performing high-frequency observation compensation on the authoritative live path data after strong constraint correction by using a radar jigsaw and a satellite cloud picture to obtain a high-frequency observation compensation result; s5, fusing the mode prior recognition result, the strong constraint correction result and the high-frequency observation compensation result to generate a real-time correction result; according to the method, the accuracy of key parameters such as the center position, the strong wind radius and the asymmetric structure is remarkably improved.

The application discloses a large-scale wind farm mesoscale numerical simulation method considering wind turbine interference. The method first obtains the basic data of the target wind farm wind turbine; numerical modeling is carried out on each wind turbine by using the basic data; then in the numerical modeling, the wind turbine sub-grid interference model is added, and the atmospheric inflow conditions of each wind turbine in the same grid are corrected, so that the accuracy of the large-scale wind farm mesoscale numerical simulation is improved. Finally, the modeling results are coupled to the numerical weather prediction model to carry out numerical simulation research of the large-scale wind farm. Compared with the traditional wind farm mesoscale numerical modeling method, the modeling method of the application has better accuracy and robustness, and is more suitable for research on the interference in the large-scale wind farm and the wake characteristics of the whole farm.

The application relates to the technical field of digital processing, and discloses a wind farm wind measurement tower site selection method and system, which comprises the following steps: acquiring meteorological live conditions, grid prediction and occultation observation data of each spatial grid point in a candidate area, and calculating a terrain disturbance factor; fusing the multi-source meteorological data by the terrain disturbance factor weighting, forming a comprehensive wind field data set, inputting a numerical weather prediction model, and iteratively optimizing the terrain disturbance factor as a physical constraint to obtain wind field prediction data in space-time distribution; and screening grid points meeting preset conditions from the wind field prediction data as wind measurement tower candidate positions. The wind farm wind measurement tower site selection method and system solve the problem of inaccurate wind measurement tower site selection caused by insufficient consideration of the mechanical disturbance and turbulence effect of terrain on the wind field, and simultaneously improve the meteorological accuracy and reliability of the wind measurement tower site selection.

The invention discloses a photovoltaic snow covering depth and power loss forecasting method and system based on multi-source data fusion, and belongs to the technical field of photovoltaic power forecasting. The problems of high-precision accumulated snow influence assessment, short-term risk early warning and power loss quantitative prediction of a photovoltaic system in cold and alpine regions are solved. The method comprises the following steps: selecting three numerical weather forecasting modes, namely a global forecasting system operated by the National Environmental Forecasting Center, a wind energy and solar energy forecasting system of the China Meteorological Administration and a unified mode weather forecast of the British Meteorological Administration, acquiring weather forecasting data, performing unified space-time interpolation, abnormal value correction and unit conversion, and then performing set averaging to obtain a set average value; ensemble forecast data is obtained; based on a temperature-irradiance condition and a friction force mechanism, an accumulated snow covering model is constructed, a photovoltaic panel snow covering range and photovoltaic power loss are obtained, early warning information of snow covering time, duration and power loss is generated through matching of station longitude and latitude and national grid forecasting, and photovoltaic snow covering depth and power loss forecasting based on multi-source data fusion is completed.

The invention relates to an optimal interpolation assimilation method for adaptive observation station space distribution. The method comprises the following steps: (1) obtaining a background error covariance matrix, an observation error covariance matrix, an optimal weight matrix, a kth observation station and a background field; (2) carrying out first iteration on the background field, and carrying out weighted averaging to obtain an observation operator of initial iteration at a grid point in the background field; (3) according to the observation operator of the initial iteration, calculating to obtain a background field of the first-generation iteration; iteration is carried out in the same manner until the absolute value of the observation increment is smaller than a small quantity, iteration is stopped, and at the moment, an observation operator dynamically changing along with the space is obtained and used for calculation of an analysis field. The method is simple, high-precision atmosphere reanalysis data can be effectively constructed, the precision of the initial field of the numerical weather forecasting mode is improved, and the method is suitable for construction or reconstruction of data sets in the fields of meteorology, new energy, aviation ocean and the like.

The application relates to the field of tropical cyclone tracking, in particular to a tropical cyclone automatic tracking method based on a relative threshold value. The method comprises the following steps: obtaining meteorological historical data through a numerical weather prediction model, obtaining relative vorticity and warm core intensity of historical tropical cyclones according to the meteorological historical data; collecting historical tropical cyclone data, calculating relative thresholds of the relative vorticity and the warm core intensity according to the historical tropical cyclone data; obtaining meteorological data at different times according to the numerical weather prediction model, obtaining candidate areas at different times according to the relative thresholds and the meteorological data; obtaining multiple sets of longitude and latitude data and intensity data of tropical cyclone centers at different times according to the candidate areas at different times; and obtaining path and intensity information of each tropical cyclone changing over time by using a clustering algorithm according to the longitude and latitude data and the intensity data. The application solves the problems of low tracking efficiency and poor precision of multiple tropical cyclones in the prior art.

The invention discloses a background field data difference evaluation method and a related device, and the method comprises the steps: obtaining background field data which are multi-source meteorological observation data related to a power grid and data needed by a numerical weather prediction model; inputting the background field data into a multi-element comprehensive evaluation model considering magnitude difference, similarity and deviation of elements to obtain a comprehensive evaluation index; and evaluating the difference performance of the background field data according to the comprehensive evaluation index. According to the method and the related device, the difference performance of the background field data can be comprehensively and quantitatively evaluated.

The present application relates to assimilation processing technical field, especially to a kind of WRFDA assimilation method, system and device based on GIIRS data.The method includes obtaining GIIRS data, extracting data therefrom, merging, checking data, obtaining GIIRS observation information after checking;Using RTTOV fast radiation transfer mode, the background field data of numerical weather prediction model is corrected to obtain stable deviation corrected simulation data;After checking GIIRS observation information and deviation corrected simulation data, cloud pollution screening is carried out, and GIIRS observation information without cloud pollution is obtained;WRFDA numerical assimilation is carried out to GIIRS observation information without cloud pollution, and initial field file is obtained, and initial field file is used to adjust and optimize the output weather forecast result.The present application is more accurate by obtaining more accurate initialization file, and the simulation accuracy of typhoon precipitation area is improved.

This invention discloses a method, system, equipment, and medium for predicting wind turbine output under icing conditions. The method includes the following steps: acquiring historical operating data of wind turbines in a target wind farm during the icing period; processing the historical operating data using a wind power calculation method to obtain wind power data; matching the wind power data with WRF simulation forecast data along the time dimension to form a training dataset; training the training dataset using a machine learning algorithm to obtain a wind speed optimization model; obtaining optimized wind speed data; and substituting the optimized wind speed data with the temperature and air pressure from the WRF simulation forecast data into the wind power calculation formula to obtain the wind turbine output prediction result. This invention combines the WRF numerical weather prediction model with N sets of algorithms to optimize the wind speed data output by the WRF model, capturing the nonlinear relationship between wind speed and wind power under icing conditions, and improving the accuracy of wind turbine output prediction.

The application discloses a boundary level grid physical constraint variational assimilation method embedded in a deep neural network, comprising: establishing a momentum equation containing a boundary level grid turbulent friction term, wherein the boundary layer turbulent friction term is simulated through a deep neural network; and constructing a weak constraint term of a variational assimilation framework cost function with the momentum equation; training the deep neural network with a dataset constructed from historical numerical weather prediction model simulation results; linearizing the trained deep neural network to obtain a corresponding tangent linear operator and an adjoint operator, and embedding the tangent linear operator and the adjoint operator into the variational assimilation framework cost function; obtaining multi-source remote sensing observation data and a numerical weather prediction model background field, and solving an analysis field by taking minimization of the cost function as an objective, to complete data assimilation. The application can improve the data assimilation and numerical prediction level of disastrous weather such as typhoon, especially the observation assimilation level related to the boundary layer.

The invention discloses a boundary hierarchical grid physical constraint variation assimilation method embedded with a deep neural network, which comprises the following steps: establishing a momentum equation containing a boundary hierarchical grid turbulence friction item which is simulated through the deep neural network; constructing a weak constraint term of a variational assimilation framework cost function by using the momentum equation; training the deep neural network by using a data set constructed by a historical numerical weather forecast mode simulation result; linearizing the trained deep neural network to obtain a corresponding tangent linear operator and an adjoint operator, and embedding the tangent linear operator and the adjoint operator into the variational assimilation framework cost function; and acquiring multi-source remote sensing observation data and a numerical weather forecast mode background field, and solving an analysis field by taking the cost function minimization as a target to complete data assimilation. According to the method, the data assimilation and numerical forecasting level of disastrous weather such as typhoon can be improved, and particularly the observation assimilation level related to a boundary layer can be improved.

The invention relates to the cross technical field of deep learning and meteorological monitoring, in particular to an extreme weather intelligent monitoring and early warning method and system based on deep learning, and the method comprises the steps: collecting and processing data, and constructing a meteorological state tensor; inputting the tensor into a space-time Transform architecture with a meta-learning capability, and extracting cross-scale meteorological features by capturing long-range correlation through an encoder and integrating a space-time convolution gating cycle unit through a decoder; an adversarial training mechanism is introduced, and a numerical weather forecast mode is used as a judgment reference to optimize features; establishing a federal learning model updating mechanism to realize distributed optimization; and inputting the predicted trajectory into a power grid digital twin system, solving an equipment thermodynamic equation through a physical information neural network, and feeding back to a feature extraction process to form a closed loop. According to the method, the problems of low identification accuracy and poor early warning timeliness caused by multi-source heterogeneity and strong time sequence nonlinearity of extreme meteorological data are solved.

The invention discloses a systematic error diagnosis method for a high-resolution numerical weather forecasting mode, which comprises the following steps: carrying out continuous four-natural-month long-term integration on the high-resolution numerical weather forecasting mode, outputting a key forecasting variable every 3 hours, and retaining the key forecasting variables in the later three months; the observation data comprises GPCP, ISCCP, CERES and SSM / I; time averaging is carried out on instantaneous variables output by the high-resolution numerical weather forecast mode, variable rate calculation is carried out on cumulants of which the time variable rate needs to be calculated, cumulants of which the cumulants need to be calculated are calculated, averaging of three initial value tests is carried out on the data, time averaging is carried out on the observation data, and the time averaging is carried out on the observation data. Performing spatial interpolation on the output variable of the high-resolution numerical weather forecast mode; and comparing the forecast variable with the live observation data to obtain an error diagnosis result.

The present invention discloses a method for updating dynamic surface data based on a numerical weather forecast model. The present invention collects the static geographic data and the corresponding atmospheric initial field and boundary field data required for the study area and performs spatial interpolation and preprocessing on the static geographic data; decodes and processes the meteorological data based on the geographical environment characteristics and climate background conditions of the study area to generate boundary conditions that meet the simulation requirements; determines the appropriate physical process parameterization scheme and numerical calculation method based on the hydrological and meteorological characteristics of the target area and the research purpose, and then couples the dynamic surface update module with the WRF model. During the operation of the WRF model, the dynamic surface update module is called to continuously update the changes in the water surface range and water level caused by reservoir flooding during the simulation period. Based on the parallel simulation principle of the WRF model, the present invention improves the simulation accuracy and enhances the numerical stability by considering the impact of the dynamic surface on the atmospheric process.

The invention provides a high-speed rail platform wind speed correction method based on real-time dynamic coding and Informer feature fusion. The high-speed rail platform wind speed correction method comprises the steps that 1, monitoring data of a high-speed rail platform ultrasonic wave wind speed monitor and corresponding wind speed data output by a numerical weather forecast NWP model are collected; 2, designing a real-time fluctuation feature dynamic encoder RFDE for sudden turbulence of the high-speed rail platform, and performing real-time feature extraction; 3, designing a multi-source time sequence attention fusion device (MTAF) to obtain fused features; and step 4, constructing an Informer architecture of physical constraints, embedding aerodynamic smooth constraints in a loss function, correcting NWP wind speed forecast data and outputting the corrected NWP wind speed forecast data. According to the method, the real-time fluctuation characteristics are extracted from the wind speed monitoring data of the high-speed rail platform through the real-time fluctuation characteristic dynamic encoder and are used for quantifying the instantaneous change of the wind speed, and the defect of NWP in micro-scale wind field prediction is overcome.

The invention relates to the technical field of weather forecast and artificial intelligence crossing, and particularly discloses a gust forecast method based on deep learning. According to the invention, a gust intensity forecasting model comprising a space-time attention layer, a multi-scale feature extraction layer and a time sequence coding layer is constructed, and deep fusion is carried out on observation data, numerical forecasting data and topographic features by adopting an adaptive weight fusion mechanism; the problems that a numerical weather forecasting mode is insufficient in small-scale gust process description capability and a traditional machine learning method is difficult to fully extract gust generation and elimination multi-scale nonlinear features are solved, and gust forecasting precision and stability under the conditions of complex terrains and urban underlying surfaces are improved.

The invention belongs to the technical field of electric power weather forecast, and discloses a power grid facility-oriented cold wave disaster process risk assessment method and system, and the method comprises the steps: collecting field data outputted by a numerical weather forecast model, and recognizing and analyzing the key weather system and evolution characteristics of cold waves; the method comprises the following steps: constructing a GIS spatial analysis framework comprising a meteorological element graph layer and a power grid facility graph layer on the basis of a key weather system and evolution characteristics of cold waves, and performing overlay analysis on the GIS spatial analysis framework to obtain meteorological element distribution of an area where power grid facilities are located; and based on the meteorological element distribution of the area where the power grid facility is located, combining preset vulnerability parameters of the power grid facility and disaster characteristics of meteorological elements, constructing a risk assessment model, and outputting a risk assessment result. Accurate analysis, evaluation and early warning of the influence of the cold wave disaster on the power grid facilities are realized.

The invention belongs to the technical field of meteorological prediction, and relates to a high plateau airport wind field prediction method based on numerical simulation and a deep neural network. The method comprises the following steps: performing mesoscale wind field numerical simulation by adopting a numerical weather forecast model, and outputting ground wind field prediction data of the high plateau airport; carrying out feature engineering processing; constructing a training data set to train the neural network model; verifying and testing the trained deep neural network model to obtain a high plateau airport wind field prediction model; and carrying out real-time high plateau airport wind field prediction. According to the high plateau region complex terrain, low-pressure and low-oxygen environment and local wind field characteristics, the numerical weather prediction model and the deep neural network are combined, multi-dimensional combined prediction is carried out on meteorological parameters, the wind field prediction precision is improved, and the short-term prediction precision of severe convective weather can be effectively improved; under the condition of lacking complete observation data, the accuracy of a prediction result can be ensured; and the method has relatively high universality and expandability.

The invention provides a multi-time scale fusion wind speed prediction method based on a dual-encoder UNet model. The method comprises the following steps: S1, constructing dual encoders; s2, encoder feature fusion: realizing feature fusion between a numerical prediction wind speed encoder and a historical wind speed encoder through a cross attention mechanism; s3, constructing a multi-time scale decoder; s4, multi-time scale prediction result fusion: fusing the prediction results of different time scales through a multi-scale fusion module to generate a final wind speed prediction result; s5, constructing a wind speed prediction UNet model based on the steps S1-S4; s6, carrying out training data collection, training database construction and model training; and S7, wind speed prediction. According to the method, the multi-time scale characteristics of the wind speed can be effectively captured, online coupling of the historical wind speed data and the numerical weather forecast model is also realized, and the precision and robustness of wind speed prediction are remarkably improved.

This invention discloses a method for constructing an artificial intelligence-based rainstorm prediction model based on multi-source heterogeneous data fusion, relating to the field of rainstorm prediction technology. It involves collecting multi-source meteorological data of the area to be predicted, including satellite remote sensing data, weather radar data, ground meteorological station data, and numerical weather prediction model data. Based on preset dominant factor discrimination rules, the area to be predicted is divided into different dominant type zones, and virtual cloud entities are constructed based on these zones. By establishing a motion model of the virtual cloud entities, their life trajectory is generated, thereby constructing a cloud motion map reflecting the dynamic evolution of the virtual cloud entities. The system generates intervention commands based on the cloud motion map analysis, projects these commands into the cloud motion map, and finally outputs a rainstorm prediction report containing deterministic warnings and potential risk assessments. This invention constructs a virtual cloud entity system with dynamic perception and proactive intervention capabilities, achieving accurate prediction of the rainstorm formation process.

The application discloses a precipitation prediction method and system based on a spatial non-uniform fractal urban canopy model, and the precipitation prediction method based on the spatial non-uniform fractal urban canopy model comprises the following steps: collecting meteorological data of a target urban area; inputting the collected meteorological data into a mesoscale numerical weather prediction model fused with the spatial non-uniform fractal urban canopy model, and outputting a precipitation prediction result. The spatial non-uniform fractal urban canopy model is a construction of urban land surface parameters with a spatial scale scaling law characteristic; the fractal geometry theory is used to describe the spatial scale scaling law of the urban building distribution, and the theory is introduced into numerical weather prediction, so that the numerical weather prediction has the ability to solve the non-uniformity of the city on a fine scale on the meteorological mechanism across scales, especially the local atmospheric movement process that may cause strong convection and precipitation, and thus the simulation precision and the prediction ability of strong precipitation events in the city and the surrounding area are effectively improved.