9results about How to "Improve the forecast effect" patented technology

The invention discloses a construction method of a dam multi-measuring-point deformation deep learning monitoring model, and the method comprises the steps: carrying out the clustering analysis of dam deformation data through employing a K-means algorithm, so as to recognize a spatial mode of a monitoring region; in each clustering region, based on the interaction of dependent variables between the monitoring points, a long-short-term memory network of a coupling attention mechanism is adopted to construct a deformation prediction model; sequencing and evaluating the measuring points and the influence factors of the measuring points in different areas by applying an interpretability analysis technology; according to the method, clustering analysis, an attention mechanism, deep learning and other algorithms are effectively integrated, and a dam multi-measuring-point deformation monitoring model which is high in prediction precision and high in explanation capacity is successfully constructed. The model provides a new thought and method for reasonably analyzing and predicting the overall deformation characteristics of the dam. The application of the method not only improves the prediction accuracy, but also enhances the transparency and credibility of the model.

The invention discloses a method and equipment for replacing sea-gas coupling parameterization in an atmospheric waveguide forecast model based on physical constraint deep learning, and a storage medium. The method comprises the following steps: step 1, preparing training data; step 2, increasing physical constraint to improve generalization ability; step 3, constructing a network for calculation; according to the method disclosed by the invention, the occupancy rate of computing resources can be reduced, the computing speed and the model forecasting performance are improved at the same time, a new idea is provided for application of artificial intelligence in the meteorological field, and a new technical development direction is provided for innovation in the meteorological field.

The present invention discloses a method for forecasting the continuous distribution probability of extended-period precipitation by integrating fine terrain features, including: obtaining standardized multi-member multi-factor forecast data of the extended-period numerical model ensemble forecast system and regional historical long-term series precipitation observation data, and extracting the continuous distribution characteristics of historical precipitation; obtaining a descaled key terrain multidimensional feature factor library based on regional high-resolution fine terrain data; constructing an extreme gradient boosting U-Net hybrid deep learning precipitation probability forecast model, and carrying out model training and optimization; using the trained model to generate an improved forecast result of the continuous distribution probability of extended-period precipitation. The present invention integrates fine terrain data, adopts a weighted cross entropy loss function, effectively handles the problem of imbalanced precipitation distribution categories, improves the generalization ability of the model, and improves the forecast performance of the continuous distribution probability forecast of precipitation, which has extremely high application value.

This invention relates to the field of AI weather forecasting technology and discloses a weather forecasting method based on an AI weather forecasting model and a WRF model. The method includes: inputting ERA5 global atmospheric reanalysis gridded data into the AI ​​weather forecasting model to obtain an assimilated background field; constructing an effective multi-source observation vector based on observation data from ground automatic weather stations, radiosonde observation data, geostationary meteorological satellite radiance data, and Doppler radar VAD wind profile data; solving for the optimal atmospheric analysis field; extracting atmospheric state variables from the optimal atmospheric analysis field and writing them into the WRF model's side boundary driving file, driving the WRF model to complete the integration operation, and obtaining a gridded forecast field of meteorological elements. This method enables the WRF boundary condition update frequency to be higher than the traditional 6-hour static scheme, effectively characterizing the rapid evolution of the atmospheric state in the boundary region at the sub-hourly scale, thereby improving the WRF model's forecasting capability for high-impact weather events such as severe convection.

The present invention discloses a method for correcting and calculating the near-surface temperature and wind speed of grid points using the spatiotemporal neighborhood method. The method comprises the following steps: obtaining a historical sample data set of the forecast quantity and its corresponding forecast factor; selecting historical samples similar to the current forecast through temporal and spatial classification and preliminary screening; calculating the normalized value of each forecast factor to eliminate the dimensional differences between the factors; calculating the spatiotemporal distance between the current forecast and the historical sample, selecting several historical samples with the smallest distance, and performing weighted averaging based on the analysis values ​​of these samples to generate the final corrected measurement value; testing the corrected measurement results, and optimizing the weight configuration model; in extreme weather conditions, using the seven-day deviation correction method instead of the spatiotemporal neighborhood correction. The method can effectively improve the accuracy of the forecast of near-surface temperature and wind speed in numerical forecasts, reduce the amount of calculation, and effectively improve the forecast and calculation accuracy of near-surface grid temperature and wind speed.

The invention belongs to the crossing field of new energy and meteorology, and discloses a meteorological inversion assimilation method based on new energy power generation data and a related device. The meteorological inversion assimilation method based on the new energy power generation data comprises the following steps: acquiring original power generation data of a new energy station; performing state discrimination and data cleaning on the original power generation data to obtain inversion basic data; carrying out meteorological inversion by adopting a physical-data hybrid driving model, and carrying out uncertainty quantification and screening on meteorological inversion initial data to obtain meteorological inversion screening data; and based on meteorological inversion screening data and a selected assimilation algorithm, state correction is carried out on the numerical weather forecast NWP model, and an NWP model after initial field optimization is obtained. According to the technical scheme disclosed by the invention, the problem of insufficient precision in the process of simulating and forecasting the meteorological conditions of the new energy station region by the NWP model at the present stage can be solved.

The invention discloses a solar flare forecasting method and system based on fusion of physical parameters and geometric features of an active area. The method comprises the following steps: acquiring magnetic field observation data and optical image data of a target solar active area; extracting magnetic field physical parameters from the magnetic field observation data, and extracting geometric features of an active area from the optical image data; acquiring magnetic field observation data and optical image data of the target solar active area in a historical time window, and constructing a time sequence of magnetic field physical parameters and geometric features; extracting dynamic evolution characteristics of physical parameters and geometric characteristics of the magnetic field from the time sequence; fusing the physical parameters and the geometric features of the current magnetic field with the dynamic evolution features, and constructing an enhanced fusion feature vector; inputting the enhanced fusion feature vector into a pre-trained neural network model, and obtaining a prediction probability of generating a specific-level flare in the target solar activity area in the future; and generating and issuing flare forecast information according to a comparison result of the forecast probability and a preset threshold value.

The present invention discloses a solar radiation forecasting system and method integrated with a multi-source algorithm, comprising: obtaining data 1 and data 2 based on radiation forecast data; interpolating data 2 onto hourly data to obtain data 3, interpolating the two sets of data onto a number of radiation stations, combining radiation hourly observation data, obtaining two sets of data station weight coefficient tables through data processing, flattening the two sets of data station weight coefficient tables onto a grid grid field consistent with the spatial resolution of the two sets of data sources, obtaining a gridded weight coefficient table, wherein the two sets of data are data 1 and data 3; integrating the two sets of data based on the two sets of data grid weight coefficient tables to obtain final radiation data. The present invention is applicable to the intersection of energy and meteorological forecasting, can avoid the singleness of the data source and the limitations in certain areas, improve the forecasting effect, and can also improve the quality of radiation forecasting, and enhance the accuracy and stability of forecasting results.

The present invention discloses a road surface temperature prediction method based on numerical model fusion deep learning, including making training sets and verification sets based on multi-factor forecast data and observation data; integrating and forming a unified-scale regional high-resolution multi-substrate feature library based on regional high-resolution multi-substrate data; constructing a deep learning road surface temperature prediction model based on an attention mechanism graph convolutional neural network, using a Gaussian weighted loss function to carry out model training; using the trained model, for the target time, based on the numerical weather forecast model multi-factor forecast data and regional high-resolution multi-substrate data, generating a road surface temperature prediction result based on numerical model fusion deep learning. The present invention effectively solves the sample imbalance problem of road surface temperature at different scales, enhances the model's prediction ability for road surface temperature extremes, and improves the accuracy of highway road surface temperature prediction based on numerical model fusion deep learning, and has extremely strong application value.