Multi-element deep learning correction method and device for numerical mode forecasting

Through the multi-factor deep learning correction method, the feature extraction and fusion is used using DeepLab V3+ and ResNet networks, combined with mask tensor and loss function optimization, the problem of point-to-face deviation correction in numerical mode forecasting is solved, and the refined forecast correction effect is achieved.

CN120448466APending Publication Date: 2025-08-08CHINESE PEOPLES LIBERATION ARMY AVIATION COLLEGE
0 Cites 4 Cited by

Patent Information

Application Number
CN202510361212.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-25
Publication Date
2025-08-08

AI Technical Summary

Technical Problem

The existing numerical model forecasting methods have insufficient deviation correction capabilities from point to surface, especially when dealing with the complexity and unpredictability of atmospheric systems, resulting in significant forecast errors and limited effect of dynamic correction methods.

Method used

The multi-factor deep learning correction method is adopted to perform spatiotemporal matching and outlier screening of historical numerical model forecast data and meteorological site observation data, feature extraction and multi-scale feature fusion are used for feature extraction and multi-scale feature fusion, combined with mask tensors for observation point marking and loss function construction, and Adam optimizer and dynamic learning rate adjustment strategy are used for model training, and finally the forecast effect is evaluated through root mean square error and average absolute error.

Benefits of technology

It realizes high-quality forecasting correction from point to surface, improves the refinement accuracy and stability of numerical model forecasting, and solves the problem of forecast error in existing methods.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The embodiment of the invention provides a multi-element deep learning correction method and device for numerical mode forecasting. The method is applied to the technical field of data processing, and comprises the following steps: marking observation points, and performing loss function construction on the positions of the observation points to obtain a model optimization target; carrying out iterative updating on model parameters, and carrying out training process optimization by adopting a dynamic learning rate adjustment strategy to obtain a forecast field correction model; and applying the prediction field correction model to target numerical mode prediction data acquired in real time, performing prediction effect evaluation, and performing standardization processing and anti-standardization processing to obtain a correction prediction result. According to the method, the information extraction capability of a deep learning visual algorithm model is utilized, fine deviation correction of data of a numerical mode forecast space grid by meteorological station observation data is completed, meanwhile, multiple types of meteorological elements are fused, the deep learning model is utilized to learn mutual influences and restrictions between related elements, and the prediction precision of the numerical mode forecast space grid is improved. And finer deviation correction is completed.
Need to check novelty before this filing date? Find Prior Art