一种用于风廓线雷达水平风数据缺测补全模型的构建方法
By using the Delaunay triangulation method and a multi-layer fully connected neural network model, combined with radiosonde data, the problem of missing data from wind profiler radar under severe convective weather was solved, achieving efficient completion of horizontal wind data from wind profiler radar and improving the completeness and accuracy of the data.
CN121456320BActive Publication Date: 2026-07-17STATE QIXIANG INFORMATION CENT +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- STATE QIXIANG INFORMATION CENT
- Filing Date
- 2025-11-10
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Wind profiler radar is prone to data loss under severe convective weather conditions. Existing interpolation methods are not ideal, resulting in a high data loss rate, which affects applications in weather monitoring and wind energy.
Method used
The Delaunay triangulation method was used for radar networking. Combined with radiosonde observation data and wind profiler radar data, feature factors were extracted by principal component analysis, and a multi-layer fully connected neural network model was constructed to complete the missing data.
Benefits of technology
It improved the completeness and accuracy of horizontal wind data from wind profiler radar, optimized the data complementarity between radar stations, and significantly improved the accuracy of data completion.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN121456320B_ABST
Abstract
本发明公开一种用于风廓线雷达水平风数据缺测补全模型的构建方法，包括：步骤（1）、采用Delaunay三角剖分法进行组网，分析风廓线雷达水平风数据缺测情况；步骤（2）、对风廓线雷达观测资料进行质量控制，将质控后风廓线雷达观测的资料与其邻近的探空站观测资料进行空间匹配；步骤（3）、将匹配得到的探空‑风廓线雷达匹配资料进行归一化处理，并利用主成分分析法提取特征因子；步骤（4）、基于多层全连接神经网络模型构建风廓线雷达水平风数据缺测补全模型；步骤（5）、利用最终构建的风廓线雷达水平风数据缺测补全模型进行缺测水平风数据的补全。本发明可以解决现有的风廓线雷达缺测数据补全方法完整性与准确率较低的技术问题。
Need to check novelty before this filing date? Find Prior Art