计算机与现代化

• 数据库与数据挖掘 • 上一篇    下一篇

伴随时空特性的雷电预测BP-ANN模型研究

  

  1. (1.江西省气象信息中心,江西南昌330096; 2.南昌大学信息工程学院,江西南昌330031)
  • 收稿日期:2019-02-01 出版日期:2019-04-26 发布日期:2019-04-30
  • 作者简介:李芬(1970-),女,江西安义人,高级工程师,学士,研究方向:气象数据挖掘、处理与应用,E-mial: 413563706@qq.com; 肖建(1981-),女,讲师,研究方向:机器学习与模式识别; 林志强(1995-),男,硕士研究生,研究方向:人工智能与机器学习,物联网技术; 李志鹏(1964-),男,正研级高级工程师,硕士,研究方向:气象数据挖掘、分析与处理。
  • 基金资助:
    江西省科技计划项目(20112BBI90024)

Research on BP-ANN Models of Lightning Prediction with Spatio-temporal Characteristics

  1. (1.Jiangxi Meteorological Information Center, Nanchang 330096, China;
    2.School of Information Engineering, Nanchang University, Nanchang 330031, China)
  • Received:2019-02-01 Online:2019-04-26 Published:2019-04-30

摘要: 为提高雷电预测模型的准确率和学习性能,提出一种基于增量学习和时空特性的雷电预测BP-ANN二项分类器。通过增量方式和依据数据的时空特征进行历史数据的学习,建立多种BP-ANN模型,分别对新的数据进行预测分类,然后采用多数投票方式确定新数据的类别。分别构建基于增量学习的BP-ANN模型、基于时空特性的BP-ANN模型以及结合基于增量学习和时空特性的BP-ANN模型这3种雷电预测模型,并在真实雷电数据集上进行预测准确度和学习性能的测试,结果表明了增量学习、时空特性以及二者结合的优劣。

关键词: 雷电预测, 增量学习, 时空特性, BP-ANN, 二项分类器

Abstract: In order to improve the accuracy and learning performance of the lightning prediction model, a BP-ANN binomial classifier of lightning prediction based on incremental learning and spatio-temporal characteristics is proposed. It makes a study of historical data by incremental approach and according to spatio-temporal characteristics of data, builds many BP-ANN models, classifies the new data respectively, and then uses the majority voting to determine the category of the new data. This paper constructs three kinds of lightning prediction models, BP-ANN model based on incremental learning, BP-ANN model based on spatio-temporal characteristics, and BP-ANN model combined both. The accuracy and learning performance are tested on real lightning data set, the results show the advantages and disadvantages of incremental learning, spatio-temporal characteristics and combination of both.

Key words: lightning prediction, incremental learning, spatio-temporal characteristics, BP-ANN, binomial classifier

中图分类号: