• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文OA文献 >Engineering System Design for Automated Space Weather Forecast. Designing Automatic Software Systems for the Large-Scale Analysis of Solar Data, Knowledge Extraction and the Prediction of Solar Activities Using Machine Learning Techniques.
【2h】

Engineering System Design for Automated Space Weather Forecast. Designing Automatic Software Systems for the Large-Scale Analysis of Solar Data, Knowledge Extraction and the Prediction of Solar Activities Using Machine Learning Techniques.

机译：自动化空间天气预报的工程系统设计。使用机器学习技术设计自动软件系统，以进行大规模太阳数据分析，知识提取和太阳活动预测。

页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Coronal Mass Ejections (CMEs) and solar flares are energetic events takingudplace at the Sun that can affect the space weather or the near-Earth environment by theudrelease of vast quantities of electromagnetic radiation and charged particles. Solar activeudregions are the areas where most flares and CMEs originate. Studying the associationsudamong sunspot groups, flares, filaments, and CMEs is helpful in understanding theudpossible cause and effect relationships between these events and features. Forecastingudspace weather in a timely manner is important for protecting technological systems andudhuman life on earth and in space.udThe research presented in this thesis introduces novel, fully computerised,udmachine learning-based decision rules and models that can be used within a systemuddesign for automated space weather forecasting. The system design in this work consistsudof three stages: (1) designing computer tools to find the associations among sunspotudgroups, flares, filaments, and CMEs (2) applying machine learning algorithms to theudassociations¿ datasets and (3) studying the evolution patterns of sunspot groups usingudtime-series methods.udMachine learning algorithms are used to provide computerised learning rulesudand models that enable the system to provide automated prediction of CMEs, flares, andudevolution patterns of sunspot groups. These numerical rules are extracted from theudcharacteristics, associations, and time-series analysis of the available historical solaruddata. The training of machine learning algorithms is based on data sets created byudinvestigating the associations among sunspots, filaments, flares, and CMEs. Evolutionudpatterns of sunspot areas and McIntosh classifications are analysed using a statisticaludmachine learning method, namely the Hidden Markov Model (HMM).
机译：冠状物质抛射（CME）和太阳耀斑是在太阳上发生的高能事件，会释放大量电磁辐射和带电粒子，从而影响太空天气或近地环境。太阳活跃区是大多数耀斑和CME起源的区域。研究太阳黑子群，耀斑，细丝和CME的关联有助于理解这些事件和特征之间的可能的因果关系。及时预测 udspace天气对于保护地球和太空中的技术系统和 udhuman生命非常重要。 ud本文中的研究介绍了新颖的，完全计算机化的，基于 udmachine学习的决策规则和模型。在系统 uddesign中进行自动空间天气预报。这项工作的系统设计包括三个阶段：（1）设计计算机工具以找到黑子 udgroup，耀斑，细丝和CME之间的关联（2）将机器学习算法应用于udassociations®数据集，以及（3）使用 udtime系列方法研究黑子群的演化模式。 udMachine学习算法用于提供计算机化的学习规则 udand模型，使系统能够自动预测CME，耀斑和黑子群的演化模式。这些数值规则是从可用历史太阳 uddata的特征，关联和时间序列分析中提取的。机器学习算法的训练基于通过对黑子，细丝，耀斑和CME之间的关联进行研究而创建的数据集。利用统计机器学习方法，即隐马尔可夫模型（HMM），分析了黑子地区的演化模式和McIntosh分类。

著录项

  • 作者

    Alomari Mohammad Hani;

  • 作者单位
  • 年度 2009
  • 总页数
  • 原文格式 PDF
  • 正文语种 en
  • 中图分类

相似文献

  • 外文文献
  • 中文文献
  • 专利

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号