CAREER: Characterization of Sources of Ionospheric Scintillation and Space Weather Prediction through Analytics and Machine Learning

该项目支持职业发展计划，该计划基于对电离层闪烁来源的调查，使用基于物理的建模和机器学习（ML）相结合的方法，并进一步预测空间天气影响，同时支持和加强安柏瑞德航空大学（ERAU）的学生研究、教学和公共宣传。空间天气可以影响地球上的不同技术，例如，地磁风暴可以改变全球导航卫星系统（GNSS）的信号（称为闪烁）并降低其准确性和可靠性。该项目的主要教育目标将通过指导UG和研究生，开发一门新课程“数据科学和机器学习在空间天气预报中的应用”，以及在ERAU暑期学校和女性参与科学Embry-Riddle （WiSER）计划中包括一个新的空间天气组件来实现。为实现外联目标，将为欧洲航空研究联盟航空专业学生举办“空间天气对空中交通通信的影响”讲习班，并与代托纳比奇业余无线电俱乐部合作，向学生和当地社区宣传空间天气及其对无线电通信的影响。虽然人们正在尝试利用总电子含量（TEC）和GNSS信号闪烁指数来预测全球电离层状态，但在利用GNSS数据和建模来了解和预测局部电离层产生高纬度电离层不规则现象的潜在机制方面做得很少。本研究的主要目标是使用逆方法，一个完整的3D前向传播模型以及来自几个已建立的GNSS接收器的数据集来训练机器学习（ML）算法，基于其来源对不规则性进行聚类，并协助预测不同时间和频率的闪烁。因此，该项目将开发一种机器学习方法，并利用最先进的基于物理的模型和反演方法来预测空间天气影响。无线电通信对许多民用和军事活动至关重要，因此通过不规则物理预测空间天气对通信的影响将被证明具有巨大的社会效益。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

This project supports a CAREER development plan based upon an investigation of the sources of ionospheric scintillation using an approach that combines physics-based modeling and machine learning (ML), and further predicts space weather effects, while supporting and enhancing student research, teaching, and public outreach at Embry-Riddle Aeronautical University (ERAU). Space weather can affect different technologies on the Earth, for example, geomagnetic storms can alter the signals from Global Navigation Satellite Systems (GNSS) (called scintillation) and degrade their accuracy and reliability. The main educational goals of this project will be achieved through mentoring UG and graduate students, development of a new course "Application of data science and machine learning to space weather prediction," and including a new space weather component in the ERAU summer school and Women in Science Embry-Riddle (WiSER) program. The outreach goals will be achieved through organizing a workshop "Space weather effects on Air Traffic communication" for ERAU Aviation majors and collaborating with the Daytona Beach HAM radio club to enthuse students and local community on space weather and its effect on radio communications.While many attempts are underway to predict the global ionospheric state using Total Electron Content (TEC) and GNSS signal scintillation indices, little is done to understand and predict the local ionosphere in terms of the underlying mechanisms responsible for producing high latitude ionospheric irregularities using GNSS data and modeling. The principal objectives of this study are to use the inverse method, a full 3D forward propagation model along with datasets from several established GNSS receivers to train machine learning (ML) algorithms in clustering of irregularities based on their sources and to assist with predicting the scintillation at a different time and frequency. Thus, this project will develop an ML approach, and augment it with the state-of-the-art physics-based models and inversion method in predicting space weather effects. Radio communication is critical to many civilian and military endeavors, therefore predicting the space weather effects on communication through irregularity physics will prove to be of great societal benefit.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.