RII Track-2 FEC: Collaborative Research: Harnessing Big Data to Improve Understanding and Predictions of Geomagnetically Induced Currents

RII Track-2 FEC：协作研究：利用大数据提高对地磁感应电流的理解和预测

• 批准号: 1920965
• 负责人: Donald Hampton
• 金额: $ 399.79万
• 依托单位: University of Alaska Fairbanks Campus
• 依托单位国家: 美国
• 项目类别: Cooperative Agreement
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-08-01 至 2024-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1920965&HistoricalAwards=false
• 关键词: RII; Track; FEC; Collaborative; Research

Recently, the Office of Science and Technology for the President recommended that we take steps to prepare our nation's infrastructure to withstand the hazardous space weather impacts. Geomagnetically induced currents (GICs), caused by the geomagnetic disturbance during space weather events, can produce power outages, train system failures, and pipeline corrosion. Although the risk of GICs are widely acknowledged in the industry and space science community, the occurrence patterns and the space/ground conditions responsible for GICs are poorly understood mainly because power companies are hesitant to provide their GIC data due to a possible legal dispute over the power outages and any other technical problems. The project will take advantage of the wealth of expertise in space physics and data science within the University of Alaska Fairbanks and the University of New Hampshire to understand and predict the GICs. This project specifically focuses on the geomagnetic disturbance, the trigger of GICs, and the possible sources of such disturbance in our geospace environments. We will apply the state-of-the-art machine learning techniques to over two decades of space/ground-based observations and develop two prediction models for the geomagnetic disturbance and the GIC-risk, both of which will be provided to NOAA Space Weather Prediction Center at the end of project. Additionally, we will improve our GIC predictions in Alaska and New Hampshire, the two high GIC-risk states, via the Space Weather Underground (SWUG) program. Under this program, high-school and undergraduate students will build and deploy magnetometers, measure geomagnetic disturbances, and analyze the data. By varying the spatial distance between the magnetometers, we can investigate the optimal number and distribution of ground magnetometers for accurate GIC modeling and prediction. The project team includes early-career and under-represented scientists and will provide research projects and relevant course content to high-school, undergraduate, and graduate students, including those at a minority serving institution and regional colleges.Recently, the Office of Science and Technology for the President recommended that we take steps to prepare our nation's infrastructure to withstand the hazardous space weather impacts. Geomagnetically induced currents (GICs), caused by the geomagnetic disturbance during space weather events, can produce power outages, train system failures, and pipeline corrosion. Although the risk of GICs are widely acknowledged in the industry and space science community, the occurrence patterns and the space/ground conditions responsible for GICs are poorly understood mainly because power companies are hesitant to provide their GIC data due to a possible legal dispute over the power outages and any other technical problems. The project will take advantage of the wealth of expertise in space physics within the Geophysical Institute at the U. of Alaska (UAF) and the Space Science Center at the U. of New Hampshire (UNH) combined with data science expertise at both universities to understand and predict the GICs. This project specifically focuses on the geomagnetic disturbance, the trigger of GICs, and the possible sources of such disturbance in solar wind, magnetosphere, and ionosphere. We will apply the state-of-the-art machine learning techniques to over two decades of space/ground-based observations and develop two prediction models for the geomagnetic disturbance and the GIC-risk, both of which will be provided to NOAA Space Weather Prediction Center at the end of project. Additionally, the UNH Space Weather Underground (SWUG) program will be expanded within New Hampshire and to UAF. Under this program, high-school and undergraduate students will build and deploy magnetometers and analyze the data. By varying the spatial distance between the magnetometers, we can investigate the optimal number and distribution of ground magnetometers for accurate GIC modeling and prediction. Additionally, the SWUG dataset will improve the GIC predictions in AK and NH. Alaska is in a region of high latitude with increased GIC risk. New Hampshire is at lower latitudes, but includes coastal areas as well as bedrock with high resistivity, which forces the currents to flow through structures such as power transmission lines. Thus, these two states provide ideal conditions for collaboration and comparison of results and would benefit from improved predictive capabilities for GICs. The proposed project would open new funding opportunities for project participants within NSF and elsewhere by supporting new interdisciplinary and inter-jurisdictional collaborations and building capacity for future big data science in space weather research.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.

最近，总统科学技术办公室建议我们采取措施，准备好我们国家的基础设施，以抵御危险的太空天气影响。太空天气事件期间地磁扰动引起的地磁感应电流 (GIC) 可能会导致停电、列车系统故障和管道腐蚀。尽管GIC的风险在工业界和空间科学界得到广泛认可，但人们对GIC的发生模式和空间/地面条件知之甚少，这主要是因为电力公司由于可能存在法律纠纷而不愿提供其GIC数据。停电和任何其他技术问题。该项目将利用阿拉斯加大学费尔班克斯分校和新罕布什尔大学在空间物理和数据科学方面丰富的专业知识来理解和预测 GIC。该项目特别关注地磁扰动、GIC 的触发因素以及地球空间环境中此类扰动的可能来源。我们将把最先进的机器学习技术应用于二十多年的天基/地面观测，并开发两个地磁扰动和 GIC 风险的预测模型，这两个模型都将提供给 NOAA 空间天气项目结束时的预测中心。此外，我们将通过地下空间天气 (SWUG) 计划改进对阿拉斯加和新罕布什尔州这两个 GIC 高风险州的 GIC 预测。根据该计划，高中生和本科生将构建和部署磁力计、测量地磁扰动并分析数据。通过改变磁力计之间的空间距离，我们可以研究地面磁力计的最佳数量和分布，以进行准确的 GIC 建模和预测。该项目团队包括职业生涯早期和代表性不足的科学家，将为高中、本科生和研究生提供研究项目和相关课程内容，包括少数族裔服务机构和地区学院的学生。总统的技术建议我们采取措施准备我们国家的基础设施以抵御危险的太空天气影响。太空天气事件期间地磁扰动引起的地磁感应电流 (GIC) 可能会导致停电、列车系统故障和管道腐蚀。尽管GIC的风险在工业界和空间科学界得到广泛认可，但人们对GIC的发生模式和空间/地面条件知之甚少，这主要是因为电力公司由于可能存在法律纠纷而不愿提供其GIC数据。停电和任何其他技术问题。该项目将利用阿拉斯加大学地球物理研究所 (UAF) 和新罕布什尔大学空间科学中心 (UNH) 丰富的空间物理学专业知识以及两所大学的数据科学专业知识，理解并预测 GIC。该项目特别关注地磁扰动、GIC 的触发因素以及太阳风、磁层和电离层中此类扰动的可能来源。我们将把最先进的机器学习技术应用于二十多年的天基/地面观测，并开发两个地磁扰动和 GIC 风险的预测模型，这两个模型都将提供给 NOAA 空间天气项目结束时的预测中心。此外，UNH 地下空间天气 (SWUG) 计划将在新罕布什尔州和 UAF 范围内扩展。根据该计划，高中生和本科生将构建和部署磁力计并分析数据。通过改变磁力计之间的空间距离，我们可以研究地面磁力计的最佳数量和分布，以进行准确的 GIC 建模和预测。此外，SWUG 数据集将改进 AK 和 NH 中的 GIC 预测。阿拉斯加位于高纬度地区，GIC 风险较高。新罕布什尔州位于较低纬度，但包括沿海地区以及高电阻率的基岩，这迫使电流流经输电线路等结构。因此，这两个州为协作和结果比较提供了理想的条件，并将受益于 GIC 预测能力的改进。拟议的项目将为 NSF 和其他地方的项目参与者提供新的资助机会，支持新的跨学科和跨辖区合作以及未来空间天气研究大数据科学的能力建设。该奖项反映了 NSF 的法定使命，并被认为值得支持通过使用基金会的智力优点和更广泛的影响审查标准进行评估。

项目成果

A Contrastive Learning Approach to Auroral Identification and Classification

极光识别和分类的对比学习方法

• DOI: 10.1109/icmla52953.2021.00128
• 发表时间: 2021-09-28
• 期刊: 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)
• 作者: Jeremiah W. Johnson;Swathi Hari;D. Hampton;H. Connor;A. Keesee
• 通讯作者: A. Keesee

Global Survey of Plasma Sheet Electron Precipitation due to Whistler Mode Chorus Waves in Earth's Magnetosphere

地球磁层中惠斯勒模式合唱波引起的等离子体片电子沉淀的全球调查

• DOI: 10.1029/2020gl088798
• 发表时间: 2020-07-28
• 期刊: Geophysical Research Letters
• 影响因子: 5.2
• 作者: Q. Ma;H. Connor;X.‐J. Zhang;W. Li;X. Shen;D. Gillespie;C. Kletzing;W. Kurth;G. Hospodarsky;S. Claudepierre;G. Reeves;H. Spence
• 通讯作者: H. Spence

Mesoscale Structures in Earth's Magnetotail Observed Using Energetic Neutral Atom Imaging

使用高能中性原子成像观测地球磁尾的介观结构

• DOI: 10.1029/2020gl091467
• 发表时间: 2021-02-04
• 期刊: Geophysical Research Letters
• 影响因子: 5.2
• 作者: A. Keesee;N. Buzulukova;C. Mouikis;E. Scime
• 通讯作者: E. Scime

Comparison of Deep Learning Techniques to Model Connections Between Solar Wind and Ground Magnetic Perturbations

深度学习技术对太阳风与地磁扰动之间关系模型的比较

• DOI: 10.3389/fspas.2020.550874
• 发表时间: 2020-10
• 期刊: Frontiers in Astronomy and Space Sciences
• 影响因子: 3
• 作者: Keesee, Amy M.;Pinto, Victor;Coughlan, Michael;Lennox, Connor;Mahmud, Md Shaad;Connor, Hyunju K.
• 通讯作者: Connor, Hyunju K.

A Survey of Uncertainty Quantification in Machine Learning for Space Weather Prediction

空间天气预报机器学习中不确定性量化的调查

• DOI: 10.3390/geosciences12010027
• 发表时间: 2022-01-07
• 期刊: Geosciences
• 影响因子: 2.7
• 作者: Talha Siddique;Md. Shaad Mahmud;A. Keesee;C. Ngwira;H. Connor
• 通讯作者: H. Connor