SHINE: Exploring the Initiations of Solar Flares using Deep Learning Methods
SHINE:使用深度学习方法探索太阳耀斑的起源
基本信息
- 批准号:2228996
- 负责人:
- 金额:$ 55.09万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2022
- 资助国家:美国
- 起止时间:2022-09-01 至 2025-08-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
Many new discoveries of phenomena of solar activity have been made in recent years thanks to state-of-the-art instrumentation for both ground-based and space-borne observations. However, due to ever increasing spatial and temporal resolutions, researchers are facing tremendous challenges to handle massive amounts of data in near real-time, and to extract important information from the data that can lead to further scientific discoveries and forecasting of solar activities. These tasks become more demanding when larger telescopes are revealing finer structure with rapid dynamics and evolution, such as the NSF-funded 1.6 meter Goode Solar Telescope (GST) at Big Bear Solar Observatory (BBSO). This project addresses the Solar, Heliospheric, and Interplanetary Environment (SHINE) goal of understanding the initiation of solar flares through use of deep learning methods and solar observations from the GST. The project is a joint effort between physics and computer science groups, integrating research and education through interdisciplinary training. A graduate researcher and high school students will be trained.In this research project, the team will develop and apply a suite of deep learning models and tools to advance the understanding of the initiation of solar flares, and provide near real-time flare forecasting. There are five interrelated tasks. (1) They will develop a convolutional neural network with attention mechanisms for inverting GST Stokes profiles to vector magnetograms with high efficiency and reduced noise. (2) Using a Bayesian convolutional network with uncertainty quantification, they will trace the fibril and loop structures of chromospheric observations to provide an assessment of magnetic fields in the chromosphere, which is crucial in 3D magnetic field extrapolations. (3) They will train generative adversarial networks (GANs) using simultaneous NASA Solar Dynamics Observatory (SDO) and GST magnetograms to create higher-resolution, larger field-of-view data, which are critical to derive flow fields in flare-producing solar active regions. (4) They will train a new GAN model, using SDO vector magnetograms and Hα images to derive transverse fields from the NASA Solar Heliospheric Observatory line-of-sight magnetograms. Therefore, the availability of vector magnetograms is extended to two solar cycles. (5) They will develop a new encoder-decoder bidirectional long short-term memory network with attention mechanisms to carry out near real-time flare prediction and evaluate the most critical magnetic parameters relevant to flare initiations. With these data and tools, they will address the following two key science questions: (i) With consistent high-resolution observations, what roles do the evolution of magnetic fields and flow fields play in storing energy and triggering solar flares? (ii) What is the quantitative assessment of flare prediction with the deep learning-processed data and deep learning-based prediction tools?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.
近年来,由于使用了最先进的地面和空间观测仪器,人们对太阳活动现象有了许多新的发现。然而,由于空间和时间分辨率的不断提高,研究人员面临着近乎实时处理大量数据的巨大挑战,并从数据中提取重要信息,这些信息可以导致进一步的科学发现和预测太阳活动。当更大的望远镜正在揭示具有快速动力学和进化的更精细结构时,这些任务变得更加苛刻,例如美国国家科学基金会资助的大熊太阳天文台(BBSO)的1.6米古德太阳望远镜(GST)。该项目解决了太阳、日球层和行星际环境(SHINE)的目标,即通过使用深度学习方法和GST的太阳观测来了解太阳耀斑的起源。该项目是物理学和计算机科学小组的共同努力,通过跨学科培训将研究和教育结合起来。将培训一名研究生研究员和一名高中生。在这个研究项目中,该团队将开发和应用一套深度学习模型和工具,以推进对太阳耀斑起源的理解,并提供近实时的耀斑预测。有五个相互关联的任务。(1)他们将开发一个具有注意力机制的卷积神经网络,用于将GST Stokes剖面高效地转化为矢量磁图,并降低噪声。(2)利用具有不确定性量化的贝叶斯卷积网络,他们将追踪色球观测的原纤维和环结构,以提供对色球磁场的评估,这在三维磁场外推中至关重要。(3)他们将同时使用NASA太阳动力学观测站(SDO)和GST磁图来训练生成对抗网络(gan),以创建更高分辨率、更大的视场数据,这对于导出产生耀斑的太阳活动区的流场至关重要。(4)他们将训练一个新的GAN模型,使用SDO矢量磁图和Hα图像从NASA太阳日球层天文台的视线磁图中导出横向场。因此,矢量磁图的可用性扩展到两个太阳周期。(5)他们将开发一种新的具有注意机制的编码器-解码器双向长短期记忆网络,以进行近实时的耀斑预测和评估与耀斑起爆相关的最关键磁参数。有了这些数据和工具,他们将解决以下两个关键的科学问题:(i)通过一致的高分辨率观测,磁场和流场的演变在储存能量和触发太阳耀斑方面发挥了什么作用?(ii)使用深度学习处理的数据和基于深度学习的预测工具对耀斑预测的定量评估是什么?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。
项目成果
期刊论文数量(2)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Solar Flare Ribbon Fronts. I. Constraining Flare Energy Deposition with IRIS Spectroscopy
太阳耀斑丝带正面。
- DOI:10.3847/1538-4357/acaf7c
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Polito, Vanessa;Kerr, Graham S.;Xu, Yan;Sadykov, Viacheslav M.;Lorincik, Juraj
- 通讯作者:Lorincik, Juraj
Inferring Line-of-sight Velocities and Doppler Widths from Stokes Profiles of GST/NIRIS Using Stacked Deep Neural Networks
- DOI:10.3847/1538-4357/ac927e
- 发表时间:2022-10
- 期刊:
- 影响因子:0
- 作者:Haodi Jiang;Qin Li;Yan Xu;W. Hsu;K. Ahn;W. Cao;J. T. Wang;Haimin Wang
- 通讯作者:Haodi Jiang;Qin Li;Yan Xu;W. Hsu;K. Ahn;W. Cao;J. T. Wang;Haimin Wang
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Yan Xu其他文献
A Proteolytic Site‐Directed Affinity Label to Inhibit the Human ATP‐Dependent Protease Caseinolytic Complex XP
抑制人类 ATP 依赖性蛋白酶酪蛋白分解复合物 XP 的蛋白水解定点亲和标记
- DOI:
10.1002/cbic.202000031 - 发表时间:
2020 - 期刊:
- 影响因子:3.2
- 作者:
Z. Sha;S. Chilakala;George W. Crabill;Iteen Cheng;Yan Xu;Jennifer Fishovitz;Irene Lee - 通讯作者:
Irene Lee
A secure distributed key management scheme for ad hoc network
一种用于自组织网络的安全分布式密钥管理方案
- DOI:
10.1109/icitis.2010.5689594 - 发表时间:
2010 - 期刊:
- 影响因子:0
- 作者:
Yan Xu;Hong Zhong;Xianping Yuan;Jia Yu - 通讯作者:
Jia Yu
Study on the asteroidal spin characteristics in the Hungaria region
匈牙利地区小行星自转特征研究
- DOI:
10.1002/asna.20210013 - 发表时间:
2021-11 - 期刊:
- 影响因子:0.9
- 作者:
Yi‐Bo Wang;Yan Xu - 通讯作者:
Yan Xu
Twisted microropes for stretchable devices based on electrospun conducting polymer fibers doped with ionic liquid
用于基于掺杂离子液体的电纺导电聚合物纤维的可拉伸装置的扭曲微绳
- DOI:
10.1039/c4tc01578a - 发表时间:
2014-10 - 期刊:
- 影响因子:6.4
- 作者:
Lin Da-Peng;He Hong-Wei;Huang Yuan-Yuan;Han Wen-Peng;Yu Gui-Feng;Yan Xu;Long Yun-Ze;Xia Lin-Hua - 通讯作者:
Xia Lin-Hua
DEVELOPMENT OF A LIQUID CHROMATOGRAPHIC METHOD FOR QUANTITATIVE DETERMINATION OF TRIAPINE, A RIBONUCLEOTIDE REDUCTASE INHIBITOR, BY SPECTROPHOTOMETRIC STUDY OF TRIAPINE COMPLEXATION REACTION
通过分光光度研究三荠平络合反应,建立定量测定核糖核苷酸还原酶抑制剂三荠平的液相色谱方法
- DOI:
- 发表时间:
2014 - 期刊:
- 影响因子:0
- 作者:
Ye Feng;M. McCulloch;Yan Xu - 通讯作者:
Yan Xu
Yan Xu的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Yan Xu', 18)}}的其他基金
Studies of White-Light and Black-Light Flares Using the 1.6 m New Solar Telescope (NST) at Big Bear Solar Observatory (BBSO)
使用大熊太阳天文台 (BBSO) 的 1.6 m 新型太阳望远镜 (NST) 研究白光和黑光耀斑
- 批准号:
1539791 - 财政年份:2016
- 资助金额:
$ 55.09万 - 项目类别:
Continuing Grant
Observations and Analysis of White-light Flares With High Resolution
高分辨率白光耀斑的观测与分析
- 批准号:
1153424 - 财政年份:2012
- 资助金额:
$ 55.09万 - 项目类别:
Continuing Grant
MRI: Acquisition of an LC-MS/MS Mass Spectrometer by Cleveland State University
MRI:克利夫兰州立大学购买 LC-MS/MS 质谱仪
- 批准号:
0923308 - 财政年份:2009
- 资助金额:
$ 55.09万 - 项目类别:
Standard Grant
相似国自然基金
Exploring Changing Fertility Intentions in China
- 批准号:
- 批准年份:2024
- 资助金额:万元
- 项目类别:外国学者研究基金
Exploring the Intrinsic Mechanisms of CEO Turnover and Market
- 批准号:
- 批准年份:2024
- 资助金额:万元
- 项目类别:外国学者研究基金
Exploring the Intrinsic Mechanisms of CEO Turnover and Market Reaction: An Explanation Based on Information Asymmetry
- 批准号:W2433169
- 批准年份:2024
- 资助金额:万元
- 项目类别:外国学者研究基金项目
相似海外基金
Planning: FIRE-PLAN: Exploring fire as medicine to revitalize cultural burning in the Upper Midwest
规划:FIRE-PLAN:探索火作为药物,以振兴中西部北部的文化燃烧
- 批准号:
2349282 - 财政年份:2024
- 资助金额:
$ 55.09万 - 项目类别:
Standard Grant
Postdoctoral Fellowship: CREST-PRP: Exploring the Impact of Heat-Waves and Nutrients on Bloom-Forming and Habitat-Building Seaweeds Along the South Florida Coast
博士后奖学金:CREST-PRP:探索热浪和营养物质对南佛罗里达海岸海藻形成和栖息地建设的影响
- 批准号:
2401066 - 财政年份:2024
- 资助金额:
$ 55.09万 - 项目类别:
Standard Grant
Winds of Change: Exploring the Meteorological Drivers of Global Dust
变革之风:探索全球沙尘的气象驱动因素
- 批准号:
2333139 - 财政年份:2024
- 资助金额:
$ 55.09万 - 项目类别:
Standard Grant
Exploring volcanic arcs as factories of critical minerals
探索火山弧作为关键矿物工厂
- 批准号:
FT230100230 - 财政年份:2024
- 资助金额:
$ 55.09万 - 项目类别:
ARC Future Fellowships
EMPOWHPVR: Exploring the factors that impact HPV self-sampling uptake amongst Black women and people with a cervix in Peel region, Ontario
EMPOWHPVR:探讨影响安大略省皮尔地区黑人女性和宫颈癌患者 HPV 自我采样率的因素
- 批准号:
502585 - 财政年份:2024
- 资助金额:
$ 55.09万 - 项目类别:
Novel species of N2O-reducing rhizobia: exploring the host range and N2O mitigation potential
减少 N2O 的根瘤菌新物种:探索寄主范围和 N2O 减排潜力
- 批准号:
24K17806 - 财政年份:2024
- 资助金额:
$ 55.09万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
Exploring the Mechanisms of Multimodal Metaphor Creation in Japanese Children
探索日本儿童多模态隐喻创造的机制
- 批准号:
24K16041 - 财政年份:2024
- 资助金额:
$ 55.09万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
An Alternative Mode of Student Well-Being or Unhappy Schools? Exploring Interdependence in Education across East and Southeast Asia, Building Evidence to Impact the Post-SDG 2030 Global Policy Agenda
学生福祉的替代模式还是不快乐的学校?
- 批准号:
23K25636 - 财政年份:2024
- 资助金额:
$ 55.09万 - 项目类别:
Grant-in-Aid for Scientific Research (B)
A2M: Exploring in-silico predicted arms-races at the plant-pathogen interface
A2M:探索植物-病原体界面的计算机预测军备竞赛
- 批准号:
BB/Y000560/1 - 财政年份:2024
- 资助金额:
$ 55.09万 - 项目类别:
Research Grant
Exploring the mental health and wellbeing of adolescent parent families affected by HIV in South Africa
探讨南非受艾滋病毒影响的青少年父母家庭的心理健康和福祉
- 批准号:
ES/Y00860X/1 - 财政年份:2024
- 资助金额:
$ 55.09万 - 项目类别:
Fellowship