HDR Institute: HARP- Harnessing Data and Model Revolution in the Polar Regions

HDR 研究所：HARP——利用极地地区的数据和模型革命

• 批准号: 2118285
• 负责人: Vandana Janeja
• 金额: $ 1300万
• 依托单位: University of Maryland Baltimore County
• 依托单位国家: 美国
• 项目类别: Cooperative Agreement
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-01-01 至 2026-12-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2118285&HistoricalAwards=false
• 关键词: HDR; Institute; HARP; Harnessing; Data

Climate-change induced loss of polar ice sheets impacts many lives and increases coastal flooding by rising sea level and affecting ocean circulation. However, it remains difficult to accurately predict how quickly the ice sheets will continue to shrink. In particular, we are still challenged by a limited understanding of transdisciplinary processes that determine ice sheet change, such as the role of subglacial topography and ice-atmosphere-ocean interactions. Timely investment in machine learning and data intensive research can revolutionize the way that scientists currently answer questions related to ice dynamics. This HDR Institute serves as a research hub where experts in data science, Arctic and Antarctic science, and cyberinfrastructure in academia, government, and private sectors come together to develop transformative and integrative data science solutions to reduce uncertainties in projecting future sea-level rise and climate change. i-HARP researchers investigate the potential of novel physics-aware data science and machine learning approaches to address national priorities and challenges on Navigating the New Arctic, climate change, and sea-level rise.The HDR Institute aims to harness massive heterogeneous, noisy, and discontinuous data in space and time and integrate data with numerical and physical models. Researchers at i-HARP are investigating novel data science techniques including deep generative adversarial networks, graph neural networks, meta learning, hybrid networks, physics-informed machine learning, causal artificial intelligence, data assimilation, spatiotemporal deep learning, and scalable algorithms. Due to the fundamental nature of data science problems that i-HARP addresses, the solutions can be translated to other disciplines such as remote sensing, medicine, and autonomous driving. Moreover, the convergence team champions multiple clusters of research-integrated educational initiatives, with a specific focus on facilitating cross-disciplinary collaborations, training next-generation multi-disciplinary researchers and engaging the public in scientific inquiry as related to climate change and data science. In partnership with related communities, i-HARP designs curricula, and offers hands-on community workshops, lecture series, conference tutorials, and training. i-HARP engages students from underrepresented minority groups by leveraging several existing organizations for underrepresented minorities.This project is part of the National Science Foundation's Big Idea activities in Harnessing the Data Revolution (HDR). This award by the Office of Advanced Cyberinfrastructure is jointly supported by the Section for Antarctic Sciences and the Section for Arctic Sciences within the NSF Office of Polar Programs.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.

气候变化引起的极地冰盖的丧失会影响许多生命，并通过增加海平面并影响海洋循环，从而增加沿海洪水。但是，很难准确预测冰盖将继续缩小的速度。特别是，我们仍然受到对决定冰盖变化的跨学科过程的有限理解的挑战，例如冰川亚地形和冰原 - 冰山相互作用的作用。及时对机器学习和数据密集型研究的投资可以彻底改变科学家目前回答与冰动态有关的问题的方式。该HDR Institute是一个研究中心，在该研究中心，数据科学，北极和南极科学专家，以及学术界，政府和私营部门的Cyber​​infrasture，共同开发了变革性和综合数据科学解决方案，以减少预测未来海平面上升和气候变化的不确定性。 I-HARP的研究人员研究了新型物理学数据科学和机器学习方法的潜力，以应对新的北极，气候变化和海平面上升的国家优先事项和挑战。HDRInstitute旨在利用大量的异质性，嘈杂性，嘈杂，嘈杂，以及在空间和数值和物理模型中整合数据中的不连续数据，并将其整合到数值和物理模型中。 I-HARP的研究人员正在研究新的数据科学技术，包括深层生成的对抗网络，图形神经网络，元学习，混合网络，物理知识的机器学习，因果人工智能，数据同化，时空深度学习和可扩展算法。由于I-HARP解决的数据科学问题的基本性质，可以将解决方案转化为其他学科，例如遥感，医学和自动驾驶。此外，融合团队支持多个研究综合教育计划的群体，特别着眼于促进跨学科合作，培训下一代多学科研究人员，并与公众参与与气候变化和数据科学有关的科学询问。与相关社区合作，I-HARP设计课程，并提供动手社区讲习班，讲座系列，会议教程和培训。我的毛力量通过利用几个现有组织的代表性不足的少数群体来吸引人数不足的少数群体的学生。该项目是国家科学基金会在利用数据革命（HDR）方面的重大思想活动的一部分。 高级网络基础设施办公室的奖项由南极科学部分和NSF Polar计划办公室内的北极科学部分共同支持。该奖项反映了NSF的法定任务，并被认为是值得通过基金会的智力和更广泛影响的评估来通过评估来支持的，这是值得的。

项目成果

Mobile Augmented Reality System for Emergency Response

用于应急响应的移动增强现实系统

• 发表时间: 2023
• 期刊: Management and Applications (SERA 2023
• 作者: Sharma, S

Metrics for the quality and consistency of ice layer annotations

冰层注释的质量和一致性指标

• 发表时间: 2023
• 期刊: IEEE International Geoscience and Remote Sensing Symposium
• 作者: N. Tack;B. A. Tama;A. Jebeli;V. Janeja;D. Engel;R. Williams
• 通讯作者: R. Williams

TSSA: two-step semi-supervised annotation for englacial radargrams on the Greenland ice sheet

TSSA：格陵兰冰盖冰川雷达图的两步半监督注释

• 发表时间: 2023
• 期刊: IEEE International Geoscience and Remote Sensing Symposium
• 作者: A. Jebeli;B. A. Tama;V. Janeja;N. Holschuh;C. Jensen;M. Morlighem;J. A MacGregor;M. Fahnestock
• 通讯作者: M. Fahnestock

Evaluating Machine Learning and Statistical Models for Greenland Subglacial Bed Topography

评估格陵兰冰下床地形的机器学习和统计模型

• DOI: 10.1109/icmla58977.2023.00097
• 发表时间: 2023
• 期刊: IEEE
• 作者: Yi, Katherine;Dewar, Angelina;Tabassum, Tartela;Lu, Jason;Chen, Ray;Alam, Homayra;Faruque, Omar;Li, Sikan;Morlighem, Mathieu;Wang, Jianwu
• 通讯作者: Wang, Jianwu

Enhanced Deep Learning Super-Resolution for Bathymetry Data

• DOI: 10.1109/bdcat56447.2022.00014
• 发表时间: 2022-12
• 期刊: 2022 IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT)
• 作者: Xingyan Li;Jian Li;Zachary Williams;Xin Huang;M. Carroll;Jianwu Wang