Collaborative Research: EarthCube Capabilities: ICESpark: An Open-Source Big Data Platform for Science Discoveries in the New Arctic and Beyond

协作研究：EarthCube 功能：ICESpark：新北极及其他地区科学发现的开源大数据平台

• 批准号: 2126449
• 负责人: Assefaw Gebremedhin
• 金额: $ 29.35万
• 依托单位: Washington State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2126449&HistoricalAwards=false
• 关键词: Collaborative; Research; EarthCube; Capabilities; ICESpark

The Arctic climate system is undergoing rapid change with rising air and sea surface temperatures, accompanied by declines in Arctic glaciers, sea ice and snow cover on land. Increases in global air temperatures and ice-sheet mass loss are driving sea level rise around the globe. Meanwhile, as the Arctic melts, maritime and commercial activities in the region are expanding, presenting new opportunities, as well as societal and cultural challenges. As Arctic regions are largely inaccessible to traditional observation techniques, satellite remote sensing systems play a key role in monitoring their essential climate variables. However, the unprecedented volume and variety of geospatial big data collected by new satellites have reached far beyond the capacity of computing platforms accessible to most geoscientists. This gap between data growth and data discovery capacity significantly undermines the value of emerging big datasets. Moreover, most existing software for geospatial big data do not offer advanced analytical capabilities to facilitate geoscience discoveries. The project aims to remove these barriers by developing a low-cost and large-scale system, namely ICESpark, to seamlessly support the lifecycle of big data enabled geoscience research in the New Arctic and beyond. The results may improve the well-being of citizens by addressing key climate change questions, including extreme events, natural disasters, sea-level rise, drought, and wildfires. It will also improve science and engineering education via development of new course materials, cross-training of students from computing and geosciences fields, as well as an ICESpark webinar series.ICESpark is a distributed platform that can combine local commodity computers into a powerful environment that is ready for geospatial big data (GeoBD). Built on Apache Sedona, ICESpark first develops data integration and cleaning tools to harness a wide variety of GeoBD across geoscience domains including oceanography, cryospheric science and ecology. Moreover, ICESpark provides a scalable data discovery layer to efficiently identify all coincidental data across streams from heterogeneous sensing platforms (e.g., ICESat-2, Jason-3, Sentinel-3, GEDI) under various conditions. Third, ICESpark offers advanced data analytics capabilities, including a geo-feature identification system and a geo-pattern mining package, to equip geoscientists with geophysical or statistical tools to examine complex relationships and patterns embedded in GeoBD. To enhance research infrastructure, ICESpark will provide a variety of pre-packed front-ends including Jupyter notebooks as well as interoperation with EarthCube’s QGreenland, improving the accessibility to the system across broad disciplinary communities. The system will also be open-sourced and follow the EarthCube GeoCODES Dataset schema for long-term sustainability. The multidisciplinary team will work together on the design and development of ICESpark and optimize it to harness GeoBD and tackle challenging geoscience problems.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.

北极气候系统正在经历快速变化，空气和海洋表面温度上升，伴随着北极冰川、海冰和陆地积雪的减少。全球气温上升和冰盖质量损失正在推动全球海平面上升。与此同时，随着北极的融化，该地区的海事和商业活动正在扩大，带来了新的机遇，也带来了社会和文化的挑战。由于传统观测技术在很大程度上无法进入北极地区，卫星遥感系统在监测其基本气候变量方面发挥了关键作用。然而，新卫星收集的地理空间大数据的数量和种类前所未有，远远超出了大多数地球科学家可以使用的计算平台的能力。数据增长和数据发现能力之间的差距极大地削弱了新兴大数据集的价值。此外，大多数现有的地理空间大数据软件不提供先进的分析能力来促进地球科学的发现。该项目旨在通过开发一种低成本、大规模的系统，即ICESpark，来消除这些障碍，以无缝支持新北极及其他地区的大数据地球科学研究的生命周期。研究结果可能通过解决关键的气候变化问题（包括极端事件、自然灾害、海平面上升、干旱和野火）来改善公民的福祉。它还将通过开发新的课程材料，对计算机和地球科学领域的学生进行交叉培训，以及ICESpark网络研讨会系列，来改善科学和工程教育。ICESpark是一个分布式平台，可以将本地商用计算机组合成一个强大的环境，为地理空间大数据（GeoBD）做好准备。基于Apache Sedona， ICESpark首先开发了数据集成和清理工具，以利用各种地球科学领域的GeoBD，包括海洋学，冰冻圈科学和生态学。此外，ICESpark提供了一个可扩展的数据发现层，可以在各种条件下有效识别来自异构传感平台（如ICESat-2、Jason-3、Sentinel-3、GEDI）的所有数据流。第三，ICESpark提供先进的数据分析功能，包括地理特征识别系统和地理模式挖掘包，为地球科学家提供地球物理或统计工具，以检查嵌入在GeoBD中的复杂关系和模式。为了加强研究基础设施，ICESpark将提供各种预先打包的前端，包括Jupyter笔记本，以及与EarthCube的QGreenland的互操作，提高系统在广泛学科社区的可访问性。该系统还将是开源的，并遵循EarthCube GeoCODES数据集模式，以实现长期可持续性。多学科团队将共同致力于ICESpark的设计和开发，并对其进行优化，以利用GeoBD解决具有挑战性的地球科学问题。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

Spatial-Net: A Self-Adaptive and Model-Agnostic Deep Learning Framework for Spatially Heterogeneous Datasets

Spatial-Net：用于空间异构数据集的自适应且与模型无关的深度学习框架

• DOI: 10.1145/3474717.3483970
• 发表时间: 2021
• 期刊: Proceedings of the 29th International Conference on Advances in Geographic Information Systems (SIGSPATIAL'21
• 作者: Xie, Yiqun;Jia, Xiaowei;Bao, Han;Zhou, Xun;Yu, Jia;Ghosh, Rahul;Ravirathinam, Praveen
• 通讯作者: Ravirathinam, Praveen