Elements: Data: HDR: Collaborative Research: Developing an On-Demand Service Module for Mining Geophysical Properties of Sea Ice from High Spatial Resolution Imagery

海冰既是气候变化的指示器，也是气候变化的放大器。目前，海冰观测有多种来源，这些来源来自各种传感器网络（原位、机载和星载）。通过开发一种智能网络基础设施元素，用于分析海冰上的高空间分辨率（HSR）遥感图像，科学界能够更好地提取重要的地球物理参数，用于气候建模。该项目为海冰界提供了新的领域知识。这是通过整合时空离散的高铁图像来实现的，以产生更快速和可靠的冰类型识别，并通过标准化的图像处理来创建兼容的海冰产品。网络基础设施模块是一种增值的按需网络服务，可以与现有基础设施自然集成。关键目标是开发一种可靠、高效的按需开放地理空间联盟网络服务，该服务能够在有限的人为干预下从高铁图像中提取有关水、淹没冰、裸冰、融化池、变形“脊”冰、脊影和其他信息的准确地理知识。嵌入式时空分析框架提供了对离散高铁图像及其他相关遥感数据和野外数据的搜索、探索、可视化、组织和分析功能。该项目通过整合计算机视觉和机器学习算法、计算资源、高铁图像数据和其他有用的数据集，为北极海冰社区创建了一个数据和知识网络服务。概念模型改进了数据流，因此用户可以查询数据、下载增值数据，并在各种信息源之间获得更一致的结果。这为科学分析创造了新的机会，可以最大限度地减少处理复杂和时空离散的高铁图像的时间投资。该项目包括通过课程开发、研究生和本科生参与研究以及为K-12教师提供夏季讲习班（由其他机构资助）来强调下一代劳动力的教学和发展。收集到的图像和图像分析结果将通过NSF北极数据中心及时与公众分享。该奖项由先进网络基础设施办公室颁发，由EarthCube和位于美国国家科学基金会地球科学理事会的极地项目北极自然科学项目办公室共同支持。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。

Sea ice acts as both an indicator and an amplifier of climate change. At present, there are multiple sources of sea ice observations which are obtained from a variety of networks of sensors (in situ, airborne, and space-borne). By developing a smart cyberinfrastructure element for the analysis of high spatial resolution (HSR) remote sensing images over sea ice, the science community is better able to extract important geophysical parameters for climate modeling. The project contributes new domain knowledge to the sea ice community. This is accomplished by integrating HSR images that are spatiotemporally discrete to produce a more rapid and reliable identification of ice types, and by a standardized image processing that allows creating compatible sea ice products. The cyberinfrastructure module is a value-added on-demand web service that can be naturally integrated with existing infrastructure.The key objective is to develop a reliable and efficient on-demand Open Geospatial Consortium-compliant web service, which is capable of extracting accurate geographic knowledge of water, submerged ice, bare ice, melt ponds, deformed 'ridging' ice, ridge shadows, and other information from HSR images with limited human intervention. The embedded spatial-temporal analysis framework provides functions to search, explore, visualize, organize, and analyze the discrete HSR images and other related remote sensing data and field data. The project creates a data and knowledge web service for the Arctic sea ice community by integrating computer vision and machine learning algorithms, computing resources, and HSR image data and other useful datasets. The conceptual model improves data flow, so users would query data, download value-added data, and have more consistent results across various sources of information. This creates new opportunities for scientific analysis that minimizes the investment of time in processing complex and spatiotemporally-discrete HSR imagery. The project includes a strong emphasis on teaching and development of the next-generation workforce through course curricula development, involvement of graduate and undergraduate students in research, and the offering of summer workshops for K-12 teachers (funded by other agencies). The collected images and results of the image analyses will be shared with the public in a timely manner through the NSF Arctic Data Center.This award by the Office of Advanced Cyberinfrastructure is jointly supported by EarthCube and the Office of the Polar Programs Arctic Natural Sciences Program, within the NSF Directorate for Geosciences.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.