CC* Data Storage: Cardinal Academic Research Data Storage (CARDS)

该项目在路易斯维尔大学建立了红衣主教学术研究数据存储(CADS)基础设施。IC卡允许管理和共享PB级的机构数据，消除了现有的存储性能瓶颈，并支持跨各种优先领域的研究，包括人工智能和机器学习、数字病理学、空间观察、癌症生长模拟和材料建模。此外，CADS通过将拥有大型数据集的领域科学家与统计学、工程学和计算机科学系聚集在一起，增强数据分析和知识发现，促进了教职员工之间的校园内合作。卡片中积累的信息为研究生创建跨学科项目提供了丰富的资源，将卡片整合到当地REU网站项目中可以扩大全国本科生可以获得的课程。通过允许测试和开发用于分布式数据存储平台的新的动态缓存和分层技术，卡是实现最先进的科学和工程进步的关键。卡片中的数据有助于创建独特的人工智能模型，以增强自主系统中的导航、避障和路径规划，以及改进数字病理的图像分析。CADES促进了新的基于机器学习的冠状物质抛射事件检测机制的产生，以及使用计算建模评估冠状动脉阻塞的非侵入性方法。CARDS能够为癌症化疗和肿瘤生长生成计算模型，并为纳米电子、神经形态计算和能量存储领域的下一代应用程序生成新的高性能材料。该奖项由高级网络基础设施办公室颁发，由既定的刺激竞争研究计划(EPSCoR)共同支持。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This project establishes the Cardinal Academic Research Data Storage (CARDS) infrastructure at the University of Louisville. CARDS allows the management and sharing of petabyte-scale institutional data, eliminates existing storage performance bottlenecks, and supports research across various priority areas including artificial intelligence and machine learning, digital pathology, space observation, cancer growth simulation, and materials modeling. In addition, CARDS promotes intra-campus collaborations among faculty by bringing domain scientists with large datasets together with statistics, engineering, and computer science faculty for enhanced data analysis and knowledge discovery. The information accumulated in CARDS provides a rich resource to create cross-disciplinary projects for graduate students, and integrating CARDS into local REU site programs scales the offerings available to undergraduate students nationwide. CARDS is critical to enable scientific and engineering advances in the state-of-the-art by allowing the testing and development of new dynamic caching and tiering techniques for distributed data storage platforms. The data in CARDS helps create unique artificial intelligence models for enhanced navigation, obstacle avoidance, and path planning in autonomous systems, as well as improved image analysis for digital pathology. CARDS facilitates the production of new machine learning based detection mechanisms for coronal mass ejection events, and non-invasive methods to assess blocked coronary arteries using computational modeling. CARDS enables the generation of computational models for cancer chemotherapy and tumor growth, and novel, high-performance materials for next-generation applications in nano-electronics, neuromorphic computing, and energy storage.This award by the Office of Advanced Cyberinfrastructure is jointly supported by the Established Program to Stimulate Competitive Research (EPSCoR).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.