Geoscience Cyberinfrastructure in the Cloud: Data-Proximate Computing to Address Big Data and Open Science Challenges
Geoscience Cyberinfrastructure in the Cloud: Data-Proximate Computing to Address Big Data and Open Science Challenges
复制标题
云中的地球科学网络基础设施：通过数据近似计算应对大数据和开放科学挑战
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
M. Ramamurthy
中科院分区：
文献类型：
--
作者：
M. Ramamurthy
数据不仅是地球科学的命脉，而且在科学和社会中都已成为现代世界的货币。计算、通信和观测技术的快速发展，以及伴随而来的地球系统高分辨率建模、集合和耦合系统预测方面的进步，正在给地球科学的几乎每一个方面带来革命性的变化。来自高分辨率集合预报系统以及高光谱卫星传感器和相控阵雷达等下一代遥感系统的现代数据量令人震惊。云计算技术和工具的出现和成熟为应对大数据和开放科学挑战开辟了新的途径，以加快科学发现。人们普遍认为，随着数据量的快速增长，减少数据移动并对数据进行处理和计算尤为重要。数据提供商还需要为科学家提供一个生态系统，其中包括在同一环境或平台中执行分析、集成、解释和合成所需的数据、工具、工作流程和其他端到端应用程序和服务。不是像传统那样将数据移动到用户附近的处理系统，而是需要为数据带来处理、计算、分析和可视化-所谓的数据接近工作台能力，也称为服务器端处理。
Data are not only the lifeblood of the geosciences but they have become the currency of the modern world both in science and in society. Rapid advances in computing, communications, and observational technologies – along with concomitant advances in high-resolution modeling, ensemble and coupled-systems predictions of the Earth system – are revolutionizing nearly every aspect of the geosciences. Modern data volumes from high-resolution ensemble prediction systems and next-generation remote-sensing systems like hyper-spectral satellite sensors and phased-array radars are staggering. The advent and maturity of cloud computing technologies and tools have opened new avenues for addressing both big data and Open Science challenges to accelerate scientific discoveries. There is broad consensus that as data volumes grow rapidly, it is particularly important to reduce data movement and bring processing and computations to the data. Data providers also need to give scientists an ecosystem that includes data, tools, workflows and other end-to-end applications and services needed to perform analysis, integration, interpretation, and synthesis - all in the same environment or platform. Instead of moving data to processing systems near users, as is the tradition, one will need to bring processing, computing, analysis and visualization to data - so called data proximate workbench capabilities, also known as server-side processing.