@article{gray2005scientific,
author = {Gray, Jim},
title = {Scientific Data Management in the Coming Decade},
year = {2005},
month = {January},
abstract = {This is a thought piece on data-intensive science requirements for databases and science centers. It argues that peta-scale datasets will be housed by science centers that provide substantial storage and processing for scientists who access the data via smart notebooks. Next-generation science instruments and simulations will generate these peta-scale datasets. The need to publish and share data and the need for generic analysis and visualization tools will finally create a convergence on common metadata standards. Database systems will be judged by their support of these metadata standards and by their ability to manage and access peta-scale datasets. The procedural stream-of-bytes-file-centric approach to data analysis is both too cumbersome and too serial for such large datasets. Non-procedural query and analysis of schematized self-describing data is both easier to use and allows much more parallelism.},
url = {http://approjects.co.za/?big=en-us/research/publication/scientific-data-management-in-the-coming-decade/},
pages = {35-41},
journal = {ACM SIGMOD Record},
volume = {34},
number = {4},
note = {also as MSR-TR-2005-10},
}