Scientific data management in the coming decade Export

@article{citeulike:475195, abstract = {Scientific instruments and computer simulations are creating vast data stores that require new scientific methods to analyze and organize the data. Data volumes are approximately doubling each year. Since these new instruments have extraordinary precision, the data quality is also rapidly improving. Analyzing this data to find the subtle effects missed by previous studies requires algorithms that can simultaneously deal with huge datasets and that can find very subtle effects --- finding both needles in the haystack and finding very small haystacks that were undetected in previous measurements.}, address = {New York, NY, USA}, author = {Gray, Jim and Liu, David T. and Santisteban, Maria N. and Szalay, Alex and DeWitt, David J. and Heber, Gerd}, citeulike-article-id = {475195}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1107503}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1107499.1107503}, doi = {10.1145/1107499.1107503}, issn = {0163-5808}, journal = {SIGMOD Rec.}, keywords = {data-intensive, parallelism, science, semantic}, month = {December}, number = {4}, pages = {34--41}, posted-at = {2006-11-14 12:51:23}, priority = {0}, publisher = {ACM}, title = {Scientific data management in the coming decade}, url = {http://dx.doi.org/10.1145/1107499.1107503}, volume = {34}, year = {2005} }

TY - JOUR ID - citeulike:475195 L3 - citeulike-article-id:475195 N2 - Scientific instruments and computer simulations are creating vast data stores that require new scientific methods to analyze and organize the data. Data volumes are approximately doubling each year. Since these new instruments have extraordinary precision, the data quality is also rapidly improving. Analyzing this data to find the subtle effects missed by previous studies requires algorithms that can simultaneously deal with huge datasets and that can find very subtle effects --- finding both needles in the haystack and finding very small haystacks that were undetected in previous measurements. IS - 4 JF - SIGMOD Rec. SN - 0163-5808 AD - New York, NY, USA EP - 41 TI - Scientific data management in the coming decade PB - ACM VL - 34 SP - 34 KW - data-intensive KW - parallelism KW - science KW - semantic AU - Gray, Jim AU - Liu, David AU - Santisteban, Maria AU - Szalay, Alex AU - DeWitt, David AU - Heber, Gerd PY - 2005/12// UR - http://dx.doi.org/10.1145/1107499.1107503 ER -