Anomaly detection and spatio-temporal analysis of global climate system

ABSTRACT

Knowledge discovery from temporal, spatial and spatio-temporal data is pivotal for understanding and predicting the behavior of Earth's ecosystem model. An important influence leaving its impact on the ecosystem is the global climate system. In this paper, the Earth Science data that we have analyzed consists of daily global air temperature and precipitation measurements, aggregated from heterogeneous sensors for fifty years (1950--1999). The enormous amount of data that is available for analysis requires employment of data mining techniques for discovering interesting patterns, detecting significant changes and extracting meaningful insights from the data. Our work considers the problem of detecting anomalous (abnormal or unexpected) behavior in the global climate system, discovering teleconnection patterns and providing consequential insights to the analysts.

REFERENCES

• 1: Nabil R. Adam, Vandana Pursnani Janeja, and Vijayalakshmi Atluri. Neighborhood based detection of anomalies in high dimensional spatio-temporal sensor datasets. In SAC '04: Proceedings of the 2004 ACM symposium on Applied computing, 2004.
• 2: The ORNL 50-Year Re analysis Data Download Website. http://www.ornl.gov/sci/knowledgediscovery/SensorKDD-2009/challenge.htm.
• 3: Stephen D. Bay and Mark Schwabacher. Mining Distance-based Outliers in Near Linear Time with Randomization and a Simple Pruning Rule. In KDD '03: Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, 2003.
• 4: University of Delaware Climate Data Archives. http://climate.geog.udel.edu/~climate/html_pages/download.html.
• 5: A. R. Ganguly and K. Steinhaeuser. Data mining for climate change and impacts. In Data Mining Workshops, 2008. ICDMW '08. IEEE International Conference on, 2008.
• 6: http://en.wikipedia.org/wiki/ENSO. El niño-southern oscillation: Wikipedia entry.
• 7: http://ggweather.com/enso/oni.htm. Enso years: A consensus list.
• 8: http://www.wrcc.dri.edu/enso. El niño, la nina and the western u.s., alaska and hawaii.
• 9: Robert Kistler, Eugenia Kalnay, William Collins, Suranjana Saha, Glenn White, John Woollen, Muthuvel Chelliah, Wesley Ebisuzaki, Masao Kanamitsu, Vernon Kousky, Huug van den Dool, Roy Jenne, and Michael Fiorino. The ncep--ncar 50-year reanalysis: Monthly means cd-rom and documentation. Bulletin of the American Meteorological Society, 82, 2001.
• 10: E. M. Knorr, R. T. Ng, and V. Tucakov. Distance-based outliers: Algorithms and applications. The VLDB Journal, 8, 2000.
• 11: Vipin Kumar. High performance data mining - application for discovery of patterns in the global climate system. Book Series Lecture Notes in Computer Science, 4873, 2007.
• 12: Fan Lin, XingXing Jin, Cheng Hu, XiaoPing Gao, Kunqing Xie, and XiaoFeng Lei. Discovery of teleconnections using data mining technologies in global climate datasets. Data Science Journal, 6, 2007.
• 13: AP Newspaper Report. http://www.breitbart.com/article.php?id=D95NOGL80&show_article=1.
• 14: S. Ramaswamy, R. Rastogi, and K. Shim. Efficient algorithms for mining outliers from large data sets. SIGMOD Rec., 29, 2000.
• 15: Gao Shiying, Wang Jingshu, and Ding Yihui. The triggering effect of near-equatorial cyclones on el niño. Advances in Atmospheric Sciences, 5, 1988.
• 16: Xiuyao Song, Mingxi Wu, Christopher Jermaine, and Sanjay Ranka. Conditional anomaly detection. IEEE Trans. on Knowl. and Data Eng., 19, 2007.
• 17: Michael Steinbach, Pang-Ning Tan, Vipin Kumar, Steven Klooster, and Christopher Potter. Discovery of climate indices using clustering. In Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, 2003.
• 18: Pang-Ning Tan, Michael Steinbach, Vipin Kumar, Steven Klooster, Christopher Potter, and Alicia Torregrosa. Finding spatio-termporal patterns in earth science data: Goals, issues and results. Temporal Data Mining Workshop, KDD, 2001.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.4 INFORMATION SYSTEMS APPLICATIONS

Additional Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.8 Database applications

Keywords:
climate phenomena, data mining, distance-based outlier detection, global climate system, spatio-temporal analysis, teleconnections