Spatio-Temporal Data Mining For Global Scale Eco-Climatic Data

National Science Foundation Award Number: #0713227 (August 1, 2007 - July 31, 2010)

Contact Information:

Vipin Kumar, PI
Department of Computer Science and Engineering
4-192, EE/CSci Building
University of Minnesota
Minneapolis, MN 55455
Phone (612) 625 0726
E-mail: kumar at cs.umn.edu URL: http://www.cs.umn.edu/~kumar

Michael Steinbach, Co-PI
Department of Computer Science and Engineering
5-225 E, EE/CSci Building
University of Minnesota
Minneapolis, MN 55455
Phone (612) 625-7503
E-mail: steinbach at cs.umn.edu URL: http://www.cs.umn.edu/~steinbac

List of Supported Students and Staff:

Graduate Students:

Shyam Boriah

Project Award Information:

Award Number:# 0713227
Duration: August 1, 2007 - July 31, 2010
Title: III-CTX: Collaborative Research: Spatio-Temporal Data Mining For Global Scale Eco-Climatic Data
Award Abstract : http://www.nsf.gov/awardsearch/showAward.do?AwardNumber=0713227
Keywords: data mining, data mining applications, data analysis, spatio-temporal data, Earth science

Project Summary:

Our work involves the analysis of high-resolution spatio-temporal vegetation data (EVI) collected by the moderate resolution imaging spectroradiometer (MODIS). Specifically, the data being studied are ecological and climatological variables collected by NASA’s earth-observing satellites. An important problem under consideration is the study of land-use change. Determining where, when, and why natural ecosystem conversions occur is a crucial concern for Earth Scientists because characteristics of the land cover can have important impacts on local climate, radiation balance, biogeochemistry, hydrology, and the diversity and abundance of terrestrial species. Consequently, understanding trends in land cover conversion at local scales is a requirement for making useful quantitative predictions about other regional and global changes.

Duration: 3 years.

Publications:

S. Boriah, V. Kumar, M. Steinbach, C. Potter, and S. Klooster. Land Cover Change Detection: A Case Study. Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2008.
S. Boriah, V. Kumar, M. Steinbach, P. Tan, C. Potter, and S. Klooster. Detecting Ecosystem Disturbances and Land Cover Change using Data Mining. In H. Kargupta, J. Han, P. Yu, R. Motwani, and V. Kumar, editors, Next Generation of Data Mining, CRC Press, 2008.

Research Contributions:

Our project activities in Year 1 have focused on the development of novel algorithms for mining global scale eco-climatic data that addresses the following issues:

1.    Development of the recursive merging change detection algorithm.
2.    Analysis of EVI data for the Bay Area and all of California using traditional data mining techniques and our proposed algorithm.
3.    Comparative evaluation of a change detection algorithm proposed by us with an algorithm proposed in the Earth science community.

Contributions to Resources for Research and Education:

PIs Kumar and Steinbach co-taught introduction to data mining course at the University of Minnesota during Fall 2007. The course included several lectures on the applications of data mining to eco-climatic data as well as importance of computationally efficient algorithms due the scale of the data.