Novel Algorithm for Mining ENSO-Oriented Marine Spatial Association Patterns from Raster-Formatted Datasets

The ENSO (El Niño Southern Oscillation) is the dominant inter-annual climate signal on Earth, and its relationships with marine environments constitute a complex interrelated system. As traditional methods face great challenges in analyzing which, how and where marine parameters change when ENSO events occur, we propose an ENSO-oriented marine spatial association pattern (EOMSAP) mining algorithm for dealing with multiple long-term raster-formatted datasets. EOMSAP consists of four key steps. The first quantifies the abnormal variations of marine parameters into three levels using the mean-standard deviation criteria of time series; the second categorizes La Niña events, neutral conditions, or El Niño events using an ENSO index; then, the EOMSAP designs a linking–pruning–generating recursive loop to generate (m + 1)-candidate association patterns from an m-dimensional one by combining a user-specified support with a conditional support; and the fourth generates strong association patterns according to the user-specified evaluation indicators. To demonstrate the feasibility and efficiency of EOMSAP, we present two case studies with real remote sensing datasets from January 1998 to December 2012: one considers performance analysis relative to the ENSO-Apriori and Apriori methods; and the other identifies marine spatial association patterns within the Pacific Ocean.

[1]  Ravindra Patel,et al.  USE OF OBJECT-ORIENTED CONCEPTS IN DATABASES FOR EFFECTIVE MINING , 2009 .

[2]  Leila Maria Garcia Fonseca,et al.  GeoDMA - Geographic Data Mining Analyst , 2013, Comput. Geosci..

[3]  Yo-Ping Huang,et al.  Efficient mining of salinity and temperature association rules from ARGO data , 2008, Expert Syst. Appl..

[4]  Francisco P. Chavez,et al.  Physical‐biological synchrony in the global ocean associated with recent variability in the central and western equatorial Pacific , 2013 .

[5]  Ramakrishnan Srikant,et al.  Fast algorithms for mining association rules , 1998, VLDB 1998.

[6]  Jian Pei,et al.  Mining frequent patterns by pattern-growth: methodology and implications , 2000, SKDD.

[7]  Shu-Hsien Liao,et al.  Data mining techniques and applications - A decade review from 2000 to 2011 , 2012, Expert Syst. Appl..

[8]  Thomas M. Smith,et al.  Improved Extended Reconstruction of SST (1854–1997) , 2004 .

[9]  Yong Han,et al.  Seasonal-to-decadal modes of global sea level variability derived from merged altimeter data , 2010 .

[10]  Yuh-Jiuan Tsay,et al.  CBAR: an efficient method for mining association rules , 2005, Knowl. Based Syst..

[11]  Vipin Kumar.  Discovery of Patterns in Global Earth Science Data Using Data Mining , 2010, PAKDD.

[12]  Antonio J. Busalacchi,et al.  Remote sensing of the Indo-Pacific region: ocean colour, sea level, winds and sea surface temperatures , 2004 .

[13]  Grégoire Mercier,et al.  Multiscale Event-Based Mining in Geophysical Time Series: Characterization and Distribution of Significant Time-Scales in the Sea Surface Temperature Anomalies Relatively to ENSO Periods from 1985 to 2009 , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[14]  Qing Dong,et al.  A mutual-information-based mining method for marine abnormal association rules , 2015, Comput. Geosci..

[15]  Kevin E. Trenberth,et al.  The Definition of El Niño. , 1997 .

[16]  Wilfred Ng,et al.  Correlated pattern mining in quantitative databases , 2008, TODS.

[17]  Bo Wu,et al.  Contrast of Rainfall-SST Relationships in the Western North Pacific between the ENSO-Developing and ENSO-Decaying Summers* , 2009 .

[18]  Chenghu Zhou,et al.  A data-mining approach to determine the spatio-temporal relationship between environmental factors and fish distribution , 2004 .

[19]  Wilfred Ng,et al.  An information-theoretic approach to quantitative association rule mining , 2008, Knowledge and Information Systems.

[20]  Michael H. Glantz,et al.  ENSO as an Integrating Concept in Earth Science , 2006, Science.

[21]  K. Wolter,et al.  El Niño/Southern Oscillation behaviour since 1871 as diagnosed in an extended multivariate ENSO index (MEI.ext) , 2011 .

[22]  Robert F. Adler,et al.  ENSO Indices Based on Patterns of Satellite-Derived Precipitation , 2000 .

[23]  Fabrice Guillet,et al.  A 2D-3D visualization support for human-centered rule mining , 2007, Comput. Graph..

[24]  R. Dickinson,et al.  The role of satellite remote sensing in climate change studies , 2013 .

[25]  Ramakrishnan Srikant,et al.  Mining quantitative association rules in large relational tables , 1996, SIGMOD '96.

[26]  Kunqing Xie,et al.  Mining geographic episode association patterns of abnormal events in global earth science data , 2008 .

[27]  Witold Pedrycz,et al.  An improved association rules mining method , 2012, Expert Syst. Appl..

[28]  Zahid Anwar,et al.  Data mining techniques and applications — A decade review , 2017, 2017 23rd International Conference on Automation and Computing (ICAC).

[29]  Paul C. Fiedler,et al.  ENSO variability and the eastern tropical Pacific: A review , 2006 .

[30]  C. McClain,et al.  The calibration and validation of SeaWiFS data , 2000 .

[31]  Li Guangqiang,et al.  Events-coverage based spatio-temporal association rules mining method , 2010 .

[32]  Dong Qing,et al.  A mutual-information-based mining method for marine abnormal association rules , 2015 .

[33]  K. Casey,et al.  Sea surface temperature and sea surface height variability in the North Pacific Ocean from 1993 to 1999 , 2002 .

[34]  Thomas M. Smith,et al.  An Improved In Situ and Satellite SST Analysis for Climate , 2002 .

[35]  Jian Huang,et al.  Data Mining in Earth System Science (DMESS 2011) , 2011, ICCS.

[36]  Yang Hong,et al.  Precipitation Extremes Estimated by GPCP and TRMM: ENSO Relationships , 2007 .

[37]  Richard Chbeir,et al.  A New Time Series Mining Approach Applied to Multitemporal Remote Sensing Imagery , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[38]  Qing Dong,et al.  Spatiotemporal association patterns of multiple parameters in the northwestern Pacific Ocean and their relationships with ENSO , 2014 .

[39]  Yin-Fu Huang,et al.  Generalized association rule mining using an efficient data structure , 2011, Expert Syst. Appl..

[40]  Christophe Rigotti,et al.  Unsupervised Spatiotemporal Mining of Satellite Image Time Series Using Grouped Frequent Sequential Patterns , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[41]  A. Govardhan,et al.  AN OBJECT -ORIENTED MODELING AND IMPLEMENTATION OF SPATIO -TEMPORAL KNOWLEDGE DISCOVERY SYSTEM , 2011 .

[42]  Thomas M. Smith,et al.  Reconstruction of near‐global annual precipitation using correlations with sea surface temperature and sea level pressure , 2009 .

[43]  Ian T. Jolliffe,et al.  Empirical orthogonal functions and related techniques in atmospheric science: A review , 2007 .

[44]  S. Cherry.  Some Comments on Singular Value Decomposition Analysis , 1997 .