International Journal of Advance Engineering and Research Development (IJAERD) Volume 1,Issue 5,May 2014, e-ISSN: 2348 - 4470 , print-ISSN:2348-6406 @IJAERD-2014, All rights Reserved 1 Discovery and Analysis of Ocean Climate Indices Using DSNN Clustering Algorithm Ravi D Patel 1 , Bhavesh Tamawala 2 ,Kirti Sharma 3 1 PG Scholer, CE Department, BVM Engineering College, aryanrdp@gmail.com 2 Assistant professor, CE Department, BVM Engineering College, Bhavesh.tanawala@bvmengineering.ac.in 3 Assistant professor,CE Department, B.V.M Engineering College, kirti.engineer@gmail.com Abstract—This Paper based on finding interesting spatio-tempral pattern from Earth Science data. The data consists measurements of various Earth Science variables (include Temperature and pressure) which are related with time series. Earth Science data has strong seasonal components that needs to be removed prior to pattern analysis, as the Earth Scientist are primarily interested in pattern that represent deviation from normal seasonal variations such as anomalous climate event (e.g. , E1 Nino) or tends (e.g., global warming). We used ―monthly‖ Z Score t o remove seasonality. After processing, we apply DSNN clustering algorithm to cluster the temperature time series associated with point on the ocean, yielding clusters that represent ocean regions with relatively homogeneous behavior. The centroids of these clusters are time series that summarize the behavior of these ocean areas and thus, represent potential OCIs (Ocean climate indices).To evaluate cluster centroid for their usefulness, we must determine which cluster centroids significantly influence the land area. For this task, we use variety approaches that analyze the correlation between potential OCIs and time series. Ke ywords—Time series analysis, Clustering,Earth science data, scientific data mining. I. INTRODUCTION The Land, Ocean and Atmosphere processes are highly coupled i.e. climate phenomena occurring one location can affect the climate at another location. For understanding this affect, climate teleconnection is required to finding how the Earth’s climate is changing and how global environment changes. To study teleconnection is by using climate indices, which are climate variability at a regional into a single time series i.e. Nino 1+2 indexes, which is defined as the average sea surface temperature anomaly region of the coast of Peru. Earth observation satellites or sensors are generating increasingly larger amounts of data which are combined with additional data from ecosystem models;create an opportunity forunderstanding andpredicting the behavior of the Earth’s global ecosystem or Earth’s Climate and how ecosystem responds to global environment change. However due to large amount of data, data mining techniques are used to facilitates the automatic extraction and analysis of interesting pattern from the earth science data.This data consists of sequence of global Earth snapshots of the Earth, typically available at monthly intervals, and include various land and ocean variable such as sea surface temperature (SST), pressure, Net Primary Production (NPP). NPP (Net Primary Production) is the net assimilation of atmospheric carbon dioxide (CO2) into organic matter by plants. Sea Level Pressure (SLP) and Sea Surface Temperature (SST) in Ocean region are the one on which most commonly used climate indices based. More Recently motivated by the massive amounts of new data being produced by satellite observation, Earth Scientist have been using eigenvaluesanalysis techniques such as principal components analysis (PCA) and singular value decomposition (SVD), to discover climate indices.[gcc] Because it’s have some limitation, they present an alternative cluster-based methodology for the discovery of climate indices that overcomes limitations of eigenvalues analysis techniques. In this paper, we describe a high-dimensional