PERCEIVE: Precipitation Data Characterization by means on Frequent Spatio-Temporal Sequences

Nowadays large amounts of climatology data, including daily precipitation data, are collected by means of sensors
located in different locations of the world. The data driven analysis of these large data sets by means of scalable
machine learning and data mining techniques allows extracting interesting knowledge from data, inferring interesting
patterns and correlations among sets of spatio-temporal events and characterizing them. In this paper, we describe
the PERCEIVE framework. PERCEIVE is a data-driven framework based on frequent spatio-temporal sequences
and aims at extracting frequent correlations among spatio-temporal precipitation events. It is implemented by
using R and Apache Spark, for scalability reasons, and provides also a visualization module that can be used to
intuitively show the extracted patterns. A preliminary set of experiments show the efficiency and the effectiveness
of PERCEIVE.