@Article{DiPaoloGoFePaViSa:2019:DaMiSp,
author = "Di Paolo, Italo F. and Gouveia, Nelson de Almeida and Ferreira
Neto, Luiz C. and Paes, Eduardo T. and Vijaykumar, Nandamudi
Lankalapalli and Santana, {\'A}damo L.",
affiliation = "{Universidade Estadual do Par{\'a} (UEPA)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and {Universidade Federal
do Par{\'a} (UFPA)} and {Universidade Federal Rural da
Amaz{\^o}nia (UFRA)} and {Instituto Nacional de Pesquisas
Espaciais (INPE)} and {Universidade Federal do Par{\'a} (UFPA)}",
title = "Data mining of spatio-temporal variability of chlorophyll-a
concentrations in a portion of the Western Atlantic with low
performance hardware",
journal = "Journal of Software Engineering and Applications",
year = "2019",
volume = "12",
number = "5",
pages = "149--170",
keywords = "Data Mining, Clustering, Chlorophyll, Atlantic, Missing Data,
Small Hardware.",
abstract = "The contemporary scientific literature that deals with the
dynamics of marine chlorophyll-a concentration is already
customarily employing data mining techniques in small geographic
areas or regional samples. However, there is little focus on the
issue of missing data related to chlorophyll-a concentration
estimated by remote sensors. Intending to provide greater scope to
the identification of the spatiotemporal distribution patterns of
marine chlorophyll-a concentrations, and to improve the
reliability of results, this study presents a data mining approach
to cluster similar chlorophyll-a concentration behaviors while
implementing an iterative spatiotemporal interpolation technique
for missing data inference. Although some dynamic behaviors of
said concentrations in specific areas are already known by
specialists, systematic studies in large geographical areas are
still scarce due to the computational complexity involved. For
this reason, this study analyzed 18 years of NASA satellite
observations in one portion of the Western Atlantic Ocean,
totaling more than 60 million records. Additionally, performance
tests were carried out in low-cost computer systems to check the
accessibility of the proposal implemented for use in computational
structures of different sizes. The approach was able to identify
patterns with high spatial resolution, accuracy and reliability,
rendered in low-cost computers even with large volumes of data,
generating new and consistent patterns of spatiotemporal
variability. Thus, it opens up new possibilities for data mining
research on a global scale in this field of application.",
doi = "10.4236/jsea.2019.125010",
url = "http://dx.doi.org/10.4236/jsea.2019.125010",
issn = "1945-3116",
label = "lattes: 2893215729403643 2 DiPaoloGoNePaViSa:2019:DaMiSp",
language = "pt",
targetfile = "paolo_data.pdf",
urlaccessdate = "2024, May 04"
}