IEEE Geoscience and Remote Sensing Magazine - December 2015 - 28

software AND data sets
Leonardo Feltrin,
Department of Earth Sciences, University of Western Ontario,
1151 Richmond St, London, Ontario, N6A5B7, Canada.
E-mail: lfeltrin@uwo.ca.

KNIME an Open Source Solution
for Predictive Analytics in the Geosciences

Abstract-KNIME (Konstanz Information Miner) is a
modular computational environment, which allows
easy visual assembly, interactive data analysis, and data
processing. It is an open source predictive analytics platform (released under the GNU General Public License
v3) suited to process a variety of data formats, from basic
csv or xlsx files, to more complex data structures such
as xml, url and relational databases (e.g., db2, Oracle,
MySQL). Surprisingly, it has not seen wide application
in the earth sciences. A number of case studies providing examples of geoscience data processing will benefit
both the academia and industry, very few geoscience
applications are currently reported and these are dominantly in geoinformatics. In particular, the Energy and
Mineral Exploration sectors, which make extensive use
of Exploratory Data Analysis, Machine Learning (ML)
and Data Mining (DM) software for data classification, pattern recognition and predictive modelling, will
benefit significantly from KNIME. In contrast to other
predictive analytics platforms (e.g., Orange, R, RapidMiner, Scikit-learn), what makes KNIME particularly
appealing to geoscience applications is its ability to
integrate different programming languages in the same
workflow environment, some of them like the statistical software R or Matlab are well known in the geoscience community. KNIME is supported by an extensive
community of users and developers. Since KNIME is
built on top of Eclipse it shares the benefit of a plugin architecture that makes it easily extensible, many
custom-built nodes are available and easily accessible
through the Community Contributions area.
1. INTRODUCTION
he Konstanz Information Miner is a modular (node
based) visual software environment built on top

Digital Object Identifier 10.1109/MGRS.2015.2496160
Date of publication: 3 February 2016

of the Eclipse Integrated Development Environment
(IDE). Each node performs algorithm based processing
of data and is capable of interacting with other nodes
allowing the generation and recording of complex
data processing workflows. KNIME is a powerful data
integration and predictive analytics platform. In particular, the software helps documenting the complex
steps usually carried out in pre-processing, statistical
analysis, statistical modelling and predictive analytics. Another strength is its open source collaborative
ecosystem, where contributors are free to develop new
algorithms, tools as well as data ma-nipulation or visualization methods [1].
The development of KNIME started in 2004 and
was led by a team of Silicon Valley engineers based at
University of Konstanz, in Germany, with Michael Berthold as project lead. The software found heavy use in
cheminformatics because of the level of automation
required to explore molecular structures [2]. Presently,
the tool sees at least fifty percent of the users coming
from rather different fields of science, medicine, business and social sciences. For instance The Economist
uses KNIME in customer relationship management as
well as private banks in Zürich and the Grand Casino
in Lucerne [3].
Information on KNIME is available through the web
in a multitude of avenues (e.g., a dedicated YouTube
channel: KNIME-TV; the KNIME web site: http://www.
knime.org/ and other independent communities such
as Stack-Overflow, http://stackoverflow.com/). Despite
the availability of useful resources, the dissemination
of information regarding this data analytics platform is
not reported in major stream geoscience journals and
databases. The author provides with this brief contribution an opportunity for any geoscientist to become
aware of KNIME as an open source solution for predictive analytics that is suitable to geoscience processing.
KNIME makes relatively easy the implementation of
ieee Geoscience and remote sensing magazine

december 2015

http://www http://www.knime.org/ http://www.stackoverflow.com/

Table of Contents for the Digital Edition of IEEE Geoscience and Remote Sensing Magazine - December 2015