IEEE Geoscience and Remote Sensing Magazine - June 2016 - 73

content and pigments to vegetation properties (such as LAI,
chlorophyll content, or fluorescence) from multi- and hyperspectral sensors, as well as estimating atmospheric parameters (such as temperature, moisture, and ozone) from
infrared sounders.
This article has taken a step forward by introducing
and illustrating two relevant uses of GP technology: 1) by
studying the important issue of passing from regression to
causation from empirical data, and 2) by considering the
approximating physically based RTMs with GPs. Both approaches, yet in their infancy, are promising ways to develop flexible statistical models that discover and incorporate physical knowledge about the problem. More exciting
developments are envisioned in the intersection of physics
and machine intelligence.
acKnoWLedgmentS
The authors wish to acknowledge the collaboration, comments, and fruitful discussions had with many researchers
during the last decade on GP models for remote sensing
and geoscience applications, including Miguel LázaroGredilla (Vicarious), Robert Jenssen (University of Tromsø, Norway), Martin Jung (Max Planck Institute, Jena,
Germany), and Salcho Salcedo-Saez (University of Alcalá,
Madrid, Spain). This article has been partially supported
by the Spanish Ministry of Economy and Competitiveness
(MINECO) under project TIN2012-38102-C03-01 and
by the European Research Council (ERC) Consolidator
Grant ERC-2014-CoG-647423. The authors also wish to
acknowledge the MINECO for the FEDER-funded project
GEOLEARN with TIN2015-64210-R.
aUthor information
Gustau Camps-Valls (gcamps@uv.es) received a B.Sc.
degree in physics in 1996 and in electronics engineering
in 1998 and a Ph.D. degree in physics in 2002, all from
the Universitat de València. He is currently an associate
professor (hab. full professor) in the Department of Electronics Engineering. He is a research coordinator in the
Image and Signal Processing group. He has been a visiting
researcher at the Remote Sensing Laboratory, University
Trento, Italy, in 2002; the Max Planck Institute for Biological Cybernetics, Tübingen, Germany, in 2009; and an
invited professor at the École Polytechnique Fédérale de
Lausanne, Switzerland, in 2013. He is the coauthor of 120
journal papers, more than 150 conference papers, and 20
international book chapters, and his interests are in the
development of machine-learning algorithms for geoscience and remote sensing data analysis. He is a Senior
Member of the IEEE. For further details, see http://www.
uv.es/gcamps.
Jochem Verrelst (jverrelst@uv.es) received the M.Sc.
degree in tropical land use and in geoinformation science,
both in 2005, and the Ph.D. degree in remote sensing in
2010 from Wageningen University, The Netherlands. His
dissertation focused on the spaceborne spectrodirectional
JUNE 2016

ieee Geoscience and remote sensing magazine

estimation of forest properties. During 2010-2012, he
was a Marie Curie Postdoctoral Fellow at the Laboratory for Earth Observation, Image Processing Laboratory, University of Valencia, Spain, where he is currently
employed. He is involved in preparatory activities of the
European Space Agency's Eighth Earth Explorer Fluorescence Explorer. His research interests include the retrieval
of vegetation properties using airborne and satellite data,
canopy radiative transfer modeling, and hyperspectral
data analysis.
Jordi Muñoz-Marí (jordi@uv.es) received the B.Sc. degree in physics, the M.Sc. degree in electronics engineering,
and the Ph.D. degree in electronics engineering from the
Universitat de València, Spain, in 1993, 1996, and 2003, respectively. Currently, he is an associate professor with the
Electronics Engineering Department, Universitat de València, where he teaches electronic circuits and programmable
logical devices, digital electronic systems, and microprocessor electronic systems. He has been a visiting researcher at
the Remote Sensing Laboratory, University of Trento, Italy,
in 2003 and an invited professor at the Laboratory of Geographic Information Systems of the École Polytechnique
Fédérale de Lausanne, Switzerland, in 2013. His research
interests are tied to the development of machine-learning
algorithms for signal and image processing. He is coauthor
of 34 journal papers, 50 conference papers, and four international book chapters.
Valero Laparra (lapeva@uv.es) received a B.Sc. degree
in telecommunications engineering in 2005, a B.Sc. degree
in electronics engineering in 2007, a B.Sc. degree in mathematics in 2010, and a Ph.D. degree in computer science
and mathematics in 2011. He is a postdoc in the Image
and Signal Processing group at Universitat de València, and
currently doing a research stay in the Laboratory for Computer Vision at New York University. For further details, see
http://www.uv.es/lapeva.
Fernando Mateo-Jiménez (fmateo@uv.es) received a
degree in telecommunication engineering from the Polytechnic University of Valencia, Spain, in 2005 and a Ph.D.
degree in electronics engineering from the same university
in 2012. He has carried out research stays in several research
centers and universities such as Delft University of Technology, The Netherlands; Aalto University, Helsinki, Finland;
and CERN, Geneva, Switzerland. At present, he works as
a data scientist at the Intelligent Data Analysis Laboratory,
University of València. He is author or coauthor of approximately 50 international peer-reviewed journal articles or
book chapters. His research focuses on data mining and
preprocessing, feature selection, machine-learning models
both for regression and classification, clustering, and timeseries forecasting.
José Gómez-Dans (j.gomez-dans@ucl.ac.uk) received the M.Eng. and Ph.D. degrees in electronic engineering from the University of Sheffield, United Kingdom. His Ph.D. thesis dealt with the use of polarimetric
interferometry in synthetic aperture radar data to monitor
75

http://www.B.Sc http://www.M.Sc http://www.B.Sc http://www.B.Sc http://www.B.Sc http://www.B.Sc http://www.uv.es/lapeva http://www http://www.uv.es/gcamps http://www.M.Sc

Table of Contents for the Digital Edition of IEEE Geoscience and Remote Sensing Magazine - June 2016