IEEE Geoscience and Remote Sensing Magazine - June 2016 - 18

for detecting land-cover changes that exhibit diverse characteristics in different modes of representation of the data,
e.g., forest fires can be characterized as spatially coherent
objects in image-based representations and time steps with
instantaneous changes in time series-based representations. These different representations can be considered as
multiple views of the same land-cover change event in a
multiview learning framework.
coNclusioNs
This article provided a brief overview of land-cover changedetection techniques from the perspective of machine
learning. Some of the major challenges faced by traditional machine-learning techniques for detecting land-cover
changes were described. To overcome these challenges,
some of the recent advances in machine learning that are
relevant for land-cover change detection were highlighted.
These methods offer the potential to set the foundations of
novel research for global-scale land-cover change detection.
author iNFormatioN
anuj karpatne (anuj@cs.umn.edu) completed his undergraduate studies at the Indian Institute of Technology, Delhi,
with an integrated B.Tech-M.Tech degree in mathematics
and computing before joining the Ph.D. program at the University of Minnesota. He is a Ph.D. candidate in the Department of Computer Science and Engineering at the University of Minnesota, Twin Cities. He has been working with
his advisor, Prof. Vipin Kumar, on developing data-mining
algorithms for environmental applications that involve
remote sensing data, such as monitoring water dynamics,
mapping forest cover, and detecting forest fires. His thesis
has been generously funded by a University of Minnesota
Doctoral Dissertation Fellowship and a University of Minnesota Informatics Institute Fellowship.
Zhe jiang (zhe@cs.umn.edu) received his bachelor's
degree from the University of Science and Technology of
China, Hefei, in 2010. He is currently a Ph.D. candidate in
computer science at the University of Minnesota, Twin Cities, where he received the Doctoral Dissertation Fellowship
in 2015. His research interests include spatial and spatiotemporal data mining, spatial databases, and geographical
information science. He is a Student Member of the IEEE.
ranga raju vatsavai (rrvatsav@ncsu.edu) holds M.S.
and Ph.D. degrees in computer science from the University of Minnesota. He is a Chancellor's Faculty Excellence
Program Geospatial Analytics Cluster Associate Professor
in the Department of Computer Science at North Carolina
State University (NCSU), Raleigh. He works at the intersection of spatial and temporal big data management,
analytics, and high-performance computing with applications in national security, geospatial intelligence, natural
resources, climate change, location-based services, and
human terrain mapping. Before joining NCSU, he was
the lead data scientist for the Computational Sciences and
Engineering Division at Oak Ridge National Laboratory,
june 2016

ieee Geoscience and remote sensing magazine

Tennessee. He has published more than 80 peer-reviewed
articles in conferences and journals and edited two books
on Knowledge Discovery from Sensor Data. He has served on
program committees of leading international conferences,
including the Association for Computing Machinery
(ACM) Knowledge Discovery and Data Mining (KDD),
the ACM Geographic Information System, the European
Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, the Society for
Industrial and Applied Mathematics International Conference on Data Mining (SDM),
multivieW learNiNG is
the Conference on Informaparticularly relevaNt
tion and Knowledge ManageWheN the multiple vieWs
ment, and IEEE BigData. He
has cochaired several workoF the tarGet class are
shops, including the InternahiGhly heteroGeNeous
tional Conference on Data
aNd made up oF a diverse
Mining (ICDM)/Workshop
set oF Features.
on Spatial and Spatiotemporal Data Mining, the ICDM/
International Workshop on
Knowledge Discovery Using Cloud and Distributed Computing Platforms, the ACM International Conference on
Advances in Geographic Information Systems BigSpatial,
the Supercomputing/International Workshop on Big
Data Analytics: Challenges, and Opportunities, the KDD/
Workshop on Large Scale Data Mining: Theory and Applications, the KDD/Sensor-KDD, and the SDM/Analytics for
Cyber-Physical Systems.
shashi shekhar (shekhar@cs.umn.edu), a McKnight Distinguished University Professor at the University of Minnesota, Twin Cities, is a leading scholar in geographic information systems (GIS). He has coedited an encyclopedia of GIS and
coauthored a spatial databases textbook. He received the IEEE
Computer Society Technical Achievement Award and the University Consortium for Geographic Information Science
Education Award. He is a coeditor-in-chief of GeoInformatica
(Springer) and has served on the Computing Community
Consortium Council and National Academy of Science committees (Mapping Science, GEOINT Workforce). He co-organized the "From GPS and Virtual Globes to Spatial Computing 2020" workshop to catalyze community research
visions. He is a Fellow of the IEEE and the AAAS.
vipin kumar (kumarg@cs.umn.edu) received the B.E.
degree in electronics and communication engineering
from the Indian Institute of Technology Roorkee (formerly
the University of Roorkee), India, in 1977; the M.E. degree in electronics engineering from Philips International
Institute, Eindhoven, The Netherlands, in 1979; and the
Ph.D. degree in computer science from the University of
Maryland, College Park, in 1982. He is a Regents Professor at the University of Minnesota, Twin Cities, where he
holds the William Norris Endowed Chair in the Department of Computer Science and Engineering. His current
research interests include data mining, high-performance
19

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