NASA GRANT HELPS RESEARCHERS REMOTELY
UNLOCK MYSTERIES OF WATER ON MARS
Lunar and Planetary Institute Collaborates with UH to Develop
Automated Tools Characterizing Martian Landscape
HOUSTON, July 31, 2006 – A mission to Mars requires an estimated
six-month voyage from Earth, but researchers at the University of
Houston and the Lunar and Planetary Institute (LPI) have found a
way to study its landscape without having to take that long trip.
Ricardo Vilalta, a UH computer scientist, has joined forces with
Tomasz Stepinski of the LPI to develop new computational tools to
characterize large portions of the Martian landscape. The duo’s
work is being funded by a three-year, quarter million dollar grant
from NASA’s Applied Information Systems Department titled
“Automated Identification and Characterization of Landforms
on Mars.” Stepinski is the principal investigator.
Founded in 1968, the LPI conducts research in lunar, planetary and
terrestrial sciences on behalf of university science departments
and NASA. Part of the Universities Space Research Association (USRA),
the LPI is a NASA-funded research institute in Houston, dedicated
to studies of the solar system, its evolution and formation. The
USRA was chartered in 1969 as the LPI’s parent organization,
and its role is to provide a mechanism through which universities
can cooperate effectively with one another, the government and other
organizations to further space science and technology, as well as
promote education in these areas.
This most recent project between UH and LPI seeks to identify natural
landscape structures, such as the inside of craters, valley networks,
the outside and inside rims of craters, the rims of inside craters
and inter-crater plains. Identifying these structures is important
because rocks, minerals and geologic landforms hold clues to past
water activity on Mars. Understanding the history of water on Mars
is a part of NASA’s long-term Mars Exploration Program.
“Currently, there’s a lack of automated tools designed
to assist planetary scientists with analyzing the surface of Mars,
and only a small percentage of the data collected has been analyzed,”
said Vilalta, an assistant professor and co-director of the UH Data
Mining and Machine Learning Group. “In fact, most of the latest
work is based on a method known as descriptive geomorphology, essentially
consisting of narrating what is in a picture. The scientific community
needs automated methods to look for complex patterns across Mars’
Combining techniques from data mining, machine learning and geomorphology,
Vilalta and his research group are in charge of providing novel
data analysis methods for the analysis of Mars’ surface. His
research specifically involves analyzing massive amounts of data
with the goal of extracting meaningful and informative patterns.
Stepinski, then, processes all data obtained from the Mars Orbiter
Laser Altimeter instrument aboard NASA’s Mars Global Surveyor
spacecraft. This data are subsequently used to construct global
topographic maps of Mars in the form of digital elevation models.
“From a data mining point of view, the project is generating
novel and computationally challenging techniques,” Vilalta
said. “For example, we are looking for new techniques to classify
the surface of Mars with minimal expert intervention. Using a technique
known as semi-supervised learning, we are exploiting information
from very few regions of Mars and using that to label large portions
of the planet’s surface.”
The Data Mining and Machine Learning Group at UH aims to develop
data analysis techniques with applications that challenge problems
in physics, geology, astronomy, environmental sciences and medicine.
The group’s work includes the design and development of a
statistical-learning tool (STL) for classification and characterization
of topographical features on Mars. This STL automates geomorphic
mapping and expedites geologic mapping, thus enabling fast and quantitative
characterization of large sections of the Martian surface.
About the University of Houston
The University of Houston, Texas’ premier metropolitan research
and teaching institution, is home to more than 40 research centers
and institutes and sponsors more than 300 partnerships with corporate,
civic and governmental entities. UH, the most diverse research university
in the country, stands at the forefront of education, research and
service with more than 35,000 students.
About the College of Natural Sciences and Mathematics
The UH College of Natural Sciences and Mathematics, with nearly
400 faculty members and approximately 4,000 students, offers bachelors,
masters and doctoral degrees in the natural sciences, computational
sciences and mathematics. Faculty members in the departments of
biology and biochemistry, chemistry, computer science, geosciences,
mathematics and physics have internationally recognized collaborative
research programs in association with UH interdisciplinary research
centers, Texas Medical Center institutions and national laboratories.
To receive UH science news via e-mail, visit www.uh.edu/admin/media/sciencelist.html.
For more information about UH visit the university’s ‘Newsroom’