Case Studies Mapping Dark Matter

Edit This Case Study Record

	Mapping Dark Matter

Mapping Dark Matter

Technology Category	Analytics & Modeling - Machine Learning Analytics & Modeling - Predictive Analytics
Applicable Industries	Aerospace Software
Applicable Functions	Product Research & Development
Use Cases	Digital Twin
Services	Data Science Services Software Design & Engineering Services
Challenge	The universe is filled with 'dark matter'—invisible, heavy matter that distorts light as it travels from distant galaxies. To create an accurate map of the universe, scientists must account for the way dark matter distorts our images of space. NASA, the British Royal Astronomical Society, and the European Space Agency sponsored the Mapping Dark Matter research competition to solve this problem. Participants were given 100,000 galaxy images, blurred to simulate the effects of dark matter. They had three months to create models to find the real shapes of galaxies; their results were scored for accuracy against known measurements. Read More
About Customer	The competition was sponsored by NASA, the British Royal Astronomical Society, and the European Space Agency. These organizations are at the forefront of astronomical research and space exploration. NASA, the United States' space agency, is known for its pioneering work in space missions and scientific research. The British Royal Astronomical Society is a learned society that promotes the study of astronomy, solar-system science, geophysics, and closely related branches of science. The European Space Agency is an intergovernmental organization dedicated to the exploration of space, with 22 member states. The competition attracted 72 teams from diverse fields, including handwriting recognition and string theory, highlighting the interdisciplinary nature of the challenge. Read More
Solution	Within the first week of the competition, Martin O’Leary, a British glaciologist, had created a solution so advanced that the White House Blog announced he had 'outperformed the state-of-the-art algorithms most commonly used in astronomy.' Meanwhile, David Kirkby and Daniel Margala, cosmologists at UC Irvine, developed an artificial neural network to recognize patterns in the galaxy images. The competition saw participation from 72 teams, including experts from fields as diverse as handwriting recognition and string theory. The winning team produced a 3x increase in accuracy over the state-of-the-art benchmark that had taken NASA decades to develop. The winners were awarded a trip to present their methods to NASA and other agencies. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Analytics & Modeling - Predictive Analytics

Applicable Industries

Aerospace

Software

Applicable Functions

Product Research & Development

Use Cases

Digital Twin

Services

Data Science Services

Software Design & Engineering Services

Challenge

The universe is filled with 'dark matter'—invisible, heavy matter that distorts light as it travels from distant galaxies. To create an accurate map of the universe, scientists must account for the way dark matter distorts our images of space. NASA, the British Royal Astronomical Society, and the European Space Agency sponsored the Mapping Dark Matter research competition to solve this problem. Participants were given 100,000 galaxy images, blurred to simulate the effects of dark matter. They had three months to create models to find the real shapes of galaxies; their results were scored for accuracy against known measurements.

About Customer

The competition was sponsored by NASA, the British Royal Astronomical Society, and the European Space Agency. These organizations are at the forefront of astronomical research and space exploration. NASA, the United States' space agency, is known for its pioneering work in space missions and scientific research. The British Royal Astronomical Society is a learned society that promotes the study of astronomy, solar-system science, geophysics, and closely related branches of science. The European Space Agency is an intergovernmental organization dedicated to the exploration of space, with 22 member states. The competition attracted 72 teams from diverse fields, including handwriting recognition and string theory, highlighting the interdisciplinary nature of the challenge.

Solution

Within the first week of the competition, Martin O’Leary, a British glaciologist, had created a solution so advanced that the White House Blog announced he had 'outperformed the state-of-the-art algorithms most commonly used in astronomy.' Meanwhile, David Kirkby and Daniel Margala, cosmologists at UC Irvine, developed an artificial neural network to recognize patterns in the galaxy images. The competition saw participation from 72 teams, including experts from fields as diverse as handwriting recognition and string theory. The winning team produced a 3x increase in accuracy over the state-of-the-art benchmark that had taken NASA decades to develop. The winners were awarded a trip to present their methods to NASA and other agencies.

Impact #1	The competition attracted 72 teams from diverse fields, including handwriting recognition and string theory, highlighting the interdisciplinary nature of the challenge.
Impact #2	Martin O’Leary, a British glaciologist, created a solution so advanced that it outperformed the state-of-the-art algorithms most commonly used in astronomy.
Impact #3	David Kirkby and Daniel Margala, cosmologists at UC Irvine, developed an artificial neural network to recognize patterns in the galaxy images.

Impact #1

The competition attracted 72 teams from diverse fields, including handwriting recognition and string theory, highlighting the interdisciplinary nature of the challenge.

Impact #2

Martin O’Leary, a British glaciologist, created a solution so advanced that it outperformed the state-of-the-art algorithms most commonly used in astronomy.

Impact #3

David Kirkby and Daniel Margala, cosmologists at UC Irvine, developed an artificial neural network to recognize patterns in the galaxy images.

Benefit #1	The winning team produced a 3x increase in accuracy over the state-of-the-art benchmark.

Benefit #1

The winning team produced a 3x increase in accuracy over the state-of-the-art benchmark.

Download PDF Version

Overview

Mapping Dark Matter

Operational Impact

Quantitative Benefit