Asteroid Data Hunter

The Asteroid Data Hunter challenge tasks competitors to develop significantly improved algorithms to identify asteroids in images from ground-based telescopes. The winning solution must increase the detection sensitivity, minimize the number of false positives, ignore imperfections in the data, and run effectively on all computers.
 

Project Background

In this challenge, we are tasking competitors with developing a significantly improved algorithm to identify asteroids in images from ground-based telescopes. The winning solution will increase the detection sensitivity, minimize the number of false positives, ignore imperfections in the data, and run effectively on all computers

Asteroids pose both a possible threat and an opportunity for Earth: they could impact us, causing damage, OR possibly be mined for resources that could help extend our ability to explore the universe.

Since 1998 NASA has led the global search for Near Earth Objects (NEOs) through its Near Earth Object Observation Program. NASA has also led the federal government in researching how crowdsourcing can help solve tough problems through efforts like the NASA Tournament Lab (NTL) supported through a contract with Harvard University and topcoder.

This fits in perfectly with Planetary Resources’ mission, which is to harness the resources in NEOs to extend humanity’s economic sphere of influence into the Solar System – so naturally, a non-exclusive partnership between Planetary Resources and NASA was developed with the goal of working together to improve asteroid detection by using crowd sourced algorithms.

Scientists find asteroids by taking images of the same place in the sky and find the starlike objects that move. With many telescopes scanning the sky during the time around the new moon, the data volumes prevent individual inspection of every image.

Traditionally, the identification of asteroids and other moving bodies in the Solar System has been achieved by acquiring images over several epochs and detecting changes between frames. This general approach has been used since before the discovery of Pluto and continues to this day.

With the vast amount of data available now flowing from modern instruments, there is no good way for professional astronomers to verify every detection. In particular, looking in the future as large surveys grow ever larger, the ability to autonomously and rapidly check the images and determine which objects are suitable for follow up will be crucial.

There is a long history to adapting programs to find these moving objects with some improvements along the way. For example, the Catalina Sky Survey (CSS) uses a crowded field galaxy photometry program (Source Extractor) that identifies centroids of targets that are distinctly separate from other objects. This output is fed into a custom program that sees which sources move. However, analysis implies that at best the CSS data pipeline is 80 – 90% accurate and there are (based on CSS discovery numbers) several thousand additional objects that could be recovered per year.

Starting from a fresh position allows specific optimizations of data analysis, which would be useful as a general moving object pipeline system for other observatories as well.

Partnership between NASA & Planetary Resources

NASA and Planetary Resources Inc., are partnering to develop crowd-sourced software solutions to enhance detection of Near-Earth Objects (NEOs) using NASA-funded data. The agreement is NASA’s first partnership associated with NASA’s Asteroid Grand Challenge.

Planetary Resources will facilitate the use of NASA-funded sky survey data and help support the algorithm competition and review results. NASA will develop and manage the contests and explore use of the best solutions for enhancing existing survey programs.

Through NASA’s asteroid initiative, NASA is enhancing its ongoing efforts to identify and characterize Near-Earth Object’s (NEOs) for scientific investigation, find asteroids potentially hazardous to Earth and find candidates viable for redirection to a stable orbit near the moon as a destination for exploration by astronauts.

The algorithm contests are managed and executed by NASA’s Center of Excellence for Collaborative Innovation (CoECI). CoECI was established at the request of the White House Office of Science and Technology Policy to advance NASA open innovation efforts and extend that expertise to other federal agencies. CoECI uses the NASA Tournament Lab (NTL) for its advanced algorithmic and software development contests. Through its contract with Harvard Business School in association with Harvard’s Institute of Quantitative Social Sciences, NTL uses the topcoder platform to enable a community of over 600,000 competitors to create the most innovative, efficient and optimized solutions for specific, real-world challenges faced by NASA.

High Level Requirements

This challenge will devise a solution that improves moving object routines, both in terms of absolute efficiency, but also decrease computation requirements to allow more modest machines to adequately perform moving object detection.

The following requirements must be met:

  • Properly ignore imperfections and artifacts in the data.
  • Identify moving objects utilizing a time series of four images of the sky
  • Recover the accurate astrometry of the moving object (RA, Dec, etc.)

Atomized Project Plan

So what’s coming up, and how do I register? Simply select any of the contest names below to find out more about each specific contest, and register to participate.

Name Contest Type Start End
GUI Wireframes Wireframes 08/11/2014 08/25/2014
Phase 2 – Marathon Match Marathon Match 08/11/2014 9/16/2014
Create Storyboards (UI Design) Application Front-End Design 08/27/2014 09/13/2014
System Architecture Architecture 09/30/2014 10/16/2014
App Development Assembly Competition 10/18/2014 11/03/2014
Integration with DS9 Visualizer Assembly Competition 11/04/2014 11/20/2014
Bug Hunt Bug Hunt 11/21/2014 11/28/2014
Fix Defects Assembly Competition 11/30/2014 12/16/2014
Project Completion 12/22/2014

 

*PLEASE NOTE: The contest start and end dates are estimates only, and may shift forward or backwards depending on contest progress. To verify a contest start date, please select the contest name to view the registration page.

 

Resources

Project Personnel

Chris Lewicki
President & Chief Asteroid Miner
Planetary Resources

Mr. Lewicki has been intimately involved with the lifecycle of NASA’s Mars Exploration Rovers and the Phoenix Mars Lander. Lewicki performed system engineering development and participated in Show more

Matthew Beasley
Senior Optical Systems Engineer, Staff Astronomer
Planetary Resources

Dr. Matthew Beasley is a core team member at Planetary Resources, Inc. He completed a Ph.D. in Astrophysics at the University of Colorado at Boulder. He was the Principal Investigator of the University of Colorado ultraviolet sounding rocket program and oversaw six Show more

.

Karim R. Lakhani
Lumry Family Associate Professor of Business Administration, Harvard Business School
Principal Investigator, Harvard-NASA Tournament Lab at the Institute for Quantitative Social Science.

Karim R. Lakhani is the Lumry Family Associate Professor of Business Administration at the Harvard Business School and the Principal Investigator of the Harvard-NASA Tournament Lab at the Institute for Quantitative Show more

Rinat Sergeev
Data Scientist, Harvard-NASA Tournament Lab
Institute of Quantitative Social Sciences, Harvard

Dr. Rinat Sergeev is a Data Scientist at the Harvard-NASA Tournament Lab (NTL). Rinat works as a lead science and technical expert on exploring and utilizing crowdsourcing approaches in application to Big Data challenges,Show more

Jason Crusan
Director, Advanced Exploration Systems Division
NASA Human Exploration and Operations Mission Directorate

As Director for the Advanced Exploration Systems (AES) Division with the Human Exploration and Operations Mission Directorate (HEOMD) at the National Aeronautics and Space Administration (NASA), Jason Crusan is the senior executive, manager, principle advisor and advocate on technology Show more

Tim Spahr
Director, Minor Planet Center
Harvard-Smithsonian Center for Astrophysics

Dr. Tim Spahr has been studying asteroids and comets since the early 1990s, and his personal interest in these objects started 15 years before that. Spahr is the Director of the International Astronomical Union Minor Show more

Victoria Friedensen
Program Lead, Robotic Precursor Mission
NASA Advanced Exploration Systems Division

Victoria Pidgeon Friedensen is a member of the Advanced Exploration Systems Division at NASA HQ and leads the Robotic Precursor Activities domain: a diverse portfolio of flight system and instrument development Show more

Partnerships


Top