Artificial Intelligence Techniques for Large-Scale Surveys of Space Science Data

P. R. Gazis, NASA Ames/SJSU Foundation
A. Barnes, NASA Ames
C. Glymour, Carnegie Mellon University

Many problems in space physics require large-scale surveys of extensive data sets to identify and classify qualitative features such as shocks, discontinuities, energetic particle enhancements, or specific types of spectra. Such surveys can be difficult to accomplish using conventional programming techniques and the manpower requirements associated with direct physical examination of the relevant data sets can be prohibitive. We have applied several artificial intelligence and machine learning techniques to a representative range of problems in space science and planetary geology. We have found that these problems can be quite tractable to well-established techniques that are no longer considered state-of-the-art by the information science community. Such difficulties as occur may not involve the algorithms themselves, but are often associated with data handling, the design of preprocessors, and communication between members of the information science community and the general scientific community. We have developed a modest suite of tools that should be applicable to a broad range of problems that involve one-dimensional pattern-recognition or surveys of extended time series that would be difficult or impossible to perform using any other means. The lessons learned from this effort will be discussed.

Contact Info: P. R. Gazis
pgazis@mail.arc.nasa.gov