# Automatic Discovery of Classification and Estimation Algorithms for Earth-Observation Satellite Imagery

Created by W.Langdon from gp-bibliography.bib Revision:1.4020

@InProceedings{riolo:1995:adcea,
author =       "Rick L. Riolo and Mark P. Line",
title =        "Automatic Discovery of Classification and Estimation
Algorithms for Earth-Observation Satellite Imagery",
booktitle =    "Working Notes for the AAAI Symposium on Genetic
Programming",
year =         "1995",
editor =       "E. V. Siegel and J. R. Koza",
pages =        "73--77",
address =      "MIT, Cambridge, MA, USA",
publisher_address = "445 Burgess Drive, Menlo Park, CA 94025, USA",
month =        "10--12 " # nov,
publisher =    "AAAI",
keywords =     "genetic algorithms, genetic programming",
URL =          "http://www.aaai.org/Papers/Symposia/Fall/1995/FS-95-01/FS95-01-010.pdf",
URL =          "http://www.aaai.org/Library/Symposia/Fall/fs95-01.php",
size =         "5 pages",
abstract =     "Under NASA's new Earth Observing System (EOS),
satellite imagery is expected to arrive back on Earth
at rates of gigabytes/day. Techniques for the
extraction of useful information from such massive data
streams must be efficient and scalable in order to
survive in petabyte archive situations, and they must
overcome the opacity inherent in the data by
classifying or estimating pixels according to
user-specified categories such as crop-type or forest
health. We are in the process of applying GP to several
related satellite remote sensing (RS) classification
and estimation problems in such a way as to surmount
the usual obstacles to large-scale exploitation of
imagery. The fitness functions used for training are
based on how well the discovered programs perform on a
set of cases from Landsat Thematic Mapper (TM) imagery.
Programs are rated on how well they perform on
out-of-training-set samples of cases from the same
imagery. We have carried out a number of preliminary
experiments on a relatively simple binary
classification task. Each case is a set of 7 spectral
intensity readings for a pixel and an associated ground
truth class: 1 for surface water, 0 for none. The GP
system very rapidly discovers simple relations that
correctly predict 98percent plus for training and
testing data sets. The key problem with the results we
have observed so far is that the simple solutions
rapidly drive out diversity in the population. Several
approaches will be taken in further study in order to
try to maintain diversity in the population.",
notes =        "AAAI-95f GP. Part of \cite{siegel:1995:aaai-fgp} {\em
Telephone:} 415-328-3123 {\em Fax:} 415-321-4457 {\em
email} info@aaai.org {\em URL:} http://www.aaai.org/",
}



Genetic Programming entries for Rick L Riolo Mark P Line

Citations