Abstract
Overfitting the training data is a common problem in supervised machine learning. When dealing with a remote sensing inverse problem, the PAR, overfitting prevents GP evolved models to be successfully applied to real data. We propose to use a classic method of overfitting control by the way of a validation set. This allows to go backward in the evolution process in order to retrieve previous, not yet overfitted models. Although this “backwarding” method performs well on academic benchmarks, there is not enough improvement to deal with the PAR. A new backwarding criterion is then derived using real satellite data and the knowledge of plausible physical bounds for the PAR coefficient in the geographical area that is monitored. This leads to satisfactory GP models and drastically improved images.
Keywords
- Genetic Programming
- Radiation Problem
- Genetic Programming Model
- Genetic Programming Algorithm
- Genetic Programming Approach
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
J. Quinlan. Induction of decision trees. Machine Learning, 1(1):81–106, 1986.
J. Quinlan. Rule induction with statistical data–a comparison with multiple regression. Journal of Operation Research Society, 38:347–352, 1987.
Tom Michael Mitchell. Machine Learning. Mc Graw-Hill, 1997.
Wolfgang Banzhaf, Peter Nordin, Robert Keller, and Frank Francone. Genetic Programming, An Introduction. Morgan Kaufmann, 1999.
Cyril Fonlupt and Denis Robilliard. Genetic programming with dynamic fitness for a remote sensing application. In [12], pages 191–200, 2000.
John Koza. Genetic Programming II: Automatic Discovery of Reusable Programs. The MIT Press, 1994.
A. Morel. Optical modeling of the upper ocean in relation to its biogenous matter content (case I waters). Journal of Geophysical Research, C9(93):10479–10768, 1988.
A. Morel. Light and marine photosynthesis: a spectral model with geochemical and climatological implications. Prog. Oceanogr., 26:263–306, 1991.
Malik Chami. Développement d’un code de transfert radiatif pour le système océanatmosphère. Application au détroit du Pas de Calais. PhD thesis, Université du Littoral–Côte d’Opale, 1997. in French.
M. Chami, E. Dilligeard, and R. Santer. A radiative transfer model for the computation of radiance and polarization in an ocean-atmosphere system. polarization properties of suspended matter for remote sensing purposes. 2000. To appear in Applied Optics.
Emmanuel Devred. Estimation du PAR (Photosynthetically Active Radiation) dans les eaux du cas II par télédétection spatiale. PhD thesis, Université du Littoral–Côte d’Opale, France, 2001. In French.
Marc Schoenaueur, Kalyanmo Deb, Günter Rudolph, Xin Yao, Evelyne Lutton, Juan Julian Merelo, and Hans-Paul Schwefel, editors. Parallel Problem Solving from Nature VI, volume 1917 of Lecture Notes in Computer Science, Paris, France, September 2000. Springer.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-VerlagBerlin Heidelberg
About this paper
Cite this paper
Robilliard, D., Fonlupt, C. (2002). Backwarding: An Overfitting Control for Genetic Programming in a Remote Sensing Application. In: Collet, P., Fonlupt, C., Hao, JK., Lutton, E., Schoenauer, M. (eds) Artificial Evolution. EA 2001. Lecture Notes in Computer Science, vol 2310. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46033-0_20
Download citation
DOI: https://doi.org/10.1007/3-540-46033-0_20
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43544-0
Online ISBN: 978-3-540-46033-6
eBook Packages: Springer Book Archive