Abstract
Near-Infrared reflectance spectra of planets can be used to infer surface parameters, sometimes with relevance to recent geologic history. Accurate prediction of parameters (such as composition, temperature, grain size, crystalline state, and dilution of one species within another) is often difficult because parameters manifest subtle but significant details in noisy spectral observations, because diverse parameters may produce similar spectral signatures, and because of the high dimensionality of the feature vectors (spectra). These challenges are often unmet by traditional inference methods. We retrieve two underlying causes of the spectral shapes, temperature and grain size, with an SOM-hybrid supervised neural prediction model. We achieve 83.0±2.7% and 100.0±0.0% prediction accuracy for temperature and grain size, respectively. The key to these high accuracies is the exploitation of an interesting antagonistic relationship between the nature of the physical parameters, and the learning mode of the SOM in the neural model.
This work was partially supported by grants NNG05GA63G and NNG05GA94G from the Applied Information Systems Research Program, NASA, Science Mission Directorate. Figures are in color, request color copy by email: llzhang@rice.edu, erzsebet@rice.edu
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Grundy, W.M., Schmitt, B.: The Temperature-Dependent Near-Infrared Absorption Spectrum of Hexagonal H 2 O Ice. J. Geophys. Res. 103, 25809–25822 (1998)
Grundy, W.M., Schmitt, B., Quirico, E.: The Temperature Dependent Spectrum of Methane Ice I between 0. 65 and 5 Microns and Opportunities for Near-Infrared Remote Thermometry. Icarus 155, 486–496 (2002)
Young, L.A., et al.: New Horizons: Anticipated Scientific Investigations at the Pluto System. Space Science Reviews 140, 93–127 (2008)
Reuter, D.C., et al.: Ralph: A Visible/Infrared Imager for the New Horizons Pluto/Kuiper Belt Mission. Space Science Reviews 140, 129–154 (2008)
Hapke, B.: Theory of Reflectance and Emittance Spectroscopy. Cambridge University Press, New York (1993)
Grundy, W.M., et al.: Near-Infrared Spectra of Icy Outer Solar System Surfaces: Remote Determination of H 2 O Ice Temperatures. Icarus 142, 536–549 (1999)
Gilmore, M.S., et al.: Effect of Mars Analogue Dust Deposition on The Automated Detection of Calcite in Visible/Near-Infrared Spectra. Icarus 172, 641–646 (2004)
English, E.C., Fricke, F.R.: The Interference Index and Its Prediction Using a Neural Network Analysis of Wind-tunnel Data. Journal of Wind Engineering and Industrial Aerodynamics 83, 567–575 (1999)
Gilbert, N., Terna, P.: How to Build and Use Agent-Based Models in Social Science. Mind & Society 1(1), 57–72 (2000)
Grundy, W.M.: Methane and Nitrogen Ices on Pluto and Triton: a Combined Laboratory and Telescope Investigation. PhD thesis, University of Arizona (1995)
Cruikshank, D.P., et al.: Ices on the Satellites of Jupiter, Saturn, and Uranus. In: Solar System Ices, pp. 579–606. Kluwer Academic Publishers, Dordrecht (1998)
Widrow, B., Smith, F.W.: Pattern-Recognizing Control Systems. In: Computer and Information Sciences (COINS) Symposium Proceedings, pp. 288–317. Spartan Books, Washington (1964)
Howell, E.S., Merényi, E., Lebofsky, L.A.: Classification of Asteroid Spectra Using a Neural Network. Jour. Geophys. Res. 99(E5), 10,847–10,865 (1994)
Rudd, L., Merényi, E.: Assessing Debris-Flow Potential by Using AVIRIS Imagery to Map Surface Materials and Stratigraphy in Cataract Canyon, Utah. In: Green, R. (ed.) Proc. 14th AVIRIS Earth Science and Applications Workshop, Pasadena, CA, May 24-27 (2005)
DeSieno, D.: Adding a Conscience to Competitive Learning. In: IEEE Intl Conference on Neural Networks, vol. 1, pp. 117–124 (1988)
Kohonen, T.: Self-Organizing Maps, 2nd edn. Springer, Heidelberg (1997)
Taşdemir, K., Merényi, E.: Exploiting the Data Topology in Visualizing and Clustering of Self-Organizing Maps. IEEE Trans. Neural Networks (in press, 2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, L., Merényi, E., Grundy, W.M., Young, E.F. (2009). An SOM-Hybrid Supervised Model for the Prediction of Underlying Physical Parameters from Near-Infrared Planetary Spectra. In: Príncipe, J.C., Miikkulainen, R. (eds) Advances in Self-Organizing Maps. WSOM 2009. Lecture Notes in Computer Science, vol 5629. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02397-2_41
Download citation
DOI: https://doi.org/10.1007/978-3-642-02397-2_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02396-5
Online ISBN: 978-3-642-02397-2
eBook Packages: Computer ScienceComputer Science (R0)