Towards Combining Probabilistic, Interval, Fuzzy Uncertainty, and Constraints: On the Example of Inverse Problem in Geophysics

Authors

George R. Keller, The University of Texas at El PasoFollow
Scott A. Starks
Aaron Velasco, The University of Texas at El PasoFollow
Matthew Averill, The University of Texas at El Paso
Roberto Araiza, The University of Texas at El PasoFollow
Gang Xiang
Vladik Kreinovich, The University of Texas at El PasoFollow

Publication Date

4-2007

Comments

UTEP-CS-06-19b.

Original paper published in the Proceedings of the Second International Conference on Fuzzy Sets and Soft Computing in Economics and Finance FSSCEF'2006, St. Petersburg, Russia, June 28 - July 1, 2006, pp. 47-54; updated version published in IEEE Proceedings of the 12th GAMM-IMACS International Symposium on Scientific Computing, Computer Arithmetic and Validated Numerics, Duisburg, Germany, September 26-29, 2006.

Abstract

In many real-life situations, we have several types of uncertainty: measurement uncertainty can lead to probabilistic and/or interval uncertainty, expert estimates come with interval and/or fuzzy uncertainty, etc. In many situations, in addition to measurement uncertainty, we have prior knowledge coming from prior data processing, prior knowledge coming from prior interval constraints. In this paper, on the example of the seismic inverse problem, we show how to combine these different types of uncertainty.