** Next:** Parameter Selection
** Up:** Alvarez: Genetic Algorithm Inversion
** Previous:** Introduction

A genetic algorithm is an optimization method inspired by evolution and
survival of the fittest. A trial solution to the problem is constructed in
the form of a suitably encoded string of model parameters, called an
*individual*. A collection of individuals is in turn called a
*population*. There are several considerations and choices to be made in
order to implement a suitable solution to an optimization problem using
genetic algorithms. A full description of all the practical details is
outside the scope of this paper, and some of them are a matter of active
research Beasley et al. (1993); Falkenauer (1998); Gen and Cheng (2000); Haupt and Haupt (1998). In Appendix A I
give a brief description of the most relevant issues of genetic algorithm
optimization as used in this study. In particular, I describe model-parameter
encoding as well as standard and non-standard operators (selection, jump and
creep mutation, crossover, elitism and niching), fitness function and
convergence criteria.

** Next:** Parameter Selection
** Up:** Alvarez: Genetic Algorithm Inversion
** Previous:** Introduction
Stanford Exploration Project

11/11/2002