Adaptive refinement for eigenvalue problems based on an associated source problem

Abstract

We introduce an adaptive finite element scheme for the efficient approximation of a (large) collection of eigenpairs of selfadjoint elliptic operators in which the adaptive refinement is driven by the solution of a single source problem -- the so-called landscape problem for the operator -- instead of refining based on the computed eigenpairs. Some theoretical justification for the approach is provided, and extensive empirical results indicate that it can provide an attractive alternative to standard adaptive schemes, particularly in the hp-adaptive environment.