Gradient Symplectic Algorithms for Solving the Schroedinger Equation with Time-Dependent Potentials

Abstract

We show that the method of factorizing the evolution operator to fourth order with purely positive coefficients, in conjunction with Suzuki's method of implementing time-ordering of operators, produces a new class of powerful algorithms for solving the Schroedinger equation with time-dependent potentials. When applied to the Walker-Preston model of a diatomic molecule in a strong laser field, these algorithms can have fourth order error coefficients that are three orders of magnitude smaller than the Forest-Ruth algorithm using the same number of Fast Fourier Transforms. When compared to the second order split-operator method, some of these algorithms can achieve comparable convergent accuracy at step sizes 50 times as large. Morever, we show that these algorithms belong to a one-parameter family of algorithms, and that the parameter can be further optimized for specific applications.