PyDEC: Software and Algorithms for Discretization of Exterior Calculus

  • Authors:
  • Nathan Bell;Anil N. Hirani

  • Affiliations:
  • Google Inc.;University of Illinois at Urbana-Champaign

  • Venue:
  • ACM Transactions on Mathematical Software (TOMS)
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

This article describes the algorithms, features, and implementation of PyDEC, a Python library for computations related to the discretization of exterior calculus. PyDEC facilitates inquiry into both physical problems on manifolds as well as purely topological problems on abstract complexes. We describe efficient algorithms for constructing the operators and objects that arise in discrete exterior calculus, lowest-order finite element exterior calculus, and in related topological problems. Our algorithms are formulated in terms of high-level matrix operations which extend to arbitrary dimension. As a result, our implementations map well to the facilities of numerical libraries such as NumPy and SciPy. The availability of such libraries makes Python suitable for prototyping numerical methods. We demonstrate how PyDEC is used to solve physical and topological problems through several concise examples.