Walks on Primes in Imaginary Quadratic Fields

We generalize the Gaussian moat problem to the finitely many imaginary quadratic fields exhibiting unique factorization in their integers. We map this problem to the Euclidean minimum spanning tree problem and use Delaunay triangulation and Kruskal’s algorithm to find moats in these fields in $O(\mathrm{\mid }\mathbf{P}\mathrm{\mid }\log \mathrm{\mid }\mathbf{P}\mathrm{\mid })$ time, where $\mathbf{P}$ denotes the set of primes we are searching through. Our algorithm uses symmetry and boundaries to correctly and efficiently identify all moats, in order of increasing length, along with the farthest prime reached for each moat, in an underlying unbounded graph of infinite primes. We also derive asymptotic estimates on the density of primes in certain imaginary quadratic fields. Based on this and symmetry arguments, we conjecture that for a given step bound $k$, we can travel farther away from the origin in $\mathbb{Z}[i]$ and $\mathbb{Z}\left[\frac{-1+\sqrt{-3}}{2}\right]$ than in $\mathbb{Z}[\sqrt{-2}]$. This conjecture is corroborated by our computational results.