Algorithm for overlapping estimation of common change-sets in spatial data of fixed size

TL;DR

This paper introduces a flexible scan-based method for estimating common change-sets in spatio-temporal data, effectively handling irregular shapes and multiple change regions through overlapping local estimates.

Contribution

It presents a novel overlapping estimation approach that combines local CUSUM estimates to accurately identify multiple change-sets in complex spatial data.

Findings

Method performs well in simulations

Effective for irregularly shaped change regions

Handles multiple change regions simultaneously

Abstract

We propose a flexible class of estimates for "common change in the mean" sets in spatio-temporal data. We rely on a scan type approach by subdividing the spatial observations into suitable overlapping regions to which classical CUSUM (cumulative sums) estimates may then be applied separately. The aggregated "local" estimates are used to construct consistent "global" estimates of the change set(s) by taking the overlapping structure into account. The domain and the change regions may have irregular shapes and the suggested procedure is especially suited for estimation of multiple change regions. The performance is demonstrated in a simulation study.