Modeling movement probabilities within heterogeneous spatial fields

Abstract

Recent efforts have focused on modeling the internal structure of space-time prisms to estimate the unequal movement opportunities within. This paper further develops this area of research by formulating a model for field-based time geography that can be used to probabilistically model movement opportunities conditioned on underlying heterogeneous spatial fields. The development of field-based time geography draws heavily on well-established methods for cost-distance analysis, common to most GIS software packages. The field-based time geographic model is compared with two alternative approaches that are commonly employed to estimate probabilistic space-time prisms - (truncated) Brownian bridges and time geographic kernel density estimation. Using simulated scenarios it is demonstrated that only field-based time geography captures underlying heterogeneity in output movement probabilities. Field-based time geography has significant potential in the field of wildlife tracking (an example is provided), where Brownian bridge models are preferred, but fail to adequately capture underlying barriers to movement.