Using machine learning to identify nontraditional spatial dependence in occupancy data

TL;DR

This paper introduces a Bayesian machine learning framework that models both traditional and nontraditional spatial dependence in occupancy data, effectively handling false absences and improving predictive accuracy.

Contribution

It combines Bayesian hierarchical modeling with machine learning to detect complex spatial dependence patterns and account for observer errors in occupancy data.

Findings

Successfully identified nontraditional spatial dependence in synthetic and real data

Enhanced predictive accuracy over traditional models

Demonstrated flexibility in modeling complex spatial patterns

Abstract

Spatial models for occupancy data are used to estimate and map the true presence of a species, which may depend on biotic and abiotic factors as well as spatial autocorrelation. Traditionally researchers have accounted for spatial autocorrelation in occupancy data by using a correlated normally distributed site-level random effect, which might be incapable of identifying nontraditional spatial dependence such as discontinuities and abrupt transitions. Machine learning approaches have the potential to identify and model nontraditional spatial dependence, but these approaches do not account for observer errors such as false absences. By combining the flexibility of Bayesian hierarchal modeling and machine learning approaches, we present a general framework to model occupancy data that accounts for both traditional and nontraditional spatial dependence as well as false absences. We demonstrate our framework using six synthetic occupancy data sets and two real data sets. Our results demonstrate how to identify and model both traditional and nontraditional spatial dependence in occupancy data which enables a broader class of spatial occupancy models that can be used to improve predictive accuracy and model adequacy.