Modelling benthic animals in space and time using Bayesian Point Process with cross validation: the case of Holoturians

TL;DR

This paper presents a Bayesian spatio-temporal modeling framework for analyzing the distribution of Holothurians in the Mediterranean, addressing challenges of presence-only data and heterogeneous sampling through advanced statistical techniques.

Contribution

It introduces a novel Log-Gaussian Cox Process model with shared spatial components and a new cross-validation method for point process predictions in marine ecology.

Findings

The model effectively captures habitat and temporal variability.

Cross-validation shows improved predictive performance over traditional methods.

The framework is computationally efficient and adaptable to heterogeneous data.

Abstract

Understanding the spatial distribution of Holothurians is an essential task for ecosystem monitoring and sustainable management, particularly in the Mediterranean habitats. However, species distribution modeling is often complicated by the presence-only nature of the data and heterogeneous sampling designs. This study develops a spatio-temporal framework based on Log-Gaussian Cox Processes to analyze Holothurians' positions collected across nine survey campaigns conducted from 2022 to 2024 near Giglio Island, Italy. The surveys combined high-resolution photogrammetry with diver-based visual censuses, leading to varying detection probabilities across habitats, especially within Posidonia oceanica meadows. We adopt a model with a shared spatial Gaussian process component to accommodate this complexity, accounting for habitat structure, environmental covariates, and temporal variability. Model estimation is performed using Integrated Nested Laplace Approximation. We evaluate the predictive performances of alternative model specifications through a novel k-fold cross-validation strategy for point processes, using the Continuous Ranked Probability Score. Our approach provides a flexible and computationally efficient framework for integrating heterogeneous presence-only data in marine ecology and comparing the predictive ability of alternative models.