Spatio-temporal Shared-Field Modeling of Beluga and Bowhead Whale Sightings Using a Joint Marked Log-Gaussian Cox Process

2025-12-06

AI Summary

This study addresses the challenge of sparse and heterogeneous survey data for beluga and bowhead whales in U.S. Arctic waters. We propose a multi-species joint-marked log-Gaussian Cox process (LGCP) model. Methodologically, we employ a shared anisotropic Matérn Gaussian latent field—constructed via the stochastic partial differential equation (SPDE) approach on an ocean-constrained triangular mesh—to capture common spatial structure, while incorporating species-specific environmental covariate responses and seasonal effects to jointly infer distribution and abundance. Bayesian inference is performed efficiently using integrated nested Laplace approximation (INLA). Results identify persistent, cross-species hotspots over multiple years and clearly reveal divergent responses of the two species to sea ice concentration, bathymetry, and other environmental drivers. This framework is the first to integrate a shared latent field with species-specific marking mechanisms within the LGCP paradigm, substantially enhancing robustness and ecological interpretability in multi-species modeling under sparse marine survey conditions.

Technology Category

• Machine Learning: Bayesian Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Web Mining and Content Analysis: Models for Web evolution

Abstract

We analyze a decade of aerial survey whale sighting data (2010-2019) to model the spatio-temporal distributions and group sizes of beluga (Delphinapterus leucas) and bowhead (Balaena mysticetus) whales in the United States Arctic. To jointly model these species, we develop a multi-species Log-Gaussian Cox Process (LGCP) in which species specific intensity surfaces are linked through a shared latent spatial Gaussian field. This structure allows the model to capture broad spatial patterns common to both species while still accommodating species level responses to environmental covariates and seasonal variation. The latent field is represented using the Stochastic Partial Differential Equation (SPDE) approach with an anisotropic Matern covariance, implemented on an ocean constrained triangulated mesh so that spatial dependence aligns with marine geography. Whale group size is incorporated through a marked point process extension with species specific negative binomial marks, allowing occurrence and group sizes to be jointly analyzed within a unified framework. Inference is carried out using the Integrated Nested Laplace Approximation (INLA), enabling efficient model fitting over a decade of survey effort. The results highlight persistent multi-species hotspots and distinct environmental associations for each species, demonstrating the value of shared field LGCPs for joint species distribution modeling in data sparse and heterogeneous survey settings.

Problem

• Models joint spatio-temporal distribution of beluga and bowhead whales
• Incorporates group sizes within a unified marked point process framework
• Enables efficient inference in data-sparse Arctic marine survey settings

Innovation

• Multi-species LGCP with shared latent spatial field
• SPDE approach with anisotropic Matern covariance on mesh
• Marked point process with negative binomial marks