A Single Index Approach to Integrated Species Distribution Modeling for Fisheries Abundance Data

2025-09-18

AI Summary

In fisheries ecology, multi-survey abundance data suffer from bias due to inter-survey differences in fishing efficiency, and existing integrated species distribution models (ISDMs) are prone to overfitting, compromising environmental effect interpretability and cross-survey predictive performance. To address this, we propose a single-index ISDM that represents true species spatial distribution via a shared latent variable, jointly modeling spatial random effects and survey-specific catchability functions within a Bayesian framework. This formulation enforces identical, linearly interpretable environmental effects across all surveys, fundamentally mitigating overfitting. Evaluated on multi-survey Atlantic sea scallop data, our model significantly improves consistency in environmental response interpretation, accuracy in catchability estimation, and cross-survey prediction performance. It establishes a novel, interpretable, and robust paradigm for integrating heterogeneous fisheries survey data.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Bayesian Learning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

In fisheries ecology, species abundance data are often collected by multiple surveys, each with unique characteristics. This article focuses on Atlantic sea scallop abundance data along the northeast coast of the United States, collected from two bottom trawl surveys which cover a larger spatial domain but have low catch efficiency, and a dredge survey which is more efficient but limited to domains where the species are believed to be present. To model such data, integrated species distribution models (ISDMs) have been proposed to incorporate information from multiple surveys, by including common environmental effects along with correlated survey-specific spatial fields. However, while flexible, these ISDMs can be susceptible to overfitting, which can complicate interpretability of the shared environmental effects and potentially lead to poor predictive performance. To overcome these drawbacks, we introduce a novel single index ISDM, built from a single index (with spatial random effects) that represents a latent measure of the true species distribution, and survey-specific catch efficiency functions which map the single index to the survey-specific expected catch. Our results show that the single index ISDM offers more meaningful interpretations of the environmental effects and survey catch efficiency differences, while potentially achieving better predictive performance than existing ISDMs.

Problem

• Modeling fisheries abundance data from multiple surveys
• Overcoming overfitting in integrated species distribution models
• Improving interpretability of environmental effects and predictions

Innovation

• Single index model with spatial random effects
• Survey-specific catch efficiency functions mapping
• Improved interpretability and predictive performance