An Ecologically-Informed Deep Learning Framework for Interpretable and Validatable Habitat Mapping

TL;DR

This paper introduces ECOSAIC, an interpretable deep learning framework that classifies benthic habitats by integrating ecological principles into AI, providing meaningful habitat maps to aid conservation and management.

Contribution

The study presents a novel autoencoder-based AI framework that incorporates ecological knowledge for habitat classification, enhancing interpretability and ecological relevance.

Findings

Identified 16 benthic habitats in the Colombian Pacific Ocean.

Habitat representations aligned with ecological constraints and species requirements.

Framework demonstrated potential for ecological management and conservation.

Abstract

Benthic habitat is challenging due to the environmental complexity of the seafloor, technological limitations, and elevated operational costs, especially in under-explored regions. This generates knowledge gaps for the sustainable management of hydrobiological resources and their nexus with society. We developed ECOSAIC (Ecological Compression via Orthogonal Specialized Autoencoders for Interpretable Classification), an Artificial Intelligence framework for automatic classification of benthic habitats through interpretable latent representations using a customizable autoencoder. ECOSAIC compresses n-dimensional feature space by optimizing specialization and orthogonality between domain-informed features. We employed two domain-informed categories: biogeochemical and hydrogeomorphological, that together integrate biological, physicochemical, hydrological and geomorphological, features, whose constraints on habitats have been recognized in ecology for a century. We applied the model to the Colombian Pacific Ocean and the results revealed 16 benthic habitats, expanding from mangroves to deep rocky areas up to 1000 m depth. The candidate habitats exhibited a strong correspondence between their environmental constraints, represented in latent space, and their expected species composition. This correspondence reflected meaningful ecological associations rather than purely statistical correlations, where the habitat's environmental offerings align semantically with the species' requirements. This approach could improve the management and conservation of benthic habitats, facilitating the development of functional maps that support marine planning, biodiversity conservation and fish stock assessment. We also hope it provides new insights into how ecological principles can inform AI frameworks, particularly given the substantial data limitations that characterize ecological research.