Digging deeper: deep joint species distribution modeling reveals environmental drivers of Earthworm Communities

2025-06-16

AI Summary

This study investigates the combined climatic, edaphic, and land-use drivers shaping earthworm community distributions across broad spatial scales to assess the potential impacts of global change on soil ecosystems. Method: We developed the first multi-species, multi-task deep learning model specifically designed for earthworm communities, enabling simultaneous historical and contemporary distribution predictions for 77 species across France. The framework integrates SHAP-based interpretability analysis, functional trait clustering, and joint feature extraction to disentangle shared versus species-specific environmental responses. Contribution/Results: The model achieves a True Skill Statistic (TSS) ≥ 0.7 and substantially improves prediction accuracy for rare species. Key drivers identified include precipitation variability, temperature seasonality, and land-use type; functional groups were delineated along an ecological strategy gradient. This interpretable, generalizable AI framework establishes a new paradigm for modeling soil animal communities under global change.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Earthworms are key drivers of soil function, influencing organic matter turnover, nutrient cycling, and soil structure. Understanding the environmental controls on their distribution is essential for predicting the impacts of land use and climate change on soil ecosystems. While local studies have identified abiotic drivers of earthworm communities, broad-scale spatial patterns remain underexplored. We developed a multi-species, multi-task deep learning model to jointly predict the distribution of 77 earthworm species across metropolitan France, using historical (1960-1970) and contemporary (1990-2020) records. The model integrates climate, soil, and land cover variables to estimate habitat suitability. We applied SHapley Additive exPlanations (SHAP) to identify key environmental drivers and used species clustering to reveal ecological response groups. The joint model achieved high predictive performance (TSS>= 0.7) and improved predictions for rare species compared to traditional species distribution models. Shared feature extraction across species allowed for more robust identification of common and contrasting environmental responses. Precipitation variability, temperature seasonality, and land cover emerged as dominant predictors of earthworm distribution. Species clustering revealed distinct ecological strategies tied to climatic and land use gradients. Our study advances both the methodological and ecological understanding of soil biodiversity. We demonstrate the utility of interpretable deep learning approaches for large-scale soil fauna modeling and provide new insights into earthworm habitat specialization. These findings support improved soil biodiversity monitoring and conservation planning in the face of global environmental change.

Problem

• Identifies environmental drivers of earthworm distribution patterns
• Predicts habitat suitability for 77 earthworm species using deep learning
• Improves soil biodiversity monitoring under climate and land use changes

Innovation

• Multi-species deep learning model predicts earthworm distributions
• SHAP analysis identifies key environmental drivers
• Species clustering reveals ecological response groups