BATIS: Bayesian Approaches for Targeted Improvement of Species Distribution Models

2025-10-22

AI Summary

Species distribution models (SDMs) often yield unreliable predictions due to spatial observation bias—particularly in data-scarce regions. To address this, we propose BATIS (Bayesian Adaptive Spatio-Temporal Integration Framework), the first SDM to systematically integrate Bayesian deep learning for joint quantification of aleatoric and epistemic uncertainty. BATIS employs a Bayesian neural network to iteratively fuse prior ecological knowledge with sparse, spatially biased eBird citizen-science observations, enabling unified representation of fine-scale local patterns and broad-scale macroecological structure—even under severe spatial bias. Evaluations demonstrate that BATIS significantly outperforms state-of-the-art SDMs in predictive accuracy and uncertainty calibration within data-sparse regions, while retaining model interpretability. This work establishes a robust, trustworthy, and auditable modeling paradigm for biodiversity monitoring and conservation decision-making.

Technology Category

• Machine Learning: Bayesian Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Species distribution models (SDMs), which aim to predict species occurrence based on environmental variables, are widely used to monitor and respond to biodiversity change. Recent deep learning advances for SDMs have been shown to perform well on complex and heterogeneous datasets, but their effectiveness remains limited by spatial biases in the data. In this paper, we revisit deep SDMs from a Bayesian perspective and introduce BATIS, a novel and practical framework wherein prior predictions are updated iteratively using limited observational data. Models must appropriately capture both aleatoric and epistemic uncertainty to effectively combine fine-grained local insights with broader ecological patterns. We benchmark an extensive set of uncertainty quantification approaches on a novel dataset including citizen science observations from the eBird platform. Our empirical study shows how Bayesian deep learning approaches can greatly improve the reliability of SDMs in data-scarce locations, which can contribute to ecological understanding and conservation efforts.

Problem

• Address spatial biases in species distribution models
• Improve model reliability in data-scarce locations
• Combine local observations with broader ecological patterns

Innovation

• Bayesian deep learning framework for species distribution models
• Iterative updating with limited observational data
• Quantifying aleatoric and epistemic uncertainty