How to Optimize Multispecies Set Predictions in Presence-Absence Modeling ?

TL;DR

This paper introduces MaxExp, a novel decision-driven binarization framework for multispecies presence-absence modeling that maximizes evaluation metrics without calibration data, improving ecological inference especially with imbalanced data.

Contribution

The paper presents MaxExp and SSE, new methods for binarizing species distribution models that outperform traditional heuristics and calibration approaches.

Findings

MaxExp consistently outperforms traditional thresholding methods.

SSE provides a computationally efficient alternative with competitive performance.

Methods are validated across diverse ecological case studies.

Abstract

Species distribution models (SDMs) commonly produce probabilistic occurrence predictions that must be converted into binary presence-absence maps for ecological inference and conservation planning. However, this binarization step is typically heuristic and can substantially distort estimates of species prevalence and community composition. We present MaxExp, a decision-driven binarization framework that selects the most probable species assemblage by directly maximizing a chosen evaluation metric. MaxExp requires no calibration data and is flexible across several scores. We also introduce the Set Size Expectation (SSE) method, a computationally efficient alternative that predicts assemblages based on expected species richness. Using three case studies spanning diverse taxa, species counts, and performance metrics, we show that MaxExp consistently matches or surpasses widely used thresholding and calibration methods, especially under strong class imbalance and high rarity. SSE offers a simpler yet competitive option. Together, these methods provide robust, reproducible tools for multispecies SDM binarization.