# SAGE: A sampling-aware global evaluation benchmark for species distribution modeling

arXiv: https://arxiv.org/abs/2609.31082 · HTML: https://mlsanity.com/paper/2609.31082/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 90 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning](https://mlsanity.com/paper/1609.06570/) (2016)
- [Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks](https://mlsanity.com/paper/2310.06743/) (2023)
- [Spatial Implicit Neural Representations for Global-Scale Species Mapping](https://mlsanity.com/paper/2306.02564/) (2023)
- [Deep Multi-Species Embedding](https://mlsanity.com/paper/1609.09353/) (2016)
- [GeoPlant: Spatial Plant Species Prediction Dataset](https://mlsanity.com/paper/2408.13928/) (2024)
- [Combining Observational Data and Language for Species Range Estimation](https://mlsanity.com/paper/2410.10931/) (2024)
- [On the selection and effectiveness of pseudo-absences for species distribution modeling with deep learning](https://mlsanity.com/paper/2401.02989/) (2024)
- [Area under the ROC Curve has the Most Consistent Evaluation for Binary Classification](https://mlsanity.com/paper/2408.10193/) (2024)
- [DivShift: Exploring Domain-Specific Distribution Shifts in Large-Scale, Volunteer-Collected Biodiversity Datasets](https://mlsanity.com/paper/2410.19816/) (2024)
- [CISO: Species Distribution Modeling Conditioned on Incomplete Species Observations](https://mlsanity.com/paper/2508.06704/) (2025)

## Abstract (arXiv)

Knowing where species occur is fundamental for biodiversity research and conservation. Species distribution models (SDMs) link species observations to environmental conditions to estimate their spatial distribution. However, accuracy varies with the underlying data and models, making it essential to know for which species models can be trusted. Deep-learning-based SDMs ("DeepSDMs") now jointly model thousands of species, drawing on hundreds of millions of community-science records. At this scale, averaging performance hides substantial species-level variability, particularly for rare species, often of greatest conservation concern. Records are also strongly biased, making occurrence counts misleading. Accounting for these factors is essential for a reliable and informative evaluation of multi-species SDMs. Here, we introduce a Sampling-Aware Global Evaluation (SAGE) benchmark, combining GBIF records for training with sPlotOpen vegetation plots for presence-absence evaluation across 5771 plant species. We propose an evaluation framework that groups species based on two properties, sampling effort and relative prevalence, which describe how densely a species' range is sampled and how frequently the species is recorded. Evaluating single-species SDMs and multi-species DeepSDMs, we find that Random Forests and DeepSDMs perform best overall, but neither dominates: DeepSDMs outperform single-species SDMs for infrequently recorded species while offering no consistent advantage for well-sampled ones. Crucially, this advantage emerges only when established bias-correction practices, such as spatial thinning and reweighting, are carried over to the deep-learning setting. SAGE helps identify the species and data conditions for which a given approach is beneficial, thereby supporting the development of more transparent and ecologically credible SDMs. Data and code: https://earens.github.io/sage/