发表机构
University of Zurich; École Polytechnique Fédérale de Lausanne; Swiss Federal Institute for Forest, Snow and Landscape Research, WSL; ETH Zürich（苏黎世大学; 洛桑联邦理工学院; 瑞士联邦森林、雪与景观研究所; 苏黎世联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SAGE基准通过结合GBIF和sPlotOpen数据评估物种分布模型，发现DeepSDMs在稀有物种上更优，但需结合偏差校正实践，以提升模型透明度和生态可信度。
AI 中文摘要
了解物种的分布位置是生物多样性研究和保护的基础。物种分布模型（SDMs）将物种观测与环境条件联系起来，以估计其空间分布。然而，模型的准确性随基础数据和模型的不同而变化，因此了解哪些物种的模型可以信赖至关重要。基于深度学习的物种分布模型（“DeepSDMs”）现在可以联合建模数千个物种，利用数亿条社区科学记录。在这种规模下，平均性能掩盖了显著的物种水平差异，特别是对于稀有物种，而这些物种往往是最需要保护的。记录也存在严重偏差，使得出现次数具有误导性。考虑这些因素对于多物种SDMs的可靠且信息丰富的评估至关重要。在此，我们引入了一个采样感知的全局评估（SAGE）基准，将用于训练的GBIF记录与用于存在-不存在评估的sPlotOpen植被样地相结合，覆盖5771种植物。我们提出了一个评估框架，根据两个属性对物种进行分组：采样努力和相对出现率，这两个属性描述了物种分布范围被采样的密度以及物种被记录的频率。通过评估单物种SDMs和多物种DeepSDMs，我们发现随机森林和DeepSDMs整体表现最佳，但两者均未占绝对优势：DeepSDMs在记录不频繁的物种上优于单物种SDMs，而在采样良好的物种上没有一致的优势。关键在于，这种优势只有在将既定的偏差校正实践（如空间稀疏化和重新加权）应用于深度学习设置时才会出现。SAGE有助于识别特定方法适用的物种和数据条件，从而支持开发更透明且生态可信的SDMs。数据和代码：此https链接。
英文摘要
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/
CommentsUnder review. Project page: https://earens.github.io/sage/
