发表机构
MIT; University of Wyoming; Marburg University; Fondazione Edmund Mach; UCSB; Queensland University of Technology; Scripps Institution of Oceanography, UCSD; Colorado State University; Smithsonian NCBI; Yale; Harvard; University of St. Andrews; UNIS; Giraffe Conservation Foundation; NTU Singapore; Max Planck Institute of Animal Behavior; UC Berkeley; Senckenberg Biodiversity and Climate Research Centre; NCSU; NC Museum of Natural Sciences（麻省理工学院; 怀俄明大学; 马尔堡大学; 埃德蒙·马赫基金会; 加州大学圣巴巴拉分校; 昆士兰理工大学; 加州大学圣迭戈分校斯克里普斯海洋研究所; 科罗拉多州立大学; 史密森尼国家自然历史博物馆; 耶鲁大学; 哈佛大学; 圣安德鲁斯大学; 斯瓦尔巴大学中心; 长颈鹿保护基金会; 新加坡南洋理工大学; 马克斯·普朗克动物行为研究所; 加州大学伯克利分校; 森肯伯格生物多样性与气候研究中心; 北卡罗来纳州立大学; 北卡罗来纳自然科学博物馆）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MoveBench是首个大规模野生动物移动预测基准，含260万GPS点和16亿环境瓦片，提出概率评估协议，发现现有方法对时间泛化优于个体泛化，深度学习不总优于基线，协变量选择影响性能。
AI 中文摘要
理解并预测野生动物移动对于生态学和保护至关重要。虽然轨迹预测在人类和车辆移动方面已取得进展，但野生动物轨迹呈现出独特的挑战：它们在空间上不受约束、高度随机，并受环境条件影响。我们推出MoveBench，这是首个大规模概率性野生动物移动预测基准，包含来自127个国家110个物种800多个个体的260万条GPS定位数据，并配有16亿个环境栅格瓦片，涵盖160个已知或被认为影响移动的协变量。我们提出了一种用于移动轨迹预测的概率性评估协议，解决了点预测指标在固有随机现象中的局限性。通过对四个方法族在多个时间和空间尺度上的全面实证评估，我们揭示：（1）现有预测方法对未来时间点的泛化能力优于对未见个体的泛化能力，（2）深度学习方法并不始终优于更简单的基线方法，（3）环境协变量的选择显著影响性能。MoveBench实现了移动预测方法的标准化评估，并为这一具有生态重要性的任务的方法论进展奠定了基础。
英文摘要
Understanding and predicting wildlife movement is critical for ecology and conservation. While trajectory forecasting has advanced for human and vehicle movement, wildlife trajectories present distinct challenges: they are unconstrained in space, highly stochastic, and influenced by environmental conditions. We introduce MoveBench, the first large-scale benchmark for probabilistic wildlife movement forecasting, containing 2.6M GPS locations from 800+ individuals across 110 species in 127 countries, paired with 1.6B environmental raster tiles capturing 160 covariates known or hypothesized to influence movement. We propose a probabilistic evaluation protocol for movement trajectory forecasts, addressing limitations of point-prediction metrics for inherently stochastic phenomena. Through comprehensive empirical evaluation of four method families across multiple temporal and spatial scales, we reveal that: (1) existing predictive methods generalize better to future timepoints than to unseen individuals, (2) deep learning approaches do not consistently outperform simpler baselines, and (3) environmental covariate selection significantly impacts performance. MoveBench enables standardized evaluation of movement forecasting methods and provides a foundation for methodological advances on this ecologically important task.
CommentsPre-release preprint
