arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.09894cs.AIcs.CYcs.LG
收藏

超越AlphaEarth:通过POI引导对比学习实现以人为中心的地理空间基础模型

Beyond AlphaEarth: Toward Human-Centered Geospatial Foundation Models via POI-Guided Contrastive Learning

Junyuan Liu, Quan Qin, Guangsheng Dong, Xinglei Wang, Jiazhuang Feng, Zichao Zeng, Tao Cheng

AI总结:

本文提出AETHER框架,通过POI引导的多模态对齐,将AlphaEarth与以人为中心的城市分析结合,提升地理空间表示的可解释性与语言可访问性。

摘要:

最近的地理空间基础模型(GFMs)生成地球表面广泛的空间表示,捕捉丰富的物理和环境模式。其中,AlphaEarth Foundation(AE)代表了重要进展,通过多源地球观测(EO)数据生成10米嵌入表示,包含多样化的环境和光谱特征。然而,此类EO驱动的表示主要编码物理和光谱模式,而非人类活动或城市语义,限制了其捕捉城市功能维度的能力,使学习的表示难以用自然语言解释或查询。本文引入AETHER(AlphaEarth-POI增强表示学习),一种轻量框架,通过POI引导的多模态对齐,将AlphaEarth与以人为中心的城市分析结合。通过强制执行跨模态AE-POI对齐和模态内多尺度一致性,AETHER整合了功能城市语义与EO驱动的表示,并将嵌入空间接地于自然语言。所得到的表示支持城市制图任务和自然语言条件的空间检索。在伦敦和新加坡的四个下游任务中,实验展示了持续的最先进性能,相对改进范围从4.5%到21.9%。此外,对齐的嵌入空间通过自然语言查询实现空间定位。通过将EO基础模型与以人为中心的语义对齐,AETHER提升了地理空间表示的可解释性,并推动地理空间表示学习向以人为中心、语言可访问的地理空间基础模型发展。

英文摘要:

Recent geospatial foundation models (GFMs) produce spatially extensive representations of the Earth's surface that capture rich physical and environmental patterns. Among them, the AlphaEarth Foundation (AE) represents a major step, generating 10 m embeddings from multi-source Earth Observation (EO) data that include diverse environmental and spectral characteristics. However, such EO-driven representations primarily encode physical and spectral patterns rather than human activities or urban semantics, limiting their ability to capture the functional dimensions of cities and making the learned representations difficult to interpret or query using natural language. We introduce AETHER (AlphaEarth-POI Enriched Representation Learning), a lightweight framework that aligns AlphaEarth with human-centered urban analysis through multimodal alignment guided by Points of Interest (POIs). By enforcing both cross-modal AE-POI alignment and intra-modal multi-scale consistency, AETHER integrates functional urban semantics with EO-driven representations and grounds the embedding space in natural language. The resulting representations support both urban mapping tasks and natural language-conditioned spatial retrieval. Experiments across four downstream tasks in Greater London and Singapore demonstrate consistent state-of-the-art performance, with relative improvements ranging from 4.5% to 21.9%. Furthermore, the aligned embedding space enables spatial localization through natural language queries. By aligning EO-based foundation models with human-centered semantics, AETHER improves the interpretability of geospatial representations and advances geospatial representation learning toward human-centered, language-accessible geospatial foundation models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑