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.
Self-Supervised Representation Learning for Geospatial Objects: A Survey
College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);Lund University(隆德大学);School of Computer Science, University of Auckland(奥克兰大学计算机科学学院)
Omni Geometry Representation Learning vs Large Language Models for Geospatial Entity Resolution
School of Mathematical and Computational Sciences, Massey University(梅西大学数学与计算科学学院);School of Computer Science and Informatics, Cardiff University(卡迪夫大学计算机科学与信息学院)
为二维空间中的点生成学习友好的表示是机器学习中的一个基本且长期存在的问题。最近,提出了多尺度编码方案(诸如Space 2 Vec)以将2D空间中的任何点直接编码为高维向量,并且已成功地应用于各种(地理)空间预测任务。然而,当将位置编码模型应用于大规模真实世界GPS坐标数据集(例如,在世界各地拍摄的物种图像)-所有当前位置编码模型被设计用于编码2D(欧几里德)空间中的点而不是球面上的点,例如,地球表面为了解决这个问题,我们提出了一个多尺度的位置编码模型称为Sphere 2 V ec直接编码点坐标在一个球面上,同时避免了mapprojection失真问题。我们提供了理论证明,Sphere 2 Vec编码保留了任何两点之间的球面距离。我们还开发了一个统一的观点,基于双傅立叶球(DFS)的球面上的距离保留编码。我们将Sphere 2 V ec应用于地理感知的图像分类任务。我们的分析表明,球体2 V ec优于其他二维空间定位编码器模型,特别是在极区和数据稀疏的地区,图像分类任务,因为它的性质,球面距离的保护。
Enhancing Ride-Hailing Forecasting at DiDi with Multi-View Geospatial Representation Learning from the Web
The Hong Kong University of Science;China University of Geoscience (Wuhan) Wuhan China;Didichuxing Co.\ Ltd Beijing China;China University of Geoscience (Wuhan);Didichuxing Co.\ Ltd
Crowd-Sourced Geographies of Income: Using Google Maps Points of Interest as High-Frequency Proxies for Sub-Municipal Income Estimation in Sao Paulo, Brazil
Bowdoin College(鲍登学院);Pontifical Catholic University of Campinas(坎皮纳斯天主教大学);Pontifical Catholic University of Minas Gerais(米纳斯吉拉斯天主教大学);School of Economics and Business, Pontifical Catholic University of Campinas(坎皮纳斯天主教大学经济与商学院)
NARA: Anchor-Conditioned Representation Learning for Heterogeneous Vector Geoentities
Department of Computer Science and Engineering, University of Minnesota(明尼苏达大学计算机科学与工程系);Department of Geography and the Environment, University of Texas at Austin(德克萨斯大学奥斯汀分校地理与环境系);Novateur Research Solutions(Novateur研究解决方案)
GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models
Universidad Católica de Ávila (UCAV)(阿维拉天主教大学);Johns Hopkins University(约翰霍普金斯大学);Independent Researcher(独立研究者);Center for Geographic Analysis, Harvard University(哈佛大学地理分析中心)
OSMGraphCLIP: Learning Global Location Representations from OpenStreetMap Graphs
Harokopio University of Athens(雅典哈罗科皮奥大学);National Technical University of Athens(雅典国家技术大学);Vienna University of Technology(维也纳技术大学);National Observatory of Athens(雅典国家天文台)
Beyond Shortest Path: Agentic Vehicular Routing with Semantic Context
Institute of Computing (IC)(计算学院);Hub de Inteligência Artificial e Arquiteturas Cognitivas (H.IAAC)(人工智能与认知架构中心);Universidade Estadual de Campinas (UNICAMP)(坎皮纳斯州立大学)