探讨地理空间基础模型的现状，涵盖表征学习至人口动态等议题，内容源自CARTO与巴塞罗那超级计算中心（BSC）联合举办的研讨会。

Explore the state of geospatial foundation models, from representation learning to population dynamics, with insights from the CARTO & BSC workshop.

探索地理空间基础模型的现状，从表征学习到人口动态，结合CARTO与巴塞罗那超级计算中心（BSC）研讨会的洞见。简言之，从有前景的原型迈向可操作的系统仍面临重大挑战。这种动力与不确定性的结合，使该领域在当下尤为引人关注。我们确实有潜力重新思考如何分析地点、移动行为及人类活动——但同时也日益意识到，仅靠技术进步并不足够。与单一方法论趋同不同，本次会议凸显了当前正在探索的多样化路径，以及分享成功与局限的价值。特别是，讨论对比了两大类模型：一类基于地球观测数据，另一类聚焦于人口与行为动态。全天最强烈的讯息之一是，尽管地理空间基础模型的可用性正迅速提升，但在真实应用场景中的采纳却进展缓慢，且大多处于实验阶段。为弥合研究与应用之间的差距，特邀报告展示了不同的视角。Bruno Sanchez-Andrade（LGND AI）围绕“地球智能”的不同愿景展开讨论，对比了以推理为中心、嵌入为中心和检索优先三种范式。他指出，许多地理空间系统仍处于“数据丰富但信息贫乏”的状态，而可扩展的检索与索引策略或许能为实现运营级智能提供更务实的路径。Esteban Moro（东北大学）聚焦城市分析中的行为嵌入，提出了“生活方式嵌入”这一可复用的人类活动表征。其研究强调了可解释性、稳定性与公平性的重要性，尤其是在模型用于公共政策与社会干预时。Joydeep Paul（Google Research）介绍了人口动态基础模型（PDFM），展示了大规模行为嵌入如何在健康、出行与社会经济等多个领域持续提升预测、超分辨率与预测任务的表现。他的演讲表明，当基础模型被精心整合进下游工作流时，能够产生可量化的价值。 尽管进展迅速，研讨会也明确指出，广泛采纳仍面临若干障碍。第三，可解释性与可说明性仍是主要关切。缺乏透明度可能阻碍采纳，因为决策者——尤其在敏感领域——需要其输出可理解且可辩护的模型。最后，模型评估仍落后于开发进度。由于缺乏广泛接受的基准，难以评估部署准备度或公平比较不同方法。在这一整体背景下，CARTO的工作重点在于使地理空间基础模型在实践中真正可用。我们的方法包含三项互补举措：将第三方嵌入集成至CARTO工作流中，开发直接作用于嵌入的分析工具，并构建我们自身的人口动态模型。这项工作的关键推动力是我们与巴塞罗那超级计算中心长期合作。通过欧洲人工智能工厂（European AI Factory）项目，CARTO利用高性能计算基础设施，训练并评估聚焦于人口动态与人类活动模式的模型。 研讨会确认，地理空间基础模型正从探索阶段迈向更成熟的應用，但持续协作将是实现这一目标的关键。欲了解更多内容，请参阅部分研讨会演讲。其中许多最有价值的时刻来自非正式交流、共有的失败案例与开放问题。这些对话与技术突破同样重要。感谢所有演讲者与参与者，使本次研讨会成为一次富有启发性与建设性的盛会。我们期待在巴塞罗那所涌现的思想基础上继续推进。Miguel是CARTO的首席数据科学家，带领一支卓越团队，致力于为用户提供空间分析能力，并运用空间统计与机器学习技术为客户开发定制化模型。Miguel是CARTO的首席数据科学家，带领一支卓越团队，致力于为用户提供空间分析能力，并运用空间统计与机器学习技术为客户开发定制化模型。Miguel是CARTO的首席数据科学家，带领一支卓越团队，致力于为用户提供空间分析能力，并运用空间统计与机器学习技术为客户开发定制化模型。CARTO现已支持在地理空间基础模型嵌入上直接运行分析。可视化、聚类并检测变化，将空间数据转化为决策依据。将Google的PDFM嵌入集成至CARTO工作流，以增强空间模型性能。本博客展示两个使用案例，说明这些嵌入如何提升预测效果。

Explore the state of geospatial foundation models, from representation learning to population dynamics, with insights from the CARTO & BSC workshop. In short, moving from promising prototypes to operational systems remains a significant challenge. This combination of momentum and uncertainty makes the field particularly compelling today. There is clear potential to rethink how we analyze places, movement, and human activity — but also a growing awareness that technical progress alone is not enough. Rather than converging on a single methodology, the event highlighted the diversity of approaches currently being explored and the value of sharing both successes and limitations. In particular, discussions contrasted two broad families of models: those rooted in Earth observation data and those focused on population and behavioral dynamics. One of the strongest messages throughout the day was that while the availability of geospatial foundation models is increasing rapidly, adoption in real-world applications is slow and largely experimental. In an effort to overcome this gap between research and adoption, invited talks illustrated different angles. Bruno Sanchez-Andrade (LGND AI) framed the discussion around different visions of “Earth intelligence”, contrasting inference-centric, embedding-centric, and retrieval-first perspectives. He argued that many geospatial systems remain “data-rich but information-poor,” and that scalable retrieval and indexing strategies may offer a more pragmatic path toward operational intelligence. Esteban Moro (Northeastern University) focused on behavioral embeddings for urban analysis, introducing “lifestyle embeddings” as reusable representations of human activity. His work highlighted the importance of interpretability, stability, and fairness, especially when models are used to inform public policy and social interventions. Joydeep Paul (Google Research) presented the Population Dynamics Foundation Model (PDFM), showing how large-scale behavioral embeddings can consistently improve prediction, super-resolution, and forecasting tasks across domains such as health, mobility, and socioeconomics. His talk demonstrated how foundation models can generate measurable value when they are carefully integrated into downstream workflows. Despite rapid progress, the workshop made clear that several obstacles still stand in the way of widespread adoption. Third, interpretability and explainability continue to be major concerns. This lack of transparency can slow adoption, as decision-makers, especially in sensitive domains, require models whose outputs can be understood and justified. Finally, model evaluation still lags behind development. The absence of widely accepted benchmarks makes it difficult to assess readiness for deployment or to compare approaches fairly. Within this broader landscape, CARTO’s work focuses on making geospatial foundation models usable in practice. Our approach combines three complementary efforts: integrating third-party embeddings into CARTO workflows, developing analytical tools that operate directly on embeddings, and building our own models for population dynamics. A key enabler of this work is our long-standing collaboration with the Barcelona Supercomputing Center. Through the European AI Factory program, we at CARTO are using high-performance computing infrastructure to train and evaluate models focused on population dynamics and human activity patterns. The workshop confirmed that geospatial foundation models are moving from an exploratory phase toward more mature applications, but that sustained collaboration will be essential to get there. To learn more, check out some of the workshop talks here. Many of the most valuable moments came from informal exchanges, shared failure cases, and open questions. These conversations are just as important as technical breakthroughs. Thank you to all speakers and participants for making the workshop such a stimulating and constructive event. We are excited to build on the ideas that emerged in Barcelona. Miguel is Lead Data Scientist at CARTO, an amazing team working to provide spatial analytics capabilities to our users as well as to develop custom models for our customers using spatial statistics and machine learning. Miguel is Lead Data Scientist at CARTO, an amazing team working to provide spatial analytics capabilities to our users as well as to develop custom models for our customers using spatial statistics and machine learning. Miguel is Lead Data Scientist at CARTO, an amazing team working to provide spatial analytics capabilities to our users as well as to develop custom models for our customers using spatial statistics and machine learning. CARTO now lets you run analytics directly on geospatial foundation model embeddings. Visualize, cluster, and detect changes to turn spatial data into decisions. Integrate Google's PDFM embeddings into CARTO Workflows for enhanced spatial models. This blog shows two use cases on how these embeddings improve predictions.