Beyond AlphaEarth: Toward Human-Centered Spatial Representation via POI-Guided Contrastive Learning

• URL: http://arxiv.org/abs/2510.09894v1
• Date: Fri, 10 Oct 2025 22:20:39 GMT
• Title: Beyond AlphaEarth: Toward Human-Centered Spatial Representation via POI-Guided Contrastive Learning
• Abstract summary: AETHER (AlphaEarth-POI Enriched Representation Learning) adapts AlphaEarth to human-centered urban analysis through multimodal alignment guided by Points of Interest (POIs)<n>In Greater London, AETHER achieves consistent gains over the AE baseline, with a 7.2% relative improvement in land-use classification F1 and a 23.6% relative reduction in Kullback-Leibler divergence for socioeconomic mapping.
• Score: 0.8677773374912304
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: General-purpose spatial representations are essential for building transferable geospatial foundation models (GFMs). Among them, the AlphaEarth Foundation (AE) represents a major step toward a global, unified representation of the Earth's surface, learning 10-meter embeddings from multi-source Earth Observation (EO) data that capture rich physical and environmental patterns across diverse landscapes. However, such EO-driven representations remain limited in capturing the functional and socioeconomic dimensions of cities, as they primarily encode physical and spectral patterns rather than human activities or spatial functions. We propose AETHER (AlphaEarth-POI Enriched Representation Learning), a lightweight framework that adapts AlphaEarth to human-centered urban analysis through multimodal alignment guided by Points of Interest (POIs). AETHER aligns AE embeddings with textual representations of POIs, enriching physically grounded EO features with semantic cues about urban functions and socioeconomic contexts. In Greater London, AETHER achieves consistent gains over the AE baseline, with a 7.2% relative improvement in land-use classification F1 and a 23.6% relative reduction in Kullback-Leibler divergence for socioeconomic mapping. Built upon pretrained AE, AETHER leverages a lightweight multimodal alignment to enrich it with human-centered semantics while remaining computationally efficient and scalable for urban applications. By coupling EO with human-centered semantics, it advances geospatial foundation models toward general-purpose urban representations that integrate both physical form and functional meaning.

Related papers

• BEACON: Behavioral and Semantic Enrichment of AlphaEarth Embeddings through Tri-Modal Contrastive Learning [9.468116544984651]
  We propose BEACON, a tri-modal contrastive learning framework that aligns three views of urban space.<n> BEACON improves relative R2 over AlphaEarth by up to 43% for obesity prevalence, 34% for poor mental health, and 22% for median household income.<n>These findings highlight the value of augmenting geospatial foundation models with semantic and behavioral signals.
  arXiv  Detail & Related papers  (2026-08-30T04:46:23Z)
• MoRAX: Mobility-based Representation Augmentation for Geospatial Foundation Models [0.37650120899162426]
  MoRAX is a framework for augmenting geospatial embeddings with functional structure derived from human mobility.<n>Across four target cities spanning two countries, the MoRAX teacher model consistently outperforms GFMs and strong urban representation baselines.
  arXiv  Detail & Related papers  (2026-08-18T14:44:41Z)
• Human-Centric Intelligence in the Era of Foundation Models: A Survey [159.29291047252138]
  Human-centric intelligence is evolving in the foundation-model era, with growing emphasis on scale, transferability, and general-purpose modeling.<n>Recent advances across this broad landscape remain fragmented across tasks, modalities, and research communities, leaving their intrinsic conceptual and methodological connections unclear.<n>To bridge these divides and rethink human-centric intelligence in the foundation-model era, we introduce a full-spectrum human context taxonomy.
  arXiv  Detail & Related papers  (2026-08-18T08:12:40Z)
• Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models [12.200359585933766]
  Recent advances in self-supervised learning have given rise to Earth Observation Foundation Models (EOFMs)<n>This paper calls for a paradigm shift toward joint Spatial Representation Learning (SRL) in an unified embedding space that integrate perception with vector-based reasoning.<n>We contend that such integration is essential for developing next-generation geospatial AI systems capable of more accurate, interpretable, and grounded understanding of the Earth.
  arXiv  Detail & Related papers  (2026-06-01T15:21:58Z)
• Global Cross-Modal Geo-Localization: A Million-Scale Dataset and a Physical Consistency Learning Framework [13.268717213871147]
  Cross-modal Geo-localization (CMGL) matches ground-level text descriptions with geo-tagged aerial imagery.<n>We introduce CORE, the first million-scale dataset dedicated to global CMGL.<n>We propose a physical-law-aware network (PLANET) for cross-modal geo-localization.
  arXiv  Detail & Related papers  (2026-03-09T15:27:19Z)
• Large Language Models for Geolocation Extraction in Humanitarian Crisis Response [0.0]
  This paper investigates whether Large Language Models can address geographic disparities in extracting location information from humanitarian documents.<n>We introduce a two-step framework that combines few-shot LLM-based named entity recognition with an agent-based geocoding module.<n>Results show that LLM-based methods substantially improve both the precision and fairness of geolocation extraction from humanitarian texts.
  arXiv  Detail & Related papers  (2026-02-09T16:34:25Z)
• Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligence [64.36291202666212]
  Urban General Intelligence (UGI) refers to AI systems that can understand and reason about complex urban environments.<n>Recent studies have built urban foundation models using supervised fine-tuning (SFT) of LLMs and MLLMs.<n>We propose Urban-R1, a reinforcement learning-based post-training framework that aligns MLLMs with the objectives of UGI.
  arXiv  Detail & Related papers  (2025-10-18T15:59:09Z)
• TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation [65.74990259650984]
  We introduce TerraFM, a scalable self-supervised learning model that leverages globally distributed Sentinel-1 and Sentinel-2 imagery.<n>Our training strategy integrates local-global contrastive learning and introduces a dual-centering mechanism.<n>TerraFM achieves strong generalization on both classification and segmentation tasks, outperforming prior models on GEO-Bench and Copernicus-Bench.
  arXiv  Detail & Related papers  (2025-06-06T17:59:50Z)
• Enriching Location Representation with Detailed Semantic Information [0.6554326244334866]
  CaLLiPer+ is an extension of the CaLLiPer model that integrates Point-of-Interest (POI) names alongside categorical labels.<n>We evaluate its effectiveness on two downstream tasks, land use classification and socioeconomic status distribution mapping.
  arXiv  Detail & Related papers  (2025-06-03T11:06:51Z)
• EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLM [103.7537991413311]
  Earth Observation (EO) data analysis is vital for monitoring environmental and human dynamics.<n>Recent Multimodal Large Language Models (MLLMs) show potential in EO understanding but remain restricted to single-sensor inputs.<n>We propose EarthMind, a unified vision-language framework that handles both single- and cross-sensor inputs.
  arXiv  Detail & Related papers  (2025-06-02T13:36:05Z)
• MobCLIP: Learning General-purpose Geospatial Representation at Scale [0.7224497621488285]
  We present MobCLIP, the first nationwide general-purpose location encoder.<n>Adopting a novel CLIP-based architecture, our framework aligns 100M+ POIs, nationwide remote sensing imagery, and structured demographic statistics with a billion-edge mobility graph.<n>We show MobCLIP achieves significantly superior general-purpose predictive performances than state-of-the-art models by an average of 35%.
  arXiv  Detail & Related papers  (2025-06-02T04:14:03Z)
• EarthMapper: Visual Autoregressive Models for Controllable Bidirectional Satellite-Map Translation [50.433911327489554]
  We introduce EarthMapper, a novel framework for controllable satellite-map translation.<n>We also contribute CNSatMap, a large-scale dataset comprising 302,132 precisely aligned satellite-map pairs across 38 Chinese cities.<n> experiments on CNSatMap and the New York dataset demonstrate EarthMapper's superior performance.
  arXiv  Detail & Related papers  (2025-04-28T02:41:12Z)
• No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data [13.412573082645096]
  Implicit neural representations (INRs) exhibit growing promise in addressing Earth representation challenges.<n>Existing methods disproportionately prioritize global average performance.<n>We introduce FAIR-Earth: a first-of-its-kind dataset to examine and challenge inequities in Earth representations.
  arXiv  Detail & Related papers  (2025-02-05T16:51:13Z)
• PEACE: Empowering Geologic Map Holistic Understanding with MLLMs [64.58959634712215]
  Geologic map, as a fundamental diagram in geology science, provides critical insights into the structure and composition of Earth's subsurface and surface.<n>Despite their significance, current Multimodal Large Language Models (MLLMs) often fall short in geologic map understanding.<n>To quantify this gap, we construct GeoMap-Bench, the first-ever benchmark for evaluating MLLMs in geologic map understanding.
  arXiv  Detail & Related papers  (2025-01-10T18:59:42Z)
• A General Purpose Neural Architecture for Geospatial Systems [142.43454584836812]
  We present a roadmap towards the construction of a general-purpose neural architecture (GPNA) with a geospatial inductive bias. We envision how such a model may facilitate cooperation between members of the community.
  arXiv  Detail & Related papers  (2022-11-04T09:58:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.