{"total":35,"items":[{"citing_arxiv_id":"2607.01082","ref_index":48,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"When Context Compensates for Sparse Event History: AlphaEarth for Spatio-Temporal Point-Process Forecasting","primary_cat":"cs.LG","submitted_at":"2026-07-01T15:38:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"AlphaEarth embeddings improve out-of-region EMS point-process forecasts 2-6x at 1-2 week histories and 10-20% at longer histories compared to event-only baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.29134","ref_index":35,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Beyond Backscatter: AlphaEarth Land-Cover Priors for Rapid SAR Flood Segmentation Across Foundation Backbones","primary_cat":"cs.CV","submitted_at":"2026-06-28T00:46:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AlphaEarth land-cover priors improve SAR flood segmentation IoU over SAR-only and DEM baselines across CNN and ViT backbones on held-out events like Hurricane Florence.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20034","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Exploring the potential of AlphaEarth and TESSERA embeddings for Fine-scale Local Climate Zone Mapping: A case study across five cities in Switzerland","primary_cat":"cs.LG","submitted_at":"2026-06-18T10:06:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TESSERA embeddings achieve the highest IoU (0.77-0.82) for 10m LCZ mapping across Swiss cities and outperform Sentinel-1/2 and AlphaEarth, though year-to-year transfer remains challenging.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11534","ref_index":18,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Urban Heat MiniCubes: An AI-Ready dataset for urban heat research","primary_cat":"physics.ao-ph","submitted_at":"2026-06-10T00:34:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Releases a publicly available, collocated multi-sensor dataset of Landsat, Sentinel-1, GOES-R and microwave observations for urban heat studies across 48 cities.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11510","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Continuous biome representations from Earth observation embeddings","primary_cat":"q-bio.QM","submitted_at":"2026-06-09T23:14:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Linear classifier on Clay v1.5 embeddings produces continuous biome probabilities that raise mean per-species AUC for occurrence prediction from 0.570 (discrete labels) to 0.618 on 10,015 Brazilian forest plots.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08046","ref_index":6,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"OSMGraphCLIP: Learning Global Location Representations from OpenStreetMap Graphs","primary_cat":"cs.AI","submitted_at":"2026-06-06T08:18:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"OSMGraphCLIP learns global location embeddings from OSM graphs via multi-scale graph encoding and contrastive alignment that match or exceed satellite baselines on many socioeconomic, health, and environmental tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05368","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Biomazon: A Multimodal Dataset for 3D Forest Structure and Biomass Modeling in the Amazon Basin","primary_cat":"cs.CV","submitted_at":"2026-06-03T19:16:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"UNKNOWN","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Biomazon is a multimodal benchmark dataset pairing GEDI RH profiles and AGBD targets with Sentinel, ALOS, DEM, and other predictors for joint 3D forest structure and biomass modeling in the Amazon.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02374","ref_index":6,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models","primary_cat":"cs.AI","submitted_at":"2026-06-01T15:21:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Perspective paper calling for unified spatial representation learning that integrates raster imagery with vector semantics in geospatial foundation models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.01745","ref_index":8,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Enhancing the Socioeconomic Understanding of Foundation Models with Urban Mobility","primary_cat":"cs.SI","submitted_at":"2026-06-01T06:08:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MobFusion fuses mobility networks into foundation models via three designs and reports improved performance on income, density, and crime prediction tasks using data from three U.S. metropolitan areas.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.26036","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities","primary_cat":"cs.AI","submitted_at":"2026-05-25T17:03:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CityRep is a new multi-city, multi-task benchmark with spatial splits for evaluating urban representation embeddings across modalities and locations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21804","ref_index":26,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Mapping Tomato Cropping Systems in California Using AlphaEarth Geospatial Embeddings and Deep Learning Analysis","primary_cat":"eess.IV","submitted_at":"2026-05-20T23:00:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A U-Net segmentation model trained on 64-band AlphaEarth embedding chips achieves 99.19% pixel accuracy and 99.04% F1 on an independent test set for distinguishing tomato from non-tomato fields in California.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21075","ref_index":11,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"SpectralEarth-FM: Bringing Hyperspectral Imagery into Multimodal Earth Observation Pretraining","primary_cat":"cs.CV","submitted_at":"2026-05-20T12:08:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SpectralEarth-FM is a multisensor hierarchical transformer pretrained on a 40TB co-located HSI-MSI-SAR dataset using a JEPA-style objective and reports state-of-the-art results on hyperspectral and standard EO benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19812","ref_index":26,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FLUXtrapolation: A benchmark on extrapolating ecosystem fluxes","primary_cat":"cs.LG","submitted_at":"2026-05-19T13:09:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FLUXtrapolation is a benchmark for domain generalization in ecosystem flux upscaling using temporal, spatial, and temperature-based extrapolation scenarios, with pilot results showing model separation on tail and multi-scale metrics.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"needed as global ecosystems are changing into new regimes due to climate change and human impacts, and because measurement sites will continue to come on and off line over time [181]. A next test will be to evaluate strong methods on new sites from the enlarged FLUXNET network and assess whether the stress tests were sufficient to identify the more robust methods. It remains to see whether external information such as foundation models [26, 86, 107] can help reduce the effect of hidden variables. Finally, many other problems in Earth system science are rich in time but sparse in space and require prediction where observations are unavailable, including plant traits [146], tree water use [191], and soil properties [189]. FLUXtrapolation's design and the lessons learned may therefore transfer beyond ecosystem fluxes to a range of environmental problems."},{"citing_arxiv_id":"2605.18667","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Better Together: Evaluating the Complementarity of Earth Embedding Models","primary_cat":"cs.CV","submitted_at":"2026-05-18T17:10:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Fusing embeddings from four Earth models (AlphaEarth, Tessera, GeoCLIP, SatCLIP) outperforms the best single model on four of six tasks, with gains depending on task and location.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16665","ref_index":26,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"In-context learning enables continental-scale subsurface temperature prediction from sparse local observations","primary_cat":"cs.LG","submitted_at":"2026-05-15T22:03:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A transformer-based in-context learning model predicts continental-scale subsurface temperatures from sparse borehole observations, outperforming physics and interpolation baselines while adapting to new regions with 20 examples.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15666","ref_index":1,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ChronoEarth-492K: A Large Scale and Long Horizon Spatiotemporal Hyperspectral Earth Observation Dataset and Benchmark","primary_cat":"cs.CV","submitted_at":"2026-05-15T06:44:23+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Introduces ChronoEarth-492K, a 492K-patch temporally calibrated hyperspectral dataset from the EO-1 Hyperion archive spanning 2001-2017, plus a benchmark for static, short-horizon, and long-horizon spatiotemporal tasks using open geospatial products.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18911","ref_index":3,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Does Your Wildfire Prediction Model Actually Work, or Just Score Well?","primary_cat":"cs.LG","submitted_at":"2026-05-14T04:28:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces WILDFIRE-FM and a fixed-contract evaluation framework demonstrating that wildfire model transfer conclusions depend strongly on evaluation design and task formulation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14120","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Mini-JEPA Foundation Model Fleet Enables Agentic Hydrologic Intelligence","primary_cat":"cs.LG","submitted_at":"2026-05-13T21:11:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A fleet of sensor-specialized 22M-parameter JEPA models routed by an LLM improves LLM-as-judge scores on hydrologic questions over AlphaEarth alone with Cohen's d of 1.10.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12678","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"No One Knows the State of the Art in Geospatial Foundation Models","primary_cat":"cs.CV","submitted_at":"2026-05-12T19:29:51+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"An audit of 152 papers reveals that geospatial foundation models lack standardized evaluations, training controls, and weight releases, so no one knows the state of the art.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06990","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"TRAJGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations","primary_cat":"cs.CV","submitted_at":"2026-05-07T22:10:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"TrajGANR learns continuous neural representations of trajectories to enable fine-grained alignment with street-view images and locations in a joint multimodal self-supervised objective, outperforming prior geospatial MSSL methods on urban mobility and road tasks.","context_count":1,"top_context_role":"other","top_context_polarity":"unclear","context_text":"[1] Lubian Bai, Xiuyuan Zhang, Siqi Zhang, Zepeng Zhang, Haoyu Wang, Wei Qin, and Shihong Du. Geolink: Empowering remote sensing foundation model with openstreetmap data.arXiv preprint arXiv:2509.26016, 2025. [2] Kaifeng Bi, Lingxi Xie, Hengheng Zhang, Xin Chen, Xiaotao Gu, and Qi Tian. Accurate medium-range global weather forecasting with 3d neural networks.Nature, 619(7970):533-538, 2023. [3] Christopher F Brown, Michal R Kazmierski, Valerie J Pasquarella, William J Rucklidge, Masha Samsikova, Chenhui Zhang, Evan Shelhamer, Estefania Lahera, Olivia Wiles, Simon Ilyushchenko, et al. Alphaearth foundations: An embedding field model for accurate and efficient global mapping from sparse label data.arXiv preprint arXiv:2507.22291, 2025. [4] Jiezhang Cao, Qin Wang, Yongqin Xian, Yawei Li, Bingbing Ni, Zhiming Pi, Kai Zhang, Yulun"},{"citing_arxiv_id":"2605.04510","ref_index":135,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Predictive and Prescriptive AI toward Optimizing Wildfire Suppression","primary_cat":"math.OC","submitted_at":"2026-05-06T05:26:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A new optimization algorithm with double machine learning for wildfire spread estimation enables better crew assignments that reduce total area burned.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00972","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Toward a Scientific Discovery Engine for Weather and Climate Data: A Visual Analytics Workbench for Embedding-Based Exploration","primary_cat":"physics.data-an","submitted_at":"2026-05-01T17:03:33+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A visual analytics workbench enables scientists to explore, query, and verify embedding-based similarity searches on weather and climate data by tracing results back to physical evidence.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.24919","ref_index":10,"ref_count":2,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Agentic AI for Remote Sensing: Technical Challenges and Research Directions","primary_cat":"cs.CV","submitted_at":"2026-04-27T18:59:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Position paper identifies structural challenges in applying generic agentic AI to Earth Observation and outlines design principles for EO-native agents focused on geospatial state and validity.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"scale as implicit or fixed, a common assumption in existing agentic pipelines, can therefore produce analyses that appear internally coherent yet lack geospatial validity. Agentic EO models must instead reason explicitly about spatial scale and geographic coverage as part of the analytical process. Related EO pretraining and multimodal work similarly treat scale as a first-class variable [ 10, 52, 62, 90, 110, 116, 138]. Agentic AI for Remote Sensing: Technical Challenges and Research Directions 9 LAYER 1 - SPATIAL SCALE LAYER 2- TEMPORAL COMPLEXITY LAYER 3 - MULTI-MODALITY LAYER 4 - PHYSICAL CONSTRAINTS LAYER 5 - RISK & VALIDATION Fine texture Urban blocks Continent map Irreversible aggregation Irregular timestamps Seasonal Change"},{"citing_arxiv_id":"2604.23678","ref_index":38,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Transferable Human Mobility Network Reconstruction with neuroGravity","primary_cat":"cs.AI","submitted_at":"2026-04-26T12:33:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"neuroGravity reconstructs transferable human mobility networks from basic urban data via physics-informed deep learning, with transferability predicted by a spatial income segregation index.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21032","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Unlocking Multi-Spectral Data for Multi-Modal Models with Guided Inputs and Chain-of-Thought Reasoning","primary_cat":"cs.CV","submitted_at":"2026-04-22T19:23:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A prompting-based adaptation technique lets RGB-trained LMMs process multi-spectral inputs and deliver strong zero-shot gains on remote-sensing benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19591","ref_index":2,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Structure-Semantic Decoupled Modulation of Global Geospatial Embeddings for High-Resolution Remote Sensing Mapping","primary_cat":"cs.CV","submitted_at":"2026-04-21T15:42:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SSDM decouples global geospatial embeddings into structural modulation and semantic injection pathways to improve accuracy and consistency in high-resolution remote sensing land cover mapping.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18881","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"A Proxy Consistency Loss for Grounded Fusion of Earth Observation and Location Encoders","primary_cat":"cs.CV","submitted_at":"2026-04-20T22:01:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A proxy consistency loss trains location encoders on proxy geographic data to outperform direct input fusion or frozen embeddings for air quality and poverty mapping with sparse labels.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.16841","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"When Earth Foundation Models Meet Diffusion: An Application to Land Surface Temperature Super-Resolution","primary_cat":"cs.CV","submitted_at":"2026-04-18T05:21:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EFDiff conditions a diffusion model with Prithvi-EO-2.0 geospatial embeddings via cross-attention to achieve 32x LST super-resolution, outperforming baselines on a global Landsat dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.11668","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"UNIGEOCLIP: Unified Geospatial Contrastive Learning","primary_cat":"cs.CV","submitted_at":"2026-04-13T16:14:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"UNIGEOCLIP creates a unified embedding for aerial imagery, street views, elevation, text, and coordinates via all-to-all contrastive alignment plus a scaled lat-long encoder, outperforming single-modality and coordinate baselines on geospatial tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.11444","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"HuiYanEarth-SAR: A Foundation Model for High-Fidelity and Low-Cost Global Remote Sensing Imagery Generation","primary_cat":"cs.CV","submitted_at":"2026-04-13T13:26:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HuiYanEarth-SAR is a foundation model that generates realistic global SAR imagery from geographic coordinates alone by integrating geospatial semantics and implicit scattering characteristics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.07092","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Data","primary_cat":"cs.CV","submitted_at":"2026-04-08T13:44:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LIANet encodes multi-temporal Earth observation data into a coordinate-based neural field that supports label-only fine-tuning for downstream tasks without access to raw imagery.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.03456","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Earth Embeddings Reveal Diverse Urban Signals from Space","primary_cat":"cs.LG","submitted_at":"2026-04-03T20:58:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Earth embeddings from satellite images predict neighborhood-level urban indicators with higher accuracy for built-environment outcomes than for behavior-driven ones, showing city-specific variation but year-to-year stability.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"tics tailored to specific tasks, regions, and sensors[18-20]. Such workflows are difficult to scale, sensitive to domain shifts, and offer limited transferability across indicators or cities[21]. Recently, the field has undergone a paradigm shift toward self-supervised learning and the development of geospatial foundation models[22]. Cutting-edge models such as AlphaEarth Foundations[23], Prithvi-EO-2.0[24], and Clay[25] are designed to ingest massive volumes of unlabeled remote sens- ing imagery to generate Earth embeddings-universal latent vectors that encapsulate complex spatial textures, land-cover patterns, and high-level semantic information. These embeddings serve as widely applicable inputs for diverse downstream applications, moving beyond task-specific archi-"},{"citing_arxiv_id":"2601.12964","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":true,"paper_title":"Cross-Scale Pretraining: Enhancing Self-Supervised Learning for Low-Resolution Satellite Imagery for Semantic Segmentation","primary_cat":"cs.CV","submitted_at":"2026-01-19T11:21:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A new spatial affinity component for self-supervised pretraining leverages high-resolution imagery to enhance mid-resolution satellite image representations and segmentation performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.17171","ref_index":9,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","primary_cat":"cs.CV","submitted_at":"2025-11-21T11:45:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"FireScope trains a VLM on US data to output wildfire risk rasters with reasoning traces and shows improved cross-continental performance on European events compared with prior approaches.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2411.19093","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Seeing SDG 6 from space: local-scale monitoring of piped water and sewage system access across Africa using satellite imagery and self-supervised learning","primary_cat":"cs.CV","submitted_at":"2024-11-28T12:13:46+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}