# S2Vec: Self-Supervised Geospatial Embeddings for the Built Environment

arXiv: https://arxiv.org/abs/2504.16942 · HTML: https://mlsanity.com/paper/2504.16942/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 48 references that are in the map.
- First posted on arXiv 10 Apr 2025.

## Builds on (most cited first, 30 of 31)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization](https://mlsanity.com/paper/2309.16020/) (2023)
- [SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery](https://mlsanity.com/paper/2311.17179/) (2023)
- [GEO-Bench: Toward Foundation Models for Earth Monitoring](https://mlsanity.com/paper/2306.03831/) (2023)
- [Self-Supervised Learning with Swin Transformers](https://mlsanity.com/paper/2105.04553/) (2021)
- [Multimodal Masked Autoencoders Learn Transferable Representations](https://mlsanity.com/paper/2205.14204/) (2022)
- [Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells](https://mlsanity.com/paper/2003.00824/) (2020)
- [A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery](https://mlsanity.com/paper/2010.08168/) (2020)
- [MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning](https://mlsanity.com/paper/2405.02771/) (2024)
- [CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations](https://mlsanity.com/paper/2305.01118/) (2023)
- [Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks](https://mlsanity.com/paper/2310.06743/) (2023)
- [A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond](https://mlsanity.com/paper/2208.00173/) (2022)
- [A Review of Location Encoding for GeoAI: Methods and Applications](https://mlsanity.com/paper/2111.04006/) (2021)
- [Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictions](https://mlsanity.com/paper/2306.17624/) (2023)
- [Towards Vision-Language Geo-Foundation Model: A Survey](https://mlsanity.com/paper/2406.09385/) (2024)
- [TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning](https://mlsanity.com/paper/2406.15658/) (2024)
- [Hex2vec -- Context-Aware Embedding H3 Hexagons with OpenStreetMap Tags](https://mlsanity.com/paper/2111.00970/) (2021)
- [Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models](https://mlsanity.com/paper/2402.01749/) (2024)
- [Towards General-Purpose Representation Learning of Polygonal Geometries](https://mlsanity.com/paper/2209.15458/) (2022)
- [City Foundation Models for Learning General Purpose Representations from OpenStreetMap](https://mlsanity.com/paper/2310.00583/) (2023)
- [General Geospatial Inference with a Population Dynamics Foundation Model](https://mlsanity.com/paper/2411.07207/) (2024)
- [TrajFM: A Vehicle Trajectory Foundation Model for Region and Task Transferability](https://mlsanity.com/paper/2408.15251/) (2024)
- [Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications](https://mlsanity.com/paper/2408.14806/) (2024)
- [GeoVectors: A Linked Open Corpus of OpenStreetMap Embeddings on World Scale](https://mlsanity.com/paper/2108.13092/) (2021)
- [A Recipe for Improving Remote Sensing VLM Zero Shot Generalization](https://mlsanity.com/paper/2503.08722/) (2025)
- [Space-aware Socioeconomic Indicator Inference with Heterogeneous Graphs](https://mlsanity.com/paper/2405.14135/) (2024)

## Built on by (most cited first, 4 of 4)

- [Inferring Height from Earth Embeddings: First insights using Google AlphaEarth](https://mlsanity.com/paper/2602.17250/) (2026)
- [Zero-Shot Multi-Spectral Learning: Reimagining a Generalist Multimodal Gemini 2.5 Model for Remote Sensing Applications](https://mlsanity.com/paper/2509.19087/) (2025)
- [Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models](https://mlsanity.com/paper/2606.02374/) (2026)
- [TrajGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations](https://mlsanity.com/paper/2605.06990/) (2026)

## Abstract (arXiv)

Scalable general-purpose representations of the built environment are crucial for geospatial artificial intelligence applications. This paper introduces S2Vec, a novel self-supervised framework for learning such geospatial embeddings. S2Vec uses the S2 Geometry library to partition large areas into discrete S2 cells, rasterizes built environment feature vectors within cells as images, and applies masked autoencoding on these rasterized images to encode the feature vectors. This approach yields task-agnostic embeddings that capture local feature characteristics and broader spatial relationships. We evaluate S2Vec on several large-scale geospatial prediction tasks, both random train/test splits (interpolation) and zero-shot geographic adaptation (extrapolation). Our experiments show S2Vec's competitive performance against several baselines on socioeconomic tasks, especially the geographic adaptation variant, with room for improvement on environmental tasks. We also explore combining S2Vec embeddings with image-based embeddings downstream, showing that such multimodal fusion can often improve performance. Our findings highlight how S2Vec can learn effective general-purpose geospatial representations of the built environment features it is provided, and how it can complement other data modalities in geospatial artificial intelligence.