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.

翻译：可扩展的通用建成环境表征对于地理空间人工智能应用至关重要。本文提出S2Vec——一种用于学习此类地理空间嵌入的新型自监督框架。S2Vec利用S2几何库将大范围区域划分为离散的S2单元，将单元内的建成环境特征向量栅格化为图像，并通过对这些栅格化图像进行掩码自编码来编码特征向量。该方法生成的任务无关嵌入能够捕捉局部特征特性和更广泛的空间关系。我们在多个大规模地理空间预测任务上评估S2Vec，包括随机训练/测试划分（插值）和零样本地理适应（外推）。实验表明，S2Vec在社会经济任务上相较于多个基线模型具有竞争优势，尤其是地理适应变体，在环境任务上仍有改进空间。我们还探索在下游任务中将S2Vec嵌入与基于图像的嵌入相结合，证明此类多模态融合通常能提升性能。我们的研究结果揭示了S2Vec如何能有效学习所提供建成环境特征的通用地理空间表征，以及如何在地理空间人工智能中与其他数据模态形成互补。