Saved in:
Bibliographic Details
Main Authors: Wen, Ya, Cai, Jixuan, Ma, Qiyao, Li, Linyan, Chen, Xinhua, Webster, Chris, Zhou, Yulun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.01297
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918306708979712
author Wen, Ya
Cai, Jixuan
Ma, Qiyao
Li, Linyan
Chen, Xinhua
Webster, Chris
Zhou, Yulun
author_facet Wen, Ya
Cai, Jixuan
Ma, Qiyao
Li, Linyan
Chen, Xinhua
Webster, Chris
Zhou, Yulun
contents Representation learning of geospatial locations remains a core challenge in achieving general geospatial intelligence, with increasingly diverging philosophies and techniques. While Earth observation paradigms excel at depicting locations in their physical states, we claim that a location's comprehensive "meaning" is better grounded in its internal human activity patterns and, crucially, its functional relationships with other locations, as revealed by human movement. We present MoRA, a human-centric geospatial framework that leverages a mobility graph as its core backbone to fuse various data modalities, aiming to learn embeddings that represent the socio-economic context and functional role of a location. MoRA achieves this through the integration of spatial tokenization, GNNs, and asymmetric contrastive learning to align 100M+ POIs, massive remote sensing imagery, and structured demographic statistics with a billion-edge mobility graph, ensuring the three auxiliary modalities are interpreted through the lens of fundamental human dynamics. To rigorously evaluate the effectiveness of MoRA, we construct a benchmark dataset composed of 9 downstream prediction tasks across social and economic domains. Experiments show that MoRA, with four input modalities and a compact 128-dimensional representation space, achieves superior predictive performances than state-of-the-art models by an average of 12.9%. Echoing LLM scaling laws, we further demonstrate the scaling behavior in geospatial representation learning. We open-source code and pretrained models at: https://github.com/ylzhouchris/MoRA.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01297
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MoRA: Mobility as the Backbone for Geospatial Representation Learning at Scale
Wen, Ya
Cai, Jixuan
Ma, Qiyao
Li, Linyan
Chen, Xinhua
Webster, Chris
Zhou, Yulun
Artificial Intelligence
Representation learning of geospatial locations remains a core challenge in achieving general geospatial intelligence, with increasingly diverging philosophies and techniques. While Earth observation paradigms excel at depicting locations in their physical states, we claim that a location's comprehensive "meaning" is better grounded in its internal human activity patterns and, crucially, its functional relationships with other locations, as revealed by human movement. We present MoRA, a human-centric geospatial framework that leverages a mobility graph as its core backbone to fuse various data modalities, aiming to learn embeddings that represent the socio-economic context and functional role of a location. MoRA achieves this through the integration of spatial tokenization, GNNs, and asymmetric contrastive learning to align 100M+ POIs, massive remote sensing imagery, and structured demographic statistics with a billion-edge mobility graph, ensuring the three auxiliary modalities are interpreted through the lens of fundamental human dynamics. To rigorously evaluate the effectiveness of MoRA, we construct a benchmark dataset composed of 9 downstream prediction tasks across social and economic domains. Experiments show that MoRA, with four input modalities and a compact 128-dimensional representation space, achieves superior predictive performances than state-of-the-art models by an average of 12.9%. Echoing LLM scaling laws, we further demonstrate the scaling behavior in geospatial representation learning. We open-source code and pretrained models at: https://github.com/ylzhouchris/MoRA.
title MoRA: Mobility as the Backbone for Geospatial Representation Learning at Scale
topic Artificial Intelligence
url https://arxiv.org/abs/2506.01297