# OT on the Map: Quantifying Domain Shifts in Geographic Space

arXiv: https://arxiv.org/abs/2604.16220 · HTML: https://mlsanity.com/paper/2604.16220/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Functional Map of the World](https://mlsanity.com/paper/1711.07846/) (2017)
- [Joint Distribution Optimal Transportation for Domain Adaptation](https://mlsanity.com/paper/1705.08848/) (2017)
- [Task2Vec: Task Embedding for Meta-Learning](https://mlsanity.com/paper/1902.03545/) (2019)
- [GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization](https://mlsanity.com/paper/2309.16020/) (2023)
- [Geometric Dataset Distances via Optimal Transport](https://mlsanity.com/paper/2002.02923/) (2020)
- [No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World](https://mlsanity.com/paper/1711.08536/) (2017)
- [SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery](https://mlsanity.com/paper/2311.17179/) (2023)
- [Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning](https://mlsanity.com/paper/2402.01444/) (2024)
- [Optimal Transport for Multi-source Domain Adaptation under Target Shift](https://mlsanity.com/paper/1803.04899/) (2018)
- [Adaptive Methods for Real-World Domain Generalization](https://mlsanity.com/paper/2103.15796/) (2021)
- [OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations](https://mlsanity.com/paper/2103.13843/) (2021)
- [Hierarchical Optimal Transport for Document Representation](https://mlsanity.com/paper/1906.10827/) (2019)
- [GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition](https://mlsanity.com/paper/2301.02560/) (2023)
- [CO-Optimal Transport](https://mlsanity.com/paper/2002.03731/) (2020)
- [Predicting into unknown space? Estimating the area of applicability of spatial prediction models](https://mlsanity.com/paper/2005.07939/) (2020)
- [An Information-theoretic Approach to Distribution Shifts](https://mlsanity.com/paper/2106.03783/) (2021)
- [Improving Domain Generalization with Domain Relations](https://mlsanity.com/paper/2302.02609/) (2023)
- [Detecting Out-Of-Distribution Earth Observation Images with Diffusion Models](https://mlsanity.com/paper/2404.12667/) (2024)
- [An Entropic Optimal Transport Loss for Learning Deep Neural Networks under Label Noise in Remote Sensing Images](https://mlsanity.com/paper/1810.01163/) (2018)
- [Distribution Shifts at Scale: Out-of-distribution Detection in Earth Observation](https://mlsanity.com/paper/2412.13394/) (2024)
- [Out-of-distribution detection in satellite image classification](https://mlsanity.com/paper/2104.05442/) (2021)
- [Unsupervised Domain Adaptation for Semantic Segmentation using One-shot Image-to-Image Translation via Latent Representation Mixing](https://mlsanity.com/paper/2212.03826/) (2022)
- [Leveraging Domain Adaptation for Low-Resource Geospatial Machine Learning](https://mlsanity.com/paper/2107.04983/) (2021)
- [Nearest Neighbor Based Out-of-Distribution Detection in Remote Sensing Scene Classification](https://mlsanity.com/paper/2303.16616/) (2023)

## Built on by (most cited first, 1 of 1)

- [Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models](https://mlsanity.com/paper/2606.02374/) (2026)

## Abstract (arXiv)

In computer vision and machine learning for geographic data, out-of-domain generalization is a pervasive challenge, arising from uneven global data coverage and distribution shifts across geographic regions. Though models are frequently trained in one region and deployed in another, there is no principled method for determining when this cross-region adaptation will be successful. A well-defined notion of distance between distributions can effectively quantify how different a new target domain is compared to the domains used for model training, which in turn could support model training and deployment decisions. In this paper, we propose a strategy for computing distances between geospatial domains that leverages geographic information with Optimal Transport methods (GeoSpOT). In our experiments, GeoSpOT distances emerge as effective predictors of cross-domain transfer difficulty. We further demonstrate that embeddings from pretrained location encoders provide information comparable to image/text embeddings, despite relying solely on longitude-latitude pairs as input. This allows users to get an approximation of out-of-domain performance for geospatial models, even when the exact downstream task is unknown, or no task-specific data is available. Building on these findings, we show that GeoSpOT distances can preemptively guide data selection and enable predictive tools to analyze regions where a model is likely to underperform.