# GeoGNN: Time Series Geo-Localization using Two-Tower Graph Neural Networks

arXiv: https://arxiv.org/abs/2606.08303 · HTML: https://mlsanity.com/paper/2606.08303/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 64 references that are in the map.
- First posted on arXiv 6 Jun 2026.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https://mlsanity.com/paper/2106.09305/) (2021)
- [GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization](https://mlsanity.com/paper/2309.16020/) (2023)
- [Revisiting IM2GPS in the Deep Learning Era](https://mlsanity.com/paper/1705.04838/) (2017)
- [Where in the World is this Image? Transformer-based Geo-localization in the Wild](https://mlsanity.com/paper/2204.13861/) (2022)
- [Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes](https://mlsanity.com/paper/2303.04249/) (2023)
- [G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models](https://mlsanity.com/paper/2405.14702/) (2024)
- [Towards Neural Scaling Laws for Time Series Foundation Models](https://mlsanity.com/paper/2410.12360/) (2024)
- [OpenCity: Open Spatio-Temporal Foundation Models for Traffic Prediction](https://mlsanity.com/paper/2408.10269/) (2024)
- [GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization](https://mlsanity.com/paper/2505.13731/) (2025)
- [FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction](https://mlsanity.com/paper/2405.17898/) (2024)
- [A Neural Model for User Geolocation and Lexical Dialectology](https://mlsanity.com/paper/1704.04008/) (2017)
- [GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction](https://mlsanity.com/paper/2511.01082/) (2025)
- [A survey of location inference techniques on Twitter](https://mlsanity.com/paper/1701.03639/) (2017)
- [Bioacoustic Geolocation: Species Sounds as Geographic Signals](https://mlsanity.com/paper/2505.18726/) (2025)
- [Audio Content based Geotagging in Multimedia](https://mlsanity.com/paper/1606.02816/) (2016)
- [The "Sprekend Nederland" project and its application to accent location](https://mlsanity.com/paper/1602.02499/) (2016)
- [Predicting the Geolocation of Tweets Using transformer models on Customized Data](https://mlsanity.com/paper/2303.07865/) (2023)
- [Privacy-Preserving Analytics for Smart Meter (AMI) Data: A Hybrid Approach to Comply with CPUC Privacy Regulations](https://mlsanity.com/paper/2505.08237/) (2025)

## Abstract (arXiv)

This paper investigates a novel concept of time series geolocalization, where the goal is to infer the geographic origin of each raw time series. Successful geolocalization can provide spatial context to time series, enabling downstream location-aware applications. We formalize the problem, adapt core ideas from image geolocalization to establish strong baselines, and propose GeoGNN, a two-tower architecture. During training, GeoGNN's spatial tower learns embeddings of geographic cell candidates by leveraging the geographic adjacency graph, while the temporal tower extracts informative representations from time series. During inference, each temporal representation is matched against candidate geographic embeddings using dot-product similarity, combined with an auxiliary classification head, to predict the time series' associated geographic origin. Experiments on large-scale, countrywide electricity-consumption datasets demonstrate that GeoGNN achieves the best performance across datasets and enhances both fine- and coarse-grained geolocalization accuracy by ~27% on average.