# Performance and Generalizability Impacts of Incorporating Location Encoders into Deep Learning for Dynamic PM2.5 Estimation

arXiv: https://arxiv.org/abs/2505.18461 · HTML: https://mlsanity.com/paper/2505.18461/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 64 references that are in the map.
- First posted on arXiv 24 May 2025.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [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)
- [A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery](https://mlsanity.com/paper/2010.08168/) (2020)
- [CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations](https://mlsanity.com/paper/2305.01118/) (2023)
- [A Review of Location Encoding for GeoAI: Methods and Applications](https://mlsanity.com/paper/2111.04006/) (2021)
- [A spatiotemporal machine learning approach to forecasting COVID-19 incidence at the county level in the USA](https://mlsanity.com/paper/2109.12094/) (2021)

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

- [Localized, High-resolution Geographic Representations with Slepian Functions](https://mlsanity.com/paper/2602.00392/) (2026)
- [Tessellating The Earth](https://mlsanity.com/paper/2606.27514/) (2026)
- [A Proxy Consistency Loss for Grounded Fusion of Earth Observation and Location Encoders](https://mlsanity.com/paper/2604.18881/) (2026)
- [Chronosphere: Space-Time Tessellation of Local Climate Experts](https://mlsanity.com/paper/2609.21872/) (2026)

## Abstract (arXiv)

Deep learning has shown strong performance in geospatial prediction tasks, but the role of geolocation information in improving accuracy and generalizability remains underexamined. Recent work has introduced location encoders that aim to represent spatial context in a transferable way, yet most evaluations have focused on static mapping tasks. Here, we study the effect of incorporating geolocation into deep learning for a dynamic and spatially heterogeneous application: estimating daily surface-level PM2.5 across the contiguous United States using satellite and ground-based observations. We compare three strategies for representing location: excluding geolocation, using raw latitude and longitude, and using pretrained location encoders. We evaluate each under within-region and out-of-region generalization settings. Results show that raw coordinates can improve performance within regions by supporting spatial interpolation, but can reduce generalizability across regions. In contrast, pretrained location encoders such as GeoCLIP improve both predictive accuracy and geographic transfer. However, we also observe spatial artifacts linked to encoder characteristics, and performance varies across encoder types (e.g., SatCLIP vs. GeoCLIP). This work provides the first systematic evaluation of location encoders in a dynamic environmental estimation context and offers guidance for incorporating geolocation into deep learning models for geospatial prediction.