# Spatial Transfer Learning for Estimating PM2.5 in Data-poor Regions

arXiv: https://arxiv.org/abs/2404.07308 · HTML: https://mlsanity.com/paper/2404.07308/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 44 references that are in the map.
- First posted on arXiv 10 Apr 2024.

## Builds on (most cited first, 5 of 5)

- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Deflating Dataset Bias Using Synthetic Data Augmentation](https://mlsanity.com/paper/2004.13866/) (2020)
- [Nearest Neighbor-based Importance Weighting](https://mlsanity.com/paper/2102.02291/) (2021)
- [Artificial Dummies for Urban Dataset Augmentation](https://mlsanity.com/paper/2012.08274/) (2020)
- [Few-shot calibration of low-cost air pollution (PM2.5) sensors using meta-learning](https://mlsanity.com/paper/2108.00640/) (2021)

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

- [Conformal PM2.5 Mapping Under Spatial Covariate Shift: Satellite-Reanalysis Fusion for Africa's Green Industrial Transition](https://mlsanity.com/paper/2604.22787/) (2026)

## Abstract (arXiv)

Air pollution, especially particulate matter 2.5 (PM2.5), is a pressing concern for public health and is difficult to estimate in developing countries (data-poor regions) due to a lack of ground sensors. Transfer learning models can be leveraged to solve this problem, as they use alternate data sources to gain knowledge (i.e., data from data-rich regions). However, current transfer learning methodologies do not account for dependencies between the source and the target domains. We recognize this transfer problem as spatial transfer learning and propose a new feature named Latent Dependency Factor (LDF) that captures spatial and semantic dependencies of both domains and is subsequently added to the feature spaces of the domains. We generate LDF using a novel two-stage autoencoder model that learns from clusters of similar source and target domain data. Our experiments show that transfer learning models using LDF have a 19.34% improvement over the baselines. We additionally support our experiments with qualitative findings.