Spatial Transfer Learning for Estimating PM2.5 in Data-poor Regions
This addresses air pollution estimation in developing countries, offering an incremental advance by improving transfer learning for spatial data.
The paper tackled the problem of estimating PM2.5 in data-poor regions by proposing a new feature called Latent Dependency Factor (LDF) to capture spatial and semantic dependencies between source and target domains, resulting in a 19.34% improvement over baselines.
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.