Work

A non-stationary spatial model of PM$$_{2.5}$$ with localized transfer learning from numerical model output

Year: 2026

Type: article

Abstract: Ambient air pollution measurements from regulatory monitoring networks are routinely used to support epidemiologic studies and environmental policy decision-making. However, regulatory monitors are spatially sparse and preferentially located in areas with large populations. Numerical air pollution model output can be leveraged into the inference and prediction of air pollution data combining with measurements from monitors. Nonstationary covariance functions allow the model to adapt to spatial surfaces whose variability changes with location like air pollution data. In the paper, we employ localized covariance parameters learned from the numerical output model to knit together into a global nonstationary covariance, to incorporate in a fully Bayesian model. We model the nonstationary structure in a computationally efficient way to make the Bayesian model scalable.

Source: Environmental and Ecological Statistics

DOI: 10.1007/s10651-026-00710-z

Authors: Wenlong Gong, Brian J. Reich, Joseph Guinness

Institutions: University of Houston - Downtown, North Carolina State University, Washington University in St. Louis

Language: English

Topic: Spatial and Panel Data Analysis

Subfield: Economics and Econometrics

Field: Economics, Econometrics and Finance

Domain: Social Sciences

SDG: Climate action

Open Access status: hybrid

Estimated APC paid: $2,290