Quantifying Uncertainty in SOA Yield Predictions and Associated Health Risks using AutoML and Quantile Regression
Year: 2025
Type: article
Abstract: Poster of work completed in Google DeepMind Research Ready Internship at University of Manchester. Abstract: Predicting the mass yield of secondary organic aerosol (SOA) is a critical challenge in atmospheric science, creating major uncertainty in air quality and climate models. In this study, we use Automated Machine Learning (AutoML) to build an accurate estimator for SOA mass yield based on complex chemical simulation data. We then extend this model using quantile regression to quantify predictive uncertainty, generating a 90% prediction interval rather than single-point estimates. By translating these probabilistic yield predictions into a Mean Attributable Mortality (AMSOA) metric, we demonstrate a novel approach for conducting more robust, uncertainty-aware health impact assessments.
Authors: Sivachelvan, Kaventthan, O'Meara, Simon Patrick
Institutions: University of Surrey, University of Manchester
Language: English
Subfield: Atmospheric Science
Field: Earth and Planetary Sciences
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7084384666
FWCI:
Cites:
Cited by:
Related to: