Uncertainty Quantification for Surface Ozone Emulators using Deep Learning
By: Kelsey Doerksen , Yuliya Marchetti , Steven Lu and more
Potential Business Impact:
Predicts air pollution to help keep people healthy.
Air pollution is a global hazard, and as of 2023, 94\% of the world's population is exposed to unsafe pollution levels. Surface Ozone (O3), an important pollutant, and the drivers of its trends are difficult to model, and traditional physics-based models fall short in their practical use for scales relevant to human-health impacts. Deep Learning-based emulators have shown promise in capturing complex climate patterns, but overall lack the interpretability necessary to support critical decision making for policy changes and public health measures. We implement an uncertainty-aware U-Net architecture to predict the Multi-mOdel Multi-cOnstituent Chemical data assimilation (MOMO-Chem) model's surface ozone residuals (bias) using Bayesian and quantile regression methods. We demonstrate the capability of our techniques in regional estimation of bias in North America and Europe for June 2019. We highlight the uncertainty quantification (UQ) scores between our two UQ methodologies and discern which ground stations are optimal and sub-optimal candidates for MOMO-Chem bias correction, and evaluate the impact of land-use information in surface ozone residual modeling.
Similar Papers
Leveraging Deep Learning for Physical Model Bias of Global Air Quality Estimates
Machine Learning (CS)
Predicts air pollution to improve health and policy.
Analyzing Uncertainty Quantification in Statistical and Deep Learning Models for Probabilistic Electricity Price Forecasting
Machine Learning (CS)
Predicts electricity prices more accurately, even when unsure.
Air Quality Prediction Using LOESS-ARIMA and Multi-Scale CNN-BiLSTM with Residual-Gated Attention
Machine Learning (CS)
Predicts air pollution spikes to help cities breathe easier.