Estimating air quality co-benefits of energy transition using machine learning

Estimating health benefits of reducing fossil fuel use from improved air quality provides important rationales for carbon emissions abatement. Simulating pollution concentration is a crucial step of the estimation, but traditional approaches often rely on complicated chemical transport models that require extensive expertise and computational resources. In this study, we develop a novel and succinct machine learning framework that is able to provide precise and robust annual average fine particle (PM2.5) concentration estimations directly from a high-resolution fossil energy use data set. The accessibility and applicability of this framework show great potentials of machine learning approaches for integrated assessment studies. Applications of the framework with Chinese data reveal highly heterogeneous health benefits of reducing fossil fuel use in different sectors and regions in China with a mean of \$34/tCO2 and a standard deviation of \$84/tCO2. Reducing rural and residential coal use offers the highest co-benefits with a mean of \$360/tCO2. Our findings prompt careful policy designs to maximize cost-effectiveness in the transition towards a carbon-neutral energy system.

Model-based Bayesian inference of disease outbreak dynamics with invertible neural networks

Mathematical models in epidemiology strive to describe the dynamics and important characteristics of infectious diseases. Apart from their scientific merit, these models are often used to inform political decisions and interventional measures during an ongoing outbreak. Since high-fidelity models are often quite complex and analytically intractable, their applicability to real data depends on powerful estimation algorithms. Moreover, uncertainty quantification in such models is far from trivial, and different types of uncertainty are often confounded. With this work, we introduce a novel coupling between epidemiological models and specialized neural network architectures. This coupling results in a powerful Bayesian inference framework capable of principled uncertainty quantification and efficient amortized inference once the networks have been trained on simulations from an arbitrarily complex model. We illustrate the utility of our framework by applying it to real Covid-19 cases from entire Germany and German federal states.