FREE Virtual Study Fair | 1 - 2 March | REGISTER NOW FREE Virtual Study Fair | 1 - 2 March | REGISTER NOW

A machine learning-enabled framework to quantify the structural uncertainty induced by aerosol representation in Earth system models

   Department of Earth and Environmental Sciences

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Dr Zhonghua Zheng, Dr D Topping, Prof Hugh Coe  No more applications being accepted  Funded PhD Project (UK Students Only)

About the Project

The use of Artificial Intelligence in Earth and environmental sciences is on the rise, however, there is a desire to limit the amount of training data while training a decent data-driven model. Aerosols, on the other hand, contribute to the large uncertainty in estimates of climate radiative forcing, but they are difficult to model. Here we are interested in developing an "economical and automated” machine learning framework for aerosol modelling, and investigating the effects of aerosol representation in Earth system models. Specifically, we will 1) develop a machine learning-enabled framework that integrates particle-resolved model simulations and data-driven emulation in a way that minimizes the effort required to collect training data and optimizes the learning process; and 2) utilize the framework to quantify the structural uncertainty induced by aerosol representations in Earth system models over the globe for multi-year simulations. The results will provide insight into potential improvements to model process representation of aerosols towards better radiative forcing estimations. The machine learning framework can be used for various applications in environmental engineering and science.

To make an application please visit -

Please search and select PhD Environmental Science (academic programme) and PhD Atmospheric Science(academic plan)

Equality, diversity and inclusion is fundamental to the success of The University of Manchester, and is at the heart of all of our activities. We know that diversity strengthens our research community, leading to enhanced research creativity, productivity and quality, and societal and economic impact. We actively encourage applicants from diverse career paths and backgrounds and from all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status.

We also support applications from those returning from a career break or other roles. We consider offering flexible study arrangements (including part-time: 50%, 60% or 80%, depending on the project/funder).

All appointments are made on merit.

Funding Notes

Department funded - fees and stipend provided at the current UKRI rate. Start date July 2023


Zheng, Z.*, West, M., Zhao, L., Ma, P., Liu, X., & Riemer, N.* (2021). Quantifying the structural uncertainty of the aerosol mixing state representation in a modal model. Atmospheric Chemistry and Physics. doi: 10.5194/acp-21-17727-2021
Zheng, Z.*, Curtis, J. H., Yao, Y., Gasparik, J. T., Anantharaj, V. G., Zhao, L., West, M., & Riemer, N.* (2021). Estimating Submicron Aerosol Mixing State at the Global Scale with Machine Learning and Earth System Modeling. Earth and Space Science. doi:10.1029/2020EA001500
Zheng, Z., Zhao, L. & Oleson, K.W. (2021). Large model structural uncertainty in global projections of urban heat waves. Nature Communications. doi: 10.1038/s41467-021-24113-9
Yao, Y., Curtis, J. H., Ching, J., Zheng, Z., & Riemer, N. (2022). Quantifying the effects of mixing state on aerosol optical properties. Atmospheric Chemistry and Physics. doi: 10.5194/acp-22-9265-2022
Huang, L., & Topping, D.* (2021). JlBox v1.1: a Julia-based multi-phase atmospheric chemistry box model. Geoscientific Model Development, 14(4), 2187-2203. doi: 10.5194/gmd-14-2187-2021

How good is research at The University of Manchester in Earth Systems and Environmental Sciences?

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities
PhD saved successfully
View saved PhDs