Weekly PhD Newsletter | SIGN UP NOW Weekly PhD Newsletter | SIGN UP NOW

Low-Carbon Policy Evaluation for Manufacturing Supply Chains using Causal Machine Learning (Advert Ref: SF22/EE/CIS/HU)

   Faculty of Engineering and Environment

  Dr Shanfeng Hu  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

The recent disruptions of oil and gas supply in the UK and around the world are crippling industrial manufacturers that turn heavy fossil energy consumptions to semi-raw materials and parts. While the surging demand of post Covid-19 recovery is partly responsible for the challenges faced by the supply chains of manufacturers, a deeper and much longer-lasting root cause is the uncertainty of government policies for curbing carbon emissions.

In the context of these challenges, manufacturers, along with their upstream suppliers and downstream consumers, are in a pressing need of capturing and quantifying the impacts of risks (e.g., high cost, shortage of supply, supply shock) posed by carbon-incurred prices. In this project, we aim to develop causal machine learning and mathematical programming to investigate new and comprehensive low-carbon policy evaluation framework for manufacturing supply chains. The objectives of the proposed work are three-folds. First, we build a comprehensive ‘structural causal model’ for low-carbon policy factors and supply chain structures, by capitalizing on the outcomes of a recently completed Innovate UK-funded study on smart supply chains and manufacturing processes. The model, being causal in nature, is fundamentally different from traditional machine learning and deep learning ones, allowing us to characterize and quantify the impacts of interventions. Second, we estimate its unknown parameters residing in the structural equations by fitting the model to observational data.

To evaluate the impacts of the proposed work, we consider two key use scenarios. One is interventional – tracking the status of low-carbon policies and simulating their impacts on supply chain costs and resilience. The other is counterfactual – searching for alternative supply chain structures that are less costly and more resilient to carbon emission targets. Both goals matter in the period of transition from fossil fuels to greener energies.

For informal enquiries please contact

Eligibility and How to Apply: 

Please note eligibility requirement:  

·               Academic excellence of the proposed student i.e. 2:1 (or equivalent GPA from non-UK universities [preference for 1st class honours]); or a Masters (preference for Merit or above); or APEL evidence of substantial practitioner achievement. 

·               Appropriate IELTS score, if required. 

For further details of how to apply, entry requirements and the application form, see 


Please note: Applications that do not include a research proposal of approximately 1,000 words (not a copy of the advert), or that do not include the advert reference (e.g. SF22/…) will not be considered. 

Start Date: 1 October 2022 

Funding Notes

Please note this is a self-funded project and does not include tuition fees or stipend.


Recent publications by the principal supervisor on Artificial Intelligence and Machine Learning:
- Hu, S., Shum, H.P., Liang, X., Li, F.W. and Aslam, N., 2021. Facial reshaping operator for controllable face beautification. Expert Systems with Applications, 167, p.114067.
- Hu, S., Liang, X., Shum, H.P., Li, F.W. and Aslam, N., 2020. Sparse metric-based mesh saliency. Neurocomputing, 400, pp.11-23.
- Hu, S., Shum, H.P., Aslam, N., Li, F.W. and Liang, X., 2019. A Unified Deep Metric Representation for Mesh Saliency Detection and Non-rigid Shape Matching. IEEE Transactions on Multimedia, 22(9), pp.2278-2292.
- Hu, S., Shum, H.P. and Mucherino, A., 2019. DSPP: Deep Shape and Pose Priors of Humans. In Motion, Interaction and Games (pp. 1-6).
- Hu, S., Bhattacharya, H., Chattopadhyay, M., Aslam, N. and Shum, H.P., 2018, December. A Dual-Stream Recurrent Neural Network for Student Feedback Prediction using Kinect. In 2018 12th International Conference on Software, Knowledge, Information Management & Applications (SKIMA) (pp. 1-8). IEEE.
- Hu, S., Rueangsirarak, W., Bouchée, M., Aslam, N. and Shum, H.P., 2017, December. A motion classification approach to fall detection. In 2017 11th International Conference on Software, Knowledge, Information Management and Applications (SKIMA) (pp. 1-6). IEEE.
Recent publications from the second supervisor (Prof Wai Lok Woo) on Machine Learning:
- R.R.O. Al-Nima, T. Han, S. Al-Sumaidaee, T. Chen, W.L. Woo, “Enhancing the Robustness and Performance of Deep Reinforcement Learning,” Applied Soft Computing, vol. 105, no. 107295, 2021
- J. Ahmed, B. Gao, W.L. Woo, “Sparse Low-Rank Tensor Decomposition for Defect Detection Using Thermographic Imaging Diagnostics,” IEEE Trans. on Industrial Informatics, vol. 17, no. 3, pp. 1810-1820, 2021
- N. Tengtrairat, W.L. Woo, P. Parathai, C. Aryupong, P Jitsangiam, D. Rinchumphu, “Automated Landslide-Risk Prediction using Web GIS and Machine Learning Models,” Sensors 2021, 21(13), 4620

Email Now

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs