Research Project: Reduced order modelling of land subsidence
Why did you apply for this internship?
The internship is a good bridge to such a PhD, and will provide me with more research skills which I feel can be developed further following my dissertation earlier this year.
Furthermore, I am looking to explore the field of numerical geotechnical engineering further, as my dissertation only covered one software, which was new and not as commonly used, whilst in the project for my internship, I will be using more commercial and widespread software.
Finally, I wish to contribute to research and return to my department, as I am grateful for the years I spent at my university during my undergraduate degree. The chance to collaborate on this project is something that I am looking forward to.
What did you hope to gain in completing this project?
I hope to gain the technical skills, as well as the general skills involved in research, such as report writing and data analysis. Whilst they can be seen as generic or standard skills that most researchers will already have honed to a high level, I feel that I have yet to reach that level, and hope that as I can spend most of my time on the project (unlike during my studies at my university), I can finally improve myself further.
As part of the project, I hope to improve my programming skills (Python), as well as computational thinking capabilities, which are a significant part of my project. I also hope to be able to contribute positively to this project that my supervisors are in charge of, as I am appreciative of the opportunity to have been selected for such an internship.
Project Overview
This project develops a neural network to predict land subsidence at specific locations, where groundwater movements are the main driver of such subsidence. Machine learning is used to map soil profiles, which describe the current state of the soil, to corresponding land subsidence values at specific times. This process is facilitated through Bede, where Julia scripts are submitted to train the neural network.
What were the key results of your research project?
Soil profiles can be successfully mapped to land subsidence, but the neural networks developed in this project only capture general trends, and missseasonal variations. Deeper networks like LSTMs or DeepONets would be a promising direction for future work, in order to capture these seasonal variations, and become suitable for practical use.
Another improvement would be relaxing the assumptions made when creating the soil profiles, which arise mainly from the use of Terzaghi's 1D consolidation equation. This would require additional geotechnical engineering expertise as well as considerable increases in data processing, but could enable much more precise, location specific soil profiles.
Non-dimensionalisation of the soil profiles could also further enhance the robustness of the training, especially with limited training data, alongside simply training with more labelled training data.
How do you feel you have benefitted from completing this internship and has it made you consider future career paths?
I feel much more confident in using HPC resources to conduct computationally intensive research, especially in the context of geotechnical engineering, where I can utilise such resources to solve problems that I have learnt over the past few years in my degree on a massive scale.
Naturally, I feel more confident in independent research, and working from advice given by supervisors and superiors without a clear answer. I had a similar experience when undertaking my dissertation earlier this year, so this was a sort of extension as I also had many directions and methods to try in this internship, with no singular clear answer.
This internship has therefore attracted me more towards scientific research, where HPC can be utilised to create practical solutions and methods based off existing ones, and I have definitely considered pursuing such a path more than before the start of the internship.