Biography
I am a PGR based in Leeds at the University of Leeds working with Dr Xiaohui Chen, investigating Physics informed deep learning for groundwater prediction. I previously obtained a BSc and MSc with honors in Civil Engineering from University of Padua (Italy) and TU Delft (the Netherlands). For 5 years, I have then worked as an employee at the Dutch independent research institute Deltares. There I have undertaken a wide range of applied research and innovative consultancy projects related to flood defences. As a result of a 360-degrees feedback, colleagues showed appreciation for my pro-active approach and my sensitivity, defining me both as a collaborative team player and an independent worker. I am an extremely curious person. I learn something new every day and I get extremely enthusiast about it. Besides participating to several volunteering experiences, I have a healthy and sustainable lifestyle, made of tennis, piano playing, movies, books and good friends.
Qualifications
2013 – 2015: Masters in Civil Engineering from TU Delft
2010 – 2013: Undergraduate in Civil Engineering from University of Padua (Italy)
Research Interests
In my research, I integrate fundamental physics into the training process of deep learning processes, engaging computational modelling and deep neural network, in order to establish a new generation of physics informed deep learning methods, which can provide accurate and quick estimates of groundwater system response.
Project Title
Physics informed deep learning for groundwater prediction
Supervisors
Dr Xiaohui Chen, Dr He Wang, Professor Peter Jimack
Funding
Panorama NERC DTP, 2020 (Start year)
CASE project (industry partner: Deltares)
Project outline
Artificial Intelligence have attracted considerable attention from Civil Engineers over the last decade, especially Artificial Neural Networks (ANN) which can provide a flexible mathematical structure capable of identifying complex nonlinear relationships between input and output data sets. However, traditionally, ANNs have been trained using input and output datasets with simple loss functions, which incorporates no physical system knowledge into the learning process, while requiring huge amounts of data, which are either costly to produce or unavailable.
Alternatively, conceptual and computational modelling has continued rapid development in the past decades as it is based on fundamental constitutive physical equations and able to provide accurate analysis and prediction, however, it suffers from problems associated with computational performance, which can hinder its usage.
This project will integrate fundamental physics into the training process of deep learning processes, engaging computational modelling and deep neural network, and establish a new generation of physics informed deep learning methods, which can provide accurate and quick estimates of groundwater system response.
The outcome of this work will highly benefit to geotechnical engineering and groundwater protection in climate changing scenarios, for instance in the forecasting of drought.