
Ammar Hamdi
- Email: ml21aamh@leeds.ac.uk
- Thesis title: Leveraging Deep Learning and Physics-Informed Analysis to Identify, Track, and Predict Macroplastic Waste Emission, Movement, and Accumulation in Terrestrial Environments
- Supervisors: Professor Nikolaos Nikitas, Professor Evangelos Pournaras, Dr Konstantinos Velis
Profile
I am a first-year postgraduate researcher in the School of Civil Engineering at the University of Leeds, with an academic background in civil and environmental engineering. Prior to beginning my PhD studies, I earned a BSc in Civil Engineering from Jazan University, KSA, in 2019. In 2023, I earned an MSc in Environmental Engineering and Project Management with distinction from the University of Leeds, UK. My dissertation focused on quantifying municipal solid waste generation and management in Arab Peninsula countries, and explored the socioeconomic factors influencing waste generation and management practices in the region.
I have professional experience in both academia and industry. Since 2023, I have been working as a lecturer in the College of Engineering and Computing Sciences at Jazan University, KSA. Prior to this, I worked as a teaching assistant from 2020 to 2023. Additionally, I gained practical civil engineering experience while working on the Jazan Economic City Port and Infrastructure Project (JEXPI) as a civil engineer from 2019 to 2020.
Research interests
My research interests lie in solid waste management, with a particular focus on plastic pollution prevention and modelling. For my PhD research, I aim to advance understanding of macroplastic waste (MPW) transport across terrestrial environments by leveraging the strengths of deep learning techniques and physics-informed analysis to effectively identify, track, and predict MPW emission mechanisms, movement, and accumulation on land.
This research will not only support the development of a generalizable model for MPW identification and tracking across diverse terrains, but also advance scientific understanding of MPW behaviour, improve data quality, and enhance the predictive accuracy and realism of MPW transport models. It will provide critical insights into the small-scale movements of MPW on land, which help inform larger-scale transport pathways. These insights will provide data-driven support for local action plans through targeted mitigation strategies and integration into monitoring systems, enabling early detection of hotspots and timely intervention before MPW reaches sensitive or harder-to-control environments.
Qualifications
- MSc (Eng) in Environmental Engineering and Project Management, University of Leeds, UK (2023)
- BSc in Civil Engineering, Jazan University, KSA (2019)