Email: b.alhnaity@mdx.ac.uk
Office address: TG11
Biography & Qualifications
Dr Bashar Al Hnaity is a lecturer in computer science (Machine Learning) at Middlesex University, London. He specialises in machine learning and deep learning, with expertise in building robust predictive models and end-to-end AI pipelines for real-world impact. At Middlesex, he teaches across undergraduate and postgraduate programmes in computer science, Artificial Intelligence, and Data analytics, and contributes to model design, assessment development, and academic citizenship.
His past and current work involves collaborating with national and international partners to develop end-to-end machine learning and deep learning solutions and data-driven products from data engineering and modelling through to evaluation and deployment. His core technical focus is advanced learning for complex data, particularly time series and spatiotemporal modelling, with applications in sustainability and smart systems.
Bashar earned a PhD in Machine Learning from Brunel University London, where his doctoral research developed integrated machine learning approaches for financial time series modelling and forecasting. His research has been carried out under projects funded by bodies including UKRI, EPSRC and NERC, and he has contributed to competitive funding proposals across these themes.
The primary theme guiding his work is impact-driven, deployable AI: advancing machine learning and deep learning methods while building practical, reproducible pipelines that integrate heterogeneous data sources (e.g., sensor, metrological, geospatial, biological, and socio-economic data) to support reliable decision-making in environmental and smart system applications.
Research Output & Interests
- Deep Learning and machine learning (end-to-end predictive modelling, robust AI pipelines)
- Generative modelling (representation learning and synthetic data generation for complex systems)
- Causal learning and causal inference (causality-aware modelling for reliable decision support)
- Time series and spatiotemporal deep learning (forecasting and sequential learning)
- Sustainability-focused AI (environmental and climate analytics using multimodal data)
- AI-powered digital twins for smart and sustainable systems
- Urban and environmental AI applications (e.g., Air quality, smart transportation, smart agriculture, energy optimisation, and GHG prediction)
Publications Repository
More here: https://scholar.google.com/citations?user=k9GPMbsAAAAJ&hl=en&oi=ao