• 🔬 I'm a Research Fellow at the Research Centre for Computational Science and Mathematical Modelling (CSM), Coventry University. I work on HOPE-MOVE, an Innovate UK-funded project using AI and machine learning to personalise digital support for movement and healthy lifestyles.

• 🎓 I completed my PhD in Computational Science & Mathematical Modelling, focused on spatiotemporal deep learning and optimisation for epidemic forecasting and healthcare resource allocation.

• 🧠 My research sits at the intersection of machine learning, scientific computing and public health: classical and deep forecasting, graph neural networks, hybrid mechanistic–neural models, physics-informed neural networks (PINNs) and time-series analysis.

• 👨‍🏫 I'm also an Associate Lecturer at QA Higher Education (QAHE), teaching computing, client-side development and deep learning, and mentoring students on MSc projects and dissertations.

• 🎖️ I'm an Associate Fellow of the Higher Education Academy (AFHEA).

• 👯 I'm open to collaboration on scientific machine learning, time-series and graph forecasting, computer vision, PINNs, and applied AI for health.

• 📫 Reach me at ajaoolarinoyemichael@gmail.com

• ⚡ Fun fact: I believe my research can change the world—right after I find that missing semicolon.

• Forecasting for Public Health — Building and benchmarking statistical, sequence deep-learning, graph-based spatiotemporal, and hybrid mechanistic–neural forecasting models.

• Scientific Machine Learning — Applying PINNs to cardiovascular haemodynamics, including pulsatile flow, wall-shear-stress prediction and arterial aneurysm modelling.

• Digital Health & Clinical ML — Developing machine-learning services and decision-support tools for the HOPE-MOVE digital health intervention.

• Healthcare Resource Allocation — Optimisation and modelling for distributing constrained healthcare resources during infectious-disease outbreaks.

• Rehman, M. A. U., et al. (including Ajao-Olarinoye, M.). “Fluid–structure interaction analysis of pulsatile flow in arterial aneurysms with physics-informed neural networks and computational fluid dynamics.” Physics of Fluids, 37(3), 031913, 2025.

• Ajao-Olarinoye, M., Palade, V., Mousavi, S., He, F., & Wark, P. A. “Deep Learning Based Forecasting of COVID-19 Hospitalisation in England: A Comparative Analysis.” 2023 International Conference on Machine Learning and Applications (ICMLA), pp. 1344–1349, 2024.

• Ajao-Olarinoye, M., et al. “A Hybrid Physics-Informed Neural Network: SEIRD Model for Forecasting COVID-19 Intensive Care Unit Demand in England.” In Recent Advances in Deep Learning Applications: New Techniques and Practical Examples, CRC Press, pp. 231–256, 2025.

• Ajao-Olarinoye, M., et al. “MSAGAT-Net: Multi-Scale Temporal Adaptive Graph Attention for Efficient Spatiotemporal Epidemic Forecasting.” Preprint, 2025. DOI: 10.2139/ssrn.5719497

📄 Profiles: Google Scholar · Coventry PURE · ORCID · ResearchGate

• Associate Lecturer, QA Higher Education — computing, client-side development and deep learning.
• Supervisor and mentor for MSc projects and dissertations in Python, machine learning, computer vision and algorithm design.
• Associate Fellow of the Higher Education Academy (AFHEA).
• Volunteer Teaching Assistant at CodeYourFuture, supporting learners entering technology careers.

Languages
Python · Julia · JavaScript · SQL · Bash · LaTeX

Machine Learning & Scientific ML
PyTorch · TensorFlow · scikit-learn · NumPy · SciPy · pandas · Graph Neural Networks · Physics-Informed Neural Networks

Data & Applications
FastAPI · Streamlit · MySQL · Git · Docker

Domains
Time-series forecasting · Spatiotemporal modelling · Computational fluid dynamics · Epidemiological modelling · Optimisation · Digital health

Open to collaboration and discussion on scientific machine learning, forecasting, PINNs, and applied AI for health.