Olu Oyebamiji

Oluwole expertise lies in theoretical foundations and multidisciplinary applications of Machine learning and Data mining, with a particular focus on Probabilistic modelling, Numerical optimization, and cutting-edge computational techniques for analysing high-dimensional spatio-temporal data.

Current projects

He is investigating challenges related to quantifying uncertainty and dealing with model over-parameterization. Some of his current works include:

• Developing a novel approach to environmental monitoring by integrating sparse convolutional neural networks and LSTM networks with fused satellite data.
• Applying Bayesian optimal weighting scheme for combining simulation ensemble for global climate projection.
• Performing uncertainty quantification for a large-scale climate impact and adaptation model using Bayesian probabilistic deep learning.

Past projects

• EA WRMP24 Decision-Making Process (2022-2023): A project to undertake assessments and provide support to the Environment Agency (EA) on Water Resources Management Plans (WRMP).
• Groundwater emulator (2022-2023): The future for groundwater in UK water resources planning. Comparing machine learning algorithms for emulating groundwater levels across the UK.
• FWY0596 (2022): Enhancements to Dam Monitoring from Satellites for Bristol Water (DAMSAT) Capability to Support Roll-out: Cloud masking. This project compared the performance of selected cloud masking algorithms for Sentinel-2 image data.
• D-MOSS (2021-2022): Dengue forecasting MOdel Satellite-based System in Vietnam. A dengue fever early warning forecasting system sponsored by the UK Space Agency. It combines the latest Earth Observation data from satellites with weather forecasts and other data to forecast dengue fever.
• DAMSAT (2021-2022): Dam Monitoring from Satellites for Bristol Water: A system that uses satellite technology to remotely monitor water and tailings dams and other tailings storage facilities. The system helps to reduce the risk of failure of these structures and the consequent risk to the downstream population and ecosystems.
• DSNE (2018-2021): Data Science for the Natural Environment. A joint project between Lancaster University and the Centre for Ecology & Hydrology (CEH), EPSRC-Funded. The aim is to co-create and deploy a data science of the natural environment driven by the grand challenges of environmental science.
• NUFEB (2015-2018): Newcastle University Frontiers in Engineering Biology - A new frontier in design: the simulation of open engineered biological systems. This is an EPSRC-funded Frontier Engineering award.
• ERMITAGE (2010-2013): Enhancing Robustness and Model Integration for the Assessment of Global Environmental Change (ERMITAGE), an FP7 EU-funded project which Involves the development of multidisciplinary modelling tools to address interactions of natural and socio-economic systems such as climate change, land use, energy market trends and economic development models for the assessment of global climate changes.

PhD in Statistics 2015

MPhil in Statistics 2010

MSc in Mathematics 2008

BSc in Statistics 2004