The BERLIN project is excited to welcome Dr. Tolulope Odunola and Dr. Davide Spinelli, who joined the team between January and February 2026. Their work will contribute to strengthening the team’s expertise in water systems analysis, Inverse Reinforcement Learning, and evidence-based climate adaptation policies.
Tolulope Odunola
Tolulope Odunola is a Water Systems Analyst and Postdoctoral Research Fellow at Politecnico di Milano. She holds a BSc. in Civil Engineering from the University of Ibadan, Nigeria, and MSc. and Ph.D. degrees in Environmental Engineering from the University of Cincinnati, Ohio, USA. She has experience in development project planning, specifically providing stakeholders and decision-makers in water resources engineering with robust analytical frameworks, tools, and decision metrics that support confident decisions under climate and other uncertainties. She has worked with academics, engineering professionals and multi-disciplinary teams across multiple institutions including the Millennium Challenge Corporation (MCC), the US Army Corps of Engineers (USACE), the World Bank and Deltares. Within BERLIN, Tolulope seeks to identify locally grounded adaptation policies for multipurpose reservoir systems using an evidence-based foundation. By assessing the impact of behavioural uncertainty on the evolution of multipurpose reservoir systems, she aims to contribute to more robust operation and management of water systems under changing conditions.
Davide Spinelli
Davide Spinelli is a Postdoctoral Research Fellow at Politecnico di Milano, where he also earned his Ph.D. in Information Technology, M.Sc. in Computer Science and Engineering, and B.Sc. in Automation Engineering. During his master’s program, he completed exchange periods at University College London and Technische Universität Berlin, and focused his thesis on multi-agent Inverse Reinforcement Learning (IRL). His doctoral work, which included a visiting period at Duke University and a collaboration with Consorzio dell’Adda, advanced Reinforcement Learning and the use of probabilistic forecasts for multi-objective reservoir operations. His expertise spans developing interpretable neuro-evolutionary frameworks and quantifying trade-offs among competing water demands.
Within BERLIN, Davide applies IRL to observational data to model agent preferences in multi-objective water systems. By replacing traditional heuristic rules with empirical, data-driven behavioural representations, he aims to simulate coupled human-natural systems globally and integrate reservoir operations into hydrologic models for future scenario simulation.
