Jacob Serpico

Background

About Jacob Serpico

I am an applied mathematician who specializes in turning modelling efforts into actionable insights. My background is in differential equations and ML-based approaches to forecasting, optimization, and scientific modelling. My more recent work spans environmental risk (predicting and managing harmful algal blooms), renewable energy analytics (pricing and operational forecasting), and uncertainty quantification/identifiability. Hence, my models are not only accurate but defensible. Specifically, my research has led to peer-reviewed publications and conference presentations, alongside industry projects that deliver a deployable model and actionable insights. In my analyst roles, I’ve built data pipelines, forecasting and pricing models, and decision support tools. In my academic work, I’ve designed and validated spatiotemporal models, developed surrogate models to accelerate calibration, and run sensitivity analyses to isolate the key drivers of outcomes. At the University of Alberta, I conduct and publish independent research in applied mathematics and scientific ML, in addition to teaching undergraduate multivariable calculus, differential equations, and linear algebra. I also collaborate with partners in energy and the environmental sciences on field-informed modelling problems and welcome conversations about joint projects where rigorous mathematics and practical constraints meet. Specialties: Differential equation models, time-series forecasting, ML, optimization, uncertainty quantification, experiment/sensitivity design, and reproducible analysis. Tools: Python, Tensorflow & Keras, PyTorch, NumPy/Pandas, scikit-learn, SQL, Git, and LaTeX. Interests: Energy and environment R&D, quantitative research, and research in mathematical biology or scientific ML.