Control Theory
Uncertainty Quantification
Bayesian Inference
Inverse Problems
Stochastic Processes
Time Series Analysis
Optimal Control
Probabilistic Modelling
Machine Learning
Python
Pandas
NumPy
R
C#
Matlab
Tensorflow
Authored a deterministic system that calculates the risk of liquefaction in a given area. Also developed a probabilistic model that extends calculations to account for uncertainties in the input parameters.
Developed software that offers a probabilistic approach to analyzing pile foundation behavior, accounting for uncertainties in soil properties and loads.
Wrote a Python library for engineers and researchers. It offers a powerful set of tools for analyzing soil mechanics, foundation design, and slope stability. Its interface and robust algorithms streamline complex geotechnical modeling, enhance accuracy, and simplify workflows.
This thesis improves the development of Artificial Pancreas systems for Type 1 diabetes by using Bayesian inference to address modeling errors, and tested these improvements through numerical simulations.
This study shows that the traditional method for predicting how structures respond to earthquakes is inaccurate, and suggests that modifying the load calculations based on experimental data can improve predictions.
Ran a study that improved how we measure the forces on a structure during shaking tests. It accomplished by using specialized equipment to get more accurate results. Published at the 2018 New Zealand Society for Earthquake Engineering Conference
Developed probabilistic risk models and analyzed large datasets to inform business decisions and develop digital products. I worked closely with cross-functional teams, using advanced mathematical models and statistical analysis to solve complex problems.