Matthew Levine

Graduate Student in Computing + Mathematical Sciences

Advised by Andrew Stuart

California Institute of Technology

About me

Welcome! I am a graduate student in computing and mathematical sciences at Caltech. My work focuses on improving the prediction and inference of physical systems by blending machine learning, mechanistic modeling, and data assimilation techniques. I aim to build robust, unifying theory for these approaches, as well as develop concrete applications. I have worked substantially in the biomedical sciences, and enjoy collaborating on impactful applied projects.

Interests

Dynamical Systems
Machine Learning
Data Assimilation

Education

BA in Biophysics, 2015
Columbia University

Featured Publications

A Framework for Machine Learning of Model Error in Dynamical Systems

The development of data-informed predictive models for dynamical systems is of widespread interest in many disciplines. We present a …

Matthew E. Levine, Andrew M. Stuart

PDF

Ensemble Kalman methods with constraints

Ensemble Kalman methods constitute an increasingly important tool in both state and parameter estimation problems. Their popularity …

David J. Albers, Paul-Adrien Blancquart, Matthew E. Levine, Elnaz Esmaeilzadeh Seylabi, Andrew Stuart

PDF DOI

Mechanistic machine learning: how data assimilation leverages physiologic knowledge using Bayesian inference to forecast the future, infer the present, and phenotype

We introduce data assimilation as a computational method that uses machine learning to combine data with human knowledge in the form of …

David J. Albers, Matthew E. Levine, Andrew Stuart, Lena Mamykina, Bruce Gluckman, George Hripcsak

PDF DOI

Personalized glucose forecasting for type 2 diabetes using data assimilation

Type 2 diabetes leads to premature death and reduced quality of life for 8% of Americans. Nutrition management is critical to …

David J. Albers, Matthew Levine, Bruce Gluckman, Henry Ginsberg, George Hripcsak, Lena Mamykina

PDF DOI

Recent Publications

A Framework for Machine Learning of Model Error in Dynamical Systems

Matthew E. Levine, Andrew M. Stuart

PDF

Using Data Assimilation of Mechanistic Models to Estimate Glucose and Insulin Metabolism

Jami J. Mulgrave, Matthew E. Levine, David J. Albers, Joon Ha, Arthur Sherman, George Hripcsak

PDF

Enabling Personalized Decision Support with Patient-Generated Data and Attributable Components

Elliot G. Mitchell, Esteban G. Tabak, Matthew E. Levine, Lena Mamykina, David J. Albers

PDF

A Simple Modeling Framework For Prediction In The Human Glucose-Insulin System

D. J. Albers, M. E. Levine, M. Sirlanci, A. M. Stuart

PDF

See all publications

Experience

PhD Student

Computing + Mathematical Sciences, California Institute of Technology

Sep 2018 – Present Pasadena, CA

Advised by Professor Andrew Stuart

Research Associate

Biomedical Informatics, Columbia University Medical Center

Jul 2015 – Jul 2018 New York, NY

Supervised by Professors David Albers, George Hripcsak, and Lena Mamykina