team
Computational Science and Machine Learning Lab (CSML) at Cal State Long Beach
Computational Science and Machine Learning Lab (CSML)
The Computational Science and Machine Learning Lab (CSML) is an interdisciplinary research lab at Cal State Long Beach focusing on aiding scientific computation using algorithmic innovation and machine learning methodologies.
GitHub: https://github.com/csml-beach
Our work concentrates on developing novel algorithms and models that can effectively meld complex data from multiple sources to improve our understanding of various scientific phenomena. We aim to contribute to the development of more accurate and reliable predictive models that can be used in a wide range of applications.
Research Focus
Our research interests span a wide range of topics, including data-driven modeling and simulation, uncertainty quantification, and optimization. We use state-of-the-art machine learning techniques in deep learning, reinforcement learning, and Bayesian learning to develop robust and efficient solutions to these problems. Our goal is to create novel approaches to scientific computation that bring together traditional methods and cutting-edge machine learning techniques.
Student Mentorship
At CSML, we believe in providing our students with individual attention, clear expectations, and ongoing support and mentoring on writing, presentation, and programming skills. We are looking for students who have demonstrated strong programming skills, research or project experience, dependability, initiative, and excellent communication skills. As mentors, we strive to create a welcoming and inclusive environment for our students to learn and grow.
Prospective Students
If you are interested in pursuing research in this exciting and rapidly growing field, we invite you to join our team at CSML. The best way to get in touch is by filling out this short survey.
Members
Arash Sarshar
Director
ECS 536
Director of CSML. Assistant Professor in the Department of Computer Engineering and Computer Science at California State University, Long Beach. Research interests include scientific machine learning, computational science, and uncertainty quantification.
Gabriel Lucero
PhD Student
Gabriel Lucero is currently pursuing a PhD in Computational Mathematics and Engineering. Previously, he has worked on projects in NMR, signal processing, and biology. His current research interests include uncertainty quantification in machine learning and using AI/ML in science and engineering.
Sakol Bun
MSc Student
Sakol Bun is currently pursuing a Master’s degree in Computer Science at California State University, Long Beach (CSULB). As an undergraduate student at CSULB, he has gained experience in machine learning, backend development, and cloud computing. His academic pursuits are deeply rooted in artificial intelligence, with a specific focus on uncertainty quantification for data-driven predictive models.
Amogh Raj
MSc Student (Former)
Amogh Raj is currently pursuing his final year in MSc Computer Science. His educational background encompasses an undergraduate degree in Computer Science, complemented by a cumulative 4-year professional experience in Data Engineering, Backend Application development, and Software Engineering. At CSML, Amogh is working on design and implementation of Physics-Informed Neural Networks (PINNs) using a Bayesian approach to solve complex Partial Differential Equations (PDEs).
Carol Gudumotu
MSc Student (Former)
Carol Gudumotu is a graduate computer science student at CSULB. Her Master’s thesis focuses on Uncertainty Quantification in deep learning neural networks. Her academic interests include Machine Learning and Software development.
Keerthana Srinivasa
MSc Student (Former)
Keerthana Srinivasa holds a bachelor’s degree in computer science and is currently pursuing a master’s degree in the same field. Over the course of four years at Honeywell, Keerthana has accumulated extensive experience working with databases, systems, and data engineering in various capacities. Her research at CSML is dedicated to solving inverse problems for chaotic flows, specifically concentrating on predictive models for fire detection.