º£½ÇÉçÇø

[Defense] Physics Informed Decision Tree

Monday, November 25, 2024

4:30 pm - 6:00 pm

In Partial Fulfillment of the Requirements for the Degree of Master of Science

Melis Ilhan
will defend her thesis

Physics Informed Decision Tree

Abstract

Physics-informed neural networks (PINN) have become a well-known machine learning (ML) model in the physics domain where partial differential equations (PDE) are commonly used. PINN can efficiently learn the underlying physics pattern and perform accurate predictions. However, due to the black-box nature of the artificial neural networks, it is lack of interpretability. Furthermore, calculating the derivatives for solving PDEs makes the model computationally expensive. To address these limitations of PINN, we introduce a novel model, a physics-informed decision tree (PIDT). This approach aims to leverage the advantages of the decision trees, such as interpretability and cost-effective computation, while still having physics-integrated architecture. The introduced model’s accuracy and efficiency are illustrated and compared with the traditional PINN and traditional decision tree on Burger’s Equation. Experiment results show that PIDT has significantly faster training time than the traditional PINN while maintaining a sufficiently similar accuracy. It has comparable training time with the traditional decision tree, but PIDT has significantly better accuracy performance. The comparison of the models demonstrates a promising result that PIDT can accurately perform and accelerate training speed, which can be essential in real-world problems.

Monday, November 25, 2024
4:30 PM - 6:00 PM

PGH 550

Dr. Jinyang Liu, thesis advisor

Faculty, students and the general public are invited.