AI-based Learning for Physical Simulation

Introduction

Computational physical modeling is a key resource to complement theoretical and experimental methods in modern scientific research and engineering. While access to large amounts of data has favored the use of Artificial Intelligence and Machine Learning (ML) techniques to enhance physical simulations, limitations of purely data-driven methods have emerged as concerns regarding their generalization capability and their intelligibility.

Importance of Intelligibility

In particular, the latter feature promotes understanding, a fundamental driver for scientific and technical progress. It possibly allows for rigorous investigation into the reliability of the models and the safety of the systems based on those models.

Proposed Hybrid Approach

To overcome these limitations, I propose a hybrid approach that originally combines ML methods and equation-based modeling to significantly improve generalization in small-data scenarios. This approach guarantees the intelligibility of the physical models through the use of symbolic representations.

Methodology

Core to the methodology are learning algorithms that reconstruct models with controllable complexity from data by consistently combining building blocks, which derive from a unifying mathematical framework for physical theories.

Knowledge Distillation Strategies

The system will also incorporate novel human-inspired strategies for knowledge distillation, accumulation, and reuse, which are missing in state-of-the-art physical model learning algorithms.

Software Implementation

To efficiently handle the computational cost associated with the proposed methods, I will implement them in a new software platform that seamlessly integrates automated model learning and high-performance simulation.

Applicability

Thanks to their general-purpose nature, the methods and algorithms developed in this project may be employed in all scientific disciplines and in engineering workflows. In particular, I plan to use them to advance biology and soft robotics by solving challenging modeling tasks.