A Phenomenological AI Foundation Model for Physical Signals

TL;DR

This paper introduces a phenomenological AI foundation model trained on diverse physical signals without prior physical knowledge, capable of generalizing across various phenomena and predicting unseen behaviors.

Contribution

It presents a novel phenomenological framework and a large-scale model that generalizes across multiple physical domains without relying on physical laws or inductive biases.

Findings

Effective encoding and prediction of physical behaviors

Generalizes to unseen phenomena

Scales across simple to complex physical processes

Abstract

The objective of this work is to develop an AI foundation model for physical signals that can generalize across diverse phenomena, domains, applications, and sensing apparatuses. We propose a phenomenological approach and framework for creating and validating such AI foundation models. Based on this framework, we developed and trained a model on 0.59 billion samples of cross-modal sensor measurements, ranging from electrical current to fluid flow to optical sensors. Notably, no prior knowledge of physical laws or inductive biases were introduced into the model. Through several real-world experiments, we demonstrate that a single foundation model could effectively encode and predict physical behaviors, such as mechanical motion and thermodynamics, including phenomena not seen in training. The model also scales across physical processes of varying complexity, from tracking the trajectory of a simple spring-mass system to forecasting large electrical grid dynamics. This work highlights the potential of building a unified AI foundation model for diverse physical world processes.