A Phenomenological AI Foundation Model for Physical Signals
This work aims to build a unified AI model for diverse physical processes, which could benefit fields like engineering and science, but it appears incremental as it extends foundation model concepts to physical signals.
The authors tackled the problem of creating a general AI foundation model for physical signals without using prior physical knowledge, and demonstrated that their model, trained on 0.59 billion cross-modal sensor samples, could encode and predict diverse physical behaviors, including unseen phenomena.
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.