A cyclical route linking fundamental mechanism and AI algorithm: An example from tuning Poisson's ratio in amorphous networks
This work addresses the problem of bridging AI and scientific discovery for researchers in materials science and physics, though it is incremental as it builds on existing AI methods in a specific domain.
The paper tackled the challenge of using AI to uncover physical mechanisms and then applying those insights to enhance AI algorithms, using the prediction of Poisson's ratio in amorphous networks as a case study. It achieved a significant efficiency improvement in predicting Poisson's ratio by training a convolutional neural network on dynamical matrices instead of traditional images.
"AI for science" is widely recognized as a future trend in the development of scientific research. Currently, although machine learning algorithms have played a crucial role in scientific research with numerous successful cases, relatively few instances exist where AI assists researchers in uncovering the underlying physical mechanisms behind a certain phenomenon and subsequently using that mechanism to improve machine learning algorithms' efficiency. This article uses the investigation into the relationship between extreme Poisson's ratio values and the structure of amorphous networks as a case study to illustrate how machine learning methods can assist in revealing underlying physical mechanisms. Upon recognizing that the Poisson's ratio relies on the low-frequency vibrational modes of dynamical matrix, we can then employ a convolutional neural network, trained on the dynamical matrix instead of traditional image recognition, to predict the Poisson's ratio of amorphous networks with a much higher efficiency. Through this example, we aim to showcase the role that artificial intelligence can play in revealing fundamental physical mechanisms, which subsequently improves the machine learning algorithms significantly.