arXiv:2606.24660v1 Announce Type: cross Abstract: Phase-field models play a central role in the continuum description of phase separation, in which the bulk free-energy density and the interfacial thickness parameter determine pattern formation and microstructural evolution. In practice, these constitutive quantities are rarely known a priori and must be inferred from limited dynamical observations. In this work, an extended pseudo-spectral physics-informed neural network (ESPINN) framework is developed for the inverse identification of phase-field models from transient snapshot data. It enabl
The proliferation of advanced neural network techniques is enabling new applications for solving complex scientific and engineering problems previously intractable or highly computationally expensive.
This development allows for improved understanding and prediction of material behaviors critical to fields like materials science, energy, and manufacturing, potentially accelerating research and development.
The ability to infer complex constitutive quantities from limited data via AI will reduce the need for extensive experimental testing and theoretical derivation in phase-field model development.
- · Materials scientists
- · AI/ML researchers
- · Advanced manufacturing
- · Chemical engineering
- · Traditional experimental modeling approaches
- · Manual parameter estimation methods
More efficient and accurate simulation and design of new materials and processes.
Accelerated discovery of novel materials with bespoke properties for various industrial applications.
Potential for autonomous materials design systems, significantly impacting industrial R&D cycles and intellectual property creation.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG