Inverse Design of Amorphous Materials With Targeted Properties
4 affiliations
- 1Department of Chemistry and Bioscience Aalborg University Aalborg Øst Denmark
- 2Department of Computer Science Aalborg University Aalborg Øst Denmark
- 3Department of Applied Physics The Hong Kong Polytechnic University Kowloon Hong Kong China
- 4School of Data Science and Engineering East China Normal University Shanghai China
Abstract
Disordered (amorphous) materials, such as glasses, are emerging as promising candidates for applications within energy storage, nonlinear optics, and catalysis. Their lack of long-range order and complex short- and medium-range order, which depend on composition as well as thermal and pressure history, offer a vast materials design space. To this end, relying on machine learning methods instead of trial and error is promising, and among these, inverse design has emerged as a tool for generating materials with desired properties. Although inverse design methods based on diffusion models have shown success for crystalline materials and molecules, similar methods targeting amorphous materials remain less developed, mainly because of the limited availability of large-scale datasets and the requirement for larger simulation cells. In this work, we propose and validate an inverse design method for amorphous materials, introducing AMDEN (Amorphous Material DEnoising Network), a diffusion model-based framework that generates structures of amorphous materials. First, we demonstrate the inherent challenges for diffusion models to generate relaxed structures. These low-energy configurations are typically obtained through a thermal motion-driven random search-like process that cannot be replicated by standard denoising procedures. We therefore introduce an energy-based AMDEN variant that implements Hamiltonian Monte Carlo refinement for generating these relaxed structures. We further introduce several amorphous material datasets with diverse properties and compositions to evaluate our framework and support future development.
Related
- Explicit pore pre-conditioning and inverse design of amorphous nanoporous carbon
- Machine Learning-Empowered Electromagnetic Wave Absorbing Materials: From Forward Prediction to Generative Inverse Design
- Small Organic Molecule-Based Multicolor Fluorescent Smart Materials: From Design Principles and Optical Properties to Versatile Applications
- Next-generation electronic packaging materials: thermal-dielectric properties and design strategies in PI and PTFE-based composites
- Targeted Chemical Functionalization of the Amorphous Phase in Polyolefins via Controlled Solvent Swelling.
BibTeX
@article{finkler2026inverse,
title = {{Inverse Design of Amorphous Materials With Targeted Properties}},
author = {Jonas A. Finkler and Yan Lin and Tao Du and Jilin Hu and Morten M. Smedskjær},
journal = {Advanced Materials},
year = {2026},
month = jun,
doi = {10.1002/adma.202522493},
url = {https://doi.org/10.1002/adma.202522493},
note = {CC BY},
}
RIS
TY - JOUR
TI - Inverse Design of Amorphous Materials With Targeted Properties
AU - Jonas A. Finkler
AU - Yan Lin
AU - Tao Du
AU - Jilin Hu
AU - Morten M. Smedskjær
PY - 2026
DA - 2026/06/09
JO - Advanced Materials
DO - 10.1002/adma.202522493
UR - https://doi.org/10.1002/adma.202522493
AB - Disordered (amorphous) materials, such as glasses, are emerging as promising candidates for applications within energy storage, nonlinear optics, and catalysis. Their lack of long-range order and complex short- and medium-range order, which depend on composition as well as thermal and pressure history, offer a vast materials design space. To this end, relying on machine learning methods instead of trial and error is promising, and among these, inverse design has emerged as a tool for generating materials with desired properties. Although inverse design methods based on diffusion models have shown success for crystalline materials and molecules, similar methods targeting amorphous materials remain less developed, mainly because of the limited availability of large-scale datasets and the requirement for larger simulation cells. In this work, we propose and validate an inverse design method for amorphous materials, introducing AMDEN (Amorphous Material DEnoising Network), a diffusion model-based framework that generates structures of amorphous materials. First, we demonstrate the inherent challenges for diffusion models to generate relaxed structures. These low-energy configurations are typically obtained through a thermal motion-driven random search-like process that cannot be replicated by standard denoising procedures. We therefore introduce an energy-based AMDEN variant that implements Hamiltonian Monte Carlo refinement for generating these relaxed structures. We further introduce several amorphous material datasets with diverse properties and compositions to evaluate our framework and support future development.
SN - 0935-9648
SN - 1521-4095
ER -