ML Workflows for Screening Degradation‐Relevant Properties of Forever Chemicals
Advanced Science · 31.01.2026
DOI: 10.1002/advs.202523817 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, online erschienen am 31.01.2026. Verfasst von Pranoy Ray und 3 weiteren Autor:innen. Beteiligte Einrichtung: George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, USA. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSF DMREF, OUSD.
Abstract (Originalsprache)
The environmental persistence of per‐ and polyfluoroalkyl substances (PFAS) necessitates new remediation technologies, yet the vast chemical space makes traditional exploration methods for understanding degradation‐relevant properties intractable. Rational design of PFAS degradation strategies requires accurate prediction of three critical molecular properties: bond dissociation energies (BDEs) to govern kinetics, polarizability to control catalytic interactions, and thermodynamic stability to govern reaction feasibility. Guided by theoretically‐rooted principles, we identify that global properties (polarizability, stability) require spatially‐informed features (3D electron density patterns), while bond‐specific properties are governed by topological features (atomic connectivity). We developed two distinct physics‐informed ML workflows implementing this principle: For global properties, two‐point spatial correlations were compressed via Principal Component Analysis (PCA) and input to a Gaussian Process Regression (GPR) model. For local properties, a graph‐based feature scheme was coupled with a Random Forest (RF) algorithm. Both workflows demonstrated strong predictive performance (GPR R 2 ≈ 0.92 for polarizability; R 2 ≈ 0.97 for enthalpy; RF R 2 ≈ 0.87 for BDE) across multiple datasets, establishing robust Structure‐Property linkages for PFAS. These physics‐informed models provide a foundational capability for rapid, high‐throughput screening of the vast PFAS library, enabling prioritization of candidate molecules and bonding motifs for subsequent experimental and process‐level remediation studies, rather than constituting complete remediation workflows by themselves.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, USA.
- School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, USA.
- Multiscale Technologies Inc., Seattle, USA.
- United States Naval Research Laboratory, Washington, DC, USA.
ORCID-Profile: Pranoy Ray, Surya R Kalidindi
Förderung
- NSF DMREF
- OUSD
Zitieren
APA
Ray, P., Castillo, A. R., Kolel-Veetil, M., & Kalidindi, S. R. (2026). ML Workflows for Screening Degradation‐Relevant Properties of Forever Chemicals. Advanced Science. https://doi.org/10.1002/advs.202523817
Vancouver
Ray P, Castillo AR, Kolel-Veetil M, Kalidindi SR. ML Workflows for Screening Degradation‐Relevant Properties of Forever Chemicals. Advanced Science. 2026. doi:10.1002/advs.202523817
BibTeX
@article{Ray2026,
author = {Ray, Pranoy and Castillo, Andrew R and Kolel-Veetil, Manoj and Kalidindi, Surya R},
title = {ML Workflows for Screening Degradation‐Relevant Properties of Forever Chemicals},
journal = {Advanced Science},
year = {2026},
doi = {10.1002/advs.202523817}
}
EUVIMED