Skip to content
Log in

Computational Approaches for the Discovery of New Phase-Change Materials Using Two Method Machine Learning and First-Principles Density Functional Theory

Mohamed Katish V. Ferrandiz-Mas
2026 · Eurotherm seminar #119: Contribution of thermal energy storage towards decarbonization · 0 citations

TL;DR

This work evaluates two approaches for solid-solid PCM discovery: data-driven machine-learning screening and first-principles density functional theory (DFT) modelling, highlighting the complementary roles of ML for rapid candidate identification via screening of known PCMs and DFT for mechanistic characterisation.

Abstract

Solid-solid phase-change materials (PCMs) are attractive for thermal energy storage due to the absence of leakage and their suitability for compact and safe storage systems. However, the discovery of new solid-solid PCMs with targeted transition temperatures and high latent heat remains challenging. This work evaluates two approaches for solid-solid PCM discovery: data-driven machine-learning (ML) screening and first-principles density functional theory (DFT) modelling. ML screening identified PEG-1000-glycerol mixtures as promising candidates near room temperature, with experimental validation confirming composition-dependent solid-solid transitions (between 14.10 to 31.40 °C) absent in the pure components. Furthermore, first-principles DFT calculations, implemented using Quantum ESPRESSO, reveal low-frequency phonon instabilities in a candidate PCM (2,2-dimethylpropane-1,3-diol (DMPD)) molecular crystal, providing atomistic insight into lattice-driven phase-transition mechanisms. Together, the results highlight the complementary roles of ML for rapid candidate identification via screening of known PCMs and DFT for mechanistic characterisation, supporting a more efficient pipeline for developing solid-solid PCMs for low-temperature thermal energy storage in decarbonised energy systems.

DOI Semantic Scholar
View source

Similar papers

Review Jul 2026

Thermodynamics-Informed Machine Learning for Energy Materials Discovery

It is argued that developing thermodynamics-informed ML constitutes one of the most important and least explored frontiers in materials discovery and that the next generation of ML models must move beyond static energy predictions towards a thermodynamic description of materials behaviour under realistic operating conditions.

Pol Benítez, Cibr'an L'opez, Claudio Cazorla · 0 citations
Jul 2026

A Machine-Learning-Accelerated Approach for Room-Temperature Phase Diagram Predictions.

A machine-learning workflow that couples the crystal generator MatterGen with a fine-tuned MatterSim interatomic potential to expand the candidate phase space and compute temperature-dependent phase stability with accuracy approaching density functional theory is reported.

Chen Su, Jie Lu, Yuchen Fu et al. · 0 citations
Review Jul 2026

Machine learning force fields for inorganic crystalline materials: principles, advances, and emerging applications.

Machine learning force fields (MLFFs) combine the high accuracy of first-principles methods with the high efficiency of classical force fields, offering new opportunities for atomic-level studies of inorganic crystalline materials. We systematically summarize the research progress on MLFFs, elucidate their fundamental principles and developmental history, and categorically introduce the technical characteristics of representative models and relevant benchmarking platforms. We aim to review the advantages of MLFFs in overcoming traditional computational limitations across four domains: structural prediction and optimization, physical properties, defect and interface properties, and phase transitions and kinetic processes. The challenges of MLFFs are also examined in computational efficiency and simulation scale, accuracy and generalization ability, data requirements and training samples, model interpretability, and physical constraints, which offer a reference for the research and application of MLFFs in the field of inorganic crystalline materials.

Jing Yi, Yuxin Zhan, Yuanmao Hu et al. · 0 citations
Preprint Jul 2026

Learning to Converge: Warm-Starting DFTB Self-Consistent Charges with Machine Learning

A machine learning approach is presented that accelerates DFTB simulations by predicting optimal initial atomic charges and demonstrates that ML-predicted initial charges consistently and significantly improve SCC convergence across diverse chemical systems including organic molecules, biomolecules, water clusters, transition metal oxides and solid electrolytes.

Maximilian L. Ach, Karsten Reuter, C. Panosetti · 0 citations