An official website of the United States government
Abstract Metal–organic frameworks (MOFs) are highly porous and versatile materials studied extensively for applications such as carbon capture and water harvesting. However, computing phonon-mediated properties in MOFs, like thermal expansion and mechanical stability, remains challenging due to the large number of atoms per unit cell, making traditional Density Functional Theory (DFT) methods impractical for high-throughput screening. Recent advances in machine learning potentials have led to foundation atomistic models, such as MACE-MP-0, that accurately predict equilibrium structures but struggle with phonon properties of MOFs. In this work, we developed a workflow for computing phonons in MOFs within the quasi-harmonic approximation with a fine-tuned MACE model, MACE-MP-MOF0. The model was trained on a curated dataset of 127 representative and diverse MOFs. The fine-tuned MACE-MP-MOF0 improves the accuracy of phonon density of states and corrects the imaginary phonon modes of MACE-MP-0, enabling high-throughput phonon calculations with state-of-the-art precision. The model successfully predicts thermal expansion and bulk moduli in agreement with DFT and experimental data for several well-known MOFs. These results highlight the potential of MACE-MP-MOF0 in guiding MOF design for applications in energy storage and thermoelectrics.
more »
« less
This content will become publicly available on October 15, 2026
A Comprehensive Assessment and Benchmark Study of Large Atomistic Foundation Models for Phonons
The rapid development of universal machine learning potentials (uMLPs) has enabled efficient, accurate predictions of diverse material properties across broad chemical spaces. While their capability for modeling phonon properties is emerging, systematic benchmarking across chemically diverse systems remains limited. We evaluate six recent uMLPs—EquiformerV2, MatterSim, MACE, and CHGNet—on 2429 crystalline materials from the Open Quantum Materials Database. Models were used to compute atomic forces in displaced supercells, derive interatomic force constants (IFCs), and predict phonon properties including lattice thermal conductivity (LTC), compared with density functional theory and experimental data. The EquiformerV2 pretrained model trained on the OMat24 dataset exhibits strong performance in predicting atomic forces and third‐order IFCs, while its fine‐tuned counterpart consistently outperforms other models in predicting second‐order IFCs, LTC, and other phonon properties. Although MACE and CHGNet demonstrated comparable force prediction accuracy to EquiformerV2, notable discrepancies in IFC fitting led to poor LTC predictions. Conversely, MatterSim, despite lower force accuracy, achieved intermediate IFC predictions, suggesting error cancellation and complex relationships between force accuracy and phonon predictions. This benchmark guides the evaluation and selection of uMLPs for high‐throughput screening of materials with targeted thermal transport properties.
more »
« less
- PAR ID:
- 10655943
- Publisher / Repository:
- Wiley
- Date Published:
- Journal Name:
- Advanced Intelligent Discovery
- ISSN:
- 2943-9981
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Lattice thermal conductivity (κL) is a crucial characteristic of crystalline solids with significant implications for thermal management, energy conversion, and thermal barrier coating. The advancement of computational tools based on density functional theory (DFT) has enabled the effective utilization of phonon quasi-particle-based approaches to unravel the underlying physics of various crystalline systems. While the higher order of anharmonicity is commonly used for explaining extraordinary heat transfer behaviors in crystals, the impact of exchange-correlation (XC) functionals in DFT on describing anharmonicity has been largely overlooked. The XC functional is essential for determining the accuracy of DFT in describing interactions among electrons/ions in solids and molecules. However, most XC functionals in solid-state physics are primarily focused on computing the properties that only require small atomic displacements from the equilibrium (within the harmonic approximation), such as harmonic phonons and elastic constants, while anharmonicity involves larger atomic displacements. Therefore, it is more challenging for XC functionals to accurately describe atomic interactions at the anharmonicity level. In this study, we systematically investigate the room-temperature κL of 16 binary compounds with rocksalt and zincblende structures using var- ious XC functionals such as local density approximation (LDA), Perdew-Burke-Ernzerhof (PBE), revised PBE for solid and surface (PBEsol), optimized B86b functional (optB86b), revised Tao-Perdew-Staroverov-Scuseria (revTPSS), strongly constrained and appropriately normed functional (SCAN), regularized SCAN (rSCAN) and regularized-restored SCAN (r2SCAN) in combination with different perturbation orders, including phonon within harmonic approximation (HA) plus three- phonon scattering (HA+3ph), phonon calculated using self-consistent phonon theory (SCPH) plus three-phonon scattering (SCPH+3ph), and SCPH phonon plus three- and four-phonon scattering (SCPH+3,4ph). Our results show that the XC functional exhibits strong entanglement with perturbation order and the mean relative absolute error (MRAE) of the computed κL is strongly influenced by both the XC functional and perturbation order, leading to error cancellation or amplification. The minimal (maximal) MRAE is achieved with revTPSS (rSCAN) at the HA+3ph level, SCAN (r2SCAN) at the SCPH+3ph level, and PBEsol (rSCAN) at the SCPH+3,4ph level. Among these functionals, PBEsol exhibits the highest accuracy at the highest perturbation order. The SCAN- related functionals demonstrate moderate accuracy but are suffer from numerical instability and high computational costs. Furthermore, the different impacts of quartic anharmonicity on κL in rocksalt and zincblende structures are identified by all XC functionals, attributed to the distinct lattice anharmonicity in these two structures. These findings serve as a valuable reference for selecting appropriate functionals for describing anharmonic phonons and offer insights into high-order force constant calculations that could facilitate the development of more accurate XC functionals for solid materials.more » « less
-
The discovery of advanced thermal materials with exceptional phonon properties drives technological advancements, impacting innovations from electronics to superconductors. Understanding the intricate relationship between composition, structure, and phonon thermal transport properties is crucial for speeding up such discovery. Exploring innovative materials involves navigating vast design spaces and considering chemical and structural factors on multiple scales and modalities. Artificial intelligence (AI) is transforming science and engineering and poised to transform discovery and innovation. This era offers a unique opportunity to establish a new paradigm for the discovery of advanced materials by leveraging databases, simulations, and accumulated knowledge, venturing into experimental frontiers, and incorporating cutting-edge AI technologies. In this perspective, first, the general approach of density functional theory (DFT) coupled with phonon Boltzmann transport equation (BTE) for predicting comprehensive phonon properties will be reviewed. Then, to circumvent the extremely computationally demanding DFT + BTE approach, some early studies and progress of deploying AI/machine learning (ML) models to phonon thermal transport in the context of structure–phonon property relationship prediction will be presented, and their limitations will also be discussed. Finally, a summary of current challenges and an outlook of future trends will be given. Further development of incorporating AI/ML algorithms for phonon thermal transport could range from phonon database construction to universal machine learning potential training, to inverse design of materials with target phonon properties and to extend ML models beyond traditional phonons.more » « less
-
Abstract Although first principles based anharmonic lattice dynamics is one of the most common methods to obtain phonon properties, such method is impractical for high-throughput search of target thermal materials. We develop an elemental spatial density neural network force field as a bottom-up approach to accurately predict atomic forces of ~80,000 cubic crystals spanning 63 elements. The primary advantage of our indirect machine learning model is the accessibility of phonon transport physics at the same level as first principles, allowing simultaneous prediction of comprehensive phonon properties from a single model. Training on 3182 first principles data and screening 77,091 unexplored structures, we identify 13,461 dynamically stable cubic structures with ultralow lattice thermal conductivity below 1 Wm −1 K −1 , among which 36 structures are validated by first principles calculations. We propose mean square displacement and bonding-antibonding as two low-cost descriptors to ease the demand of expensive first principles calculations for fast screening ultralow thermal conductivity. Our model also quantitatively reveals the correlation between off-diagonal coherence and diagonal populations and identifies the distinct crossover from particle-like to wave-like heat conduction. Our algorithm is promising for accelerating discovery of novel phononic crystals for emerging applications, such as thermoelectrics, superconductivity, and topological phonons for quantum information technology.more » « less
-
Abstract Existing machine learning potentials for predicting phonon properties of crystals are typically limited on a material-to-material basis, primarily due to the exponential scaling of model complexity with the number of atomic species. We address this bottleneck with the developed Elemental Spatial Density Neural Network Force Field, namely Elemental-SDNNFF. The effectiveness and precision of our Elemental-SDNNFF approach are demonstrated on 11,866 full, half, and quaternary Heusler structures spanning 55 elements in the periodic table by prediction of complete phonon properties. Self-improvement schemes including active learning and data augmentation techniques provide an abundant 9.4 million atomic data for training. Deep insight into predicted ultralow lattice thermal conductivity (<1 Wm −1 K −1 ) of 774 Heusler structures is gained by p–d orbital hybridization analysis. Additionally, a class of two-band charge-2 Weyl points, referred to as “double Weyl points”, are found in 68% and 87% of 1662 half and 1550 quaternary Heuslers, respectively.more » « less
