Engineering Papers⌕ Search

DOE OSTI · 2999427

When more data hurts: Optimizing data coverage while mitigating diversity-induced underfitting in an ultrafast machine-learned potential

Abstract

Machine-learned interatomic potentials (MLIPs) are becoming an essential tool in materials modeling. However, optimizing the generation of training data used to parametrize the MLIPs remains a significant challenge. This is because MLIPs can fail when encountering local environments too different from those present in the training data. The difficulty of determining a priori the environments that will be encountered during molecular dynamics simulation necessitates diverse, high-quality training data. Here, this study investigates how training data diversity affects the performance of MLIPs using the Ultra-Fast force field (UF 3 ) to model amorphous silicon nitride. We employ expert and autonomously generated data to create the training data and fit four force field variants to subsets of the data. Our findings reveal a critical balance in training data diversity: insufficient diversity hinders generalization, while excessive diversity can exceed the MLIP's learning capacity, reducing simulation accuracy. Specifically, we found that the UF 3 variant trained on a subset of the training data, in which nitrogen-rich structures were removed, offered vastly better prediction and simulation accuracy than any other variant. By comparing these UF 3 variants, we highlight the nuanced requirements for creating accurate MLIPs, emphasizing the importance of application-specific training data to achieve optimal performance in modeling complex material behaviors.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Gibson, Jason B. [Univ. of Florida, Gainesville, FL (United States)] (ORCID:0000000179745264), Janicki, Tesia Danielle [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000160086414), Hire, Ajinkya C. [Univ. of Florida, Gainesville, FL (United States)] (ORCID:0000000331472521), Bishop, Chris [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)], Lane, J. Matthew Doyle [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)] (ORCID:0000000278789158), Hennig, Richard G. [Univ. of Florida, Gainesville, FL (United States)] (ORCID:0000000349337686). 2025-04-22. When more data hurts: Optimizing data coverage while mitigating diversity-induced underfitting in an ultrafast machine-learned potential. https://doi.org/10.1103/physrevmaterials.9.043802. https://engineeringpapers.com/record/osti%3A2999427/when-more-data-hurts-optimizing-data-coverage-while-mitigating-diversity-induced-underfitting-in-an

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Engineering Papers by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related reports

Cation Effects on CO 2 Delivery to Cu Electrode in Reactive Capture of CO 2

The direct electrochemical conversion of captured CO 2 , known as reactive capture of CO 2 (RCC), remains a formidable challenge in heterogeneous catalysis. Given that amines are one of the most widely used capture agents for CO 2 , it would be desirable to electrochemically reduce the resultant adducts, such as carbamate, directly in RCC. However, current understanding suggests that the primary species undergoing reduction in RCC with amines is the CO 2 dissociated from the sorbent. Herein, we employ ab initio molecular dynamics (AIMD) with DFT to analyze how the nature of alkali metal cations in the electrolyte affects carbamate at the Cu surface, thereby assessing the possibility of promoting RCC by cation effects. The simulations show that the carbamate’s orientation with respect to the electrode is governed by the optimal distance between the carbamate and the cation, specifically how this distance aligns with the cation’s hydration spheres. Moreover, the slow-growth AIMD results indicate that the CO 2 dissociation barrier correlates with the orientation of carbamate at the interface. When the carbamate resides beyond the cation’s first hydration sphere, it adopts a flat orientation with respect to the surface that promotes the release of CO 2 from the capture agent. In contrast, when the carbamate disrupts the first hydration sphere and exhibits a strong cation−π interaction, it adopts an upright orientation that is less conducive to CO 2 release. These findings reveal a nontrivial cation effect in RCC, suggesting that it should be possible to optimize RCC via the choice of the electrolyte.

ab initio molecular dynamics↗

Trace Uranium Partitioning in a Multiphase Nano-FeOOH System

The characterization of trace elements in nanomaterials using extended X-ray absorption fine structure (EXAFS) spectroscopy constitutes a first step toward understanding how impurities or dopants affect the properties of the host phase. However, limitations to EXAFS interpretation complicate the analysis of trace concentrations of impurities that are distributed across multiple phases in a heterogeneous system. Ab initio molecular dynamics (AIMD)-informed EXAFS analysis was employed to investigate the immobilization of trace uranium associated with nanophase iron (oxyhydr)oxides, a model system for the geochemical sequestration of radiotoxic contaminants. The reductive transformation of ferrihydrite (Fe(OH)3) to nano-particulate iron oxyhydroxide minerals in the presence of uranyl (UO2)2+(aq) resulted in the preferential incorporation of U into goethite (a-FeOOH) over lepidocrocite (g-FeOOH), even though reaction conditions favored the formation of excess lepidocrocite. This unexpected result is supported by atomically resolved transmission electron microscopy. Using this model system, we demonstrate how AIMD-informed EXAFS analysis lifts the strict statistical limitations of traditional shell-by-shell EXAFS modeling, enabling the detailed analysis of the local bonding environment, charge compensation mechanisms, and oxidation states of polyvalent impurities in complex multi-phase nano-systems.

ab initio molecular dynamics↗

Facet-Dependent Thermal Instability in LiCoO2

Thermal runaways triggered by the oxygen release from oxide cathode materials pose a major safety concern for widespread application of lithium ion batteries. Utilizing in situ aberration-corrected scanning transmission electron microscopy (STEM) and electron energy loss spectroscopy (EELS) at high temperatures, we show that oxygen release from LixCoO2 cathode crystals is occurring at the surface of particles. We correlated this local oxygen evolution from the LixCoO2 structure with local phase transitions spanning from layered to spinel and then to rock salt structure upon exposure to elevated temperatures. Ab initio molecular dynamics simulations (AIMD) results show that oxygen release is highly dependent on LixCoO2 facet orientation. While the [001] facets are stable at 300 degrees C, oxygen release is observed from the [012] and [104] facets, where under-coordinated oxygen atoms from the delithiated structures can combine and eventually evolve as O-2. The novel understanding that emerges from the present study piovides in-depth insights into the thermal runaway mechanism of Li-ion batteries and can assist the design and fabrication of cathode crystals with the most thermally stable facets.

ab initio molecular dynamics↗