Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Modeling workflow”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 775 records · Page 43
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

32 examples of LLM applications in materials science and chemistry: towards automation, assistants, agents, and accelerated scientific discovery

Abstract Large language models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications of LLMs through 32 total projects developed during the second annual LLM hackathon for applications in materials science and chemistry, a global hybrid event. These projects spanned seven key research areas: (1) molecular and material property prediction, (2) molecular and material design, (3) automation and novel interfaces, (4) scientific communication and education, (5) research data management and automation, (6) hypothesis generation and evaluation, and (7) knowledge extraction and reasoning from the scientific literature. Collectively, these applications illustrate how LLMs serve as versatile predictive models, platforms for rapid prototyping of domain-specific tools, and much more. In particular, improvements in both open source and proprietary LLM performance through the addition of reasoning, additional training data, and new techniques have expanded effectiveness, particularly in low-data environments and interdisciplinary research. As LLMs continue to improve, their integration into scientific workflows presents both new opportunities and new challenges, requiring ongoing exploration, continued refinement, and further research to address reliability, interpretability, and reproducibility.

Computer Science↗
DOE OSTI2025

Autonomous phase mapping of gold nanoparticles synthesis with differentiable models of spectral shape

Autonomous experimentation–or self-driving labs–offers a systematic approach to accelerate materials discovery by integrating automated synthesis, characterization, and data-driven decision-making. We present a closed-loop workflow for the on-demand synthesis and structural characterization of colloidal gold nanoparticles, enabling direct mapping from composition to nanoscale structure. Our framework leverages differentiable models of spectral shape to address two central tasks in self-driving labs: (a) phase mapping, or identifying compositional regions with distinct structural behavior; and (b) material retrosynthesis, or optimizing compositions for target structure. Using functional data analysis, we develop a data-driven model with generative pre-training, active learning, and high-throughput experiments to predict spectral responses across composition space. We demonstrate the approach on seed-mediated growth of gold nanoparticles, showcasing its ability to extract design rules, reveal secondary interactions, and efficiently navigate morphology space. Gradient-based optimization of the models enables inverse design, making this a unified platform.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Upper critical solution temperature polymer assemblies via variable temperature liquid phase transmission electron microscopy and liquid resonant soft X-ray scattering

Abstract Here, we study the upper critical solution temperature triggered phase transition of thermally responsive poly(ethylene glycol)- block -poly(ethylene glycol) methyl ether acrylate- co -poly(ethylene glycol) phenyl ether acrylate- block -polystyrene nanoassemblies in isopropanol. To gain mechanistic insight into the organic solution-phase dynamics of the upper critical solution temperature polymer, we leverage variable temperature liquid-cell transmission electron microscopy correlated with variable temperature liquid resonant soft X-ray scattering. Heating above the upper critical solution temperature triggers a reduction in particle size and a morphological transition from a spherical core shell particle with a complex, multiphase core to a micelle with a uniform core and Gaussian polymer chains attached to the surface. These correlated solution phase methods, coupled with mass spectral validation and modeling, provide unique insight into these thermoresponsive materials. Moreover, we detail a generalizable workflow for studying complex, solution-phase nanomaterials via correlative methods.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Excess free volume and structural properties of inert gas condensation synthesized nanoparticles based CuZr nanoglasses

Abstract Nanoglass (NG) as a new structure-tunable material has been investigated using both experiments and computational modeling. Experimentally, inert gas condensation (IGC) is commonly employed to prepare metallic glass (MG) nanoparticles that are consolidated using cold compression to generate an NG. In computational modeling, various methods have been used to generate NGs. However, due to the high computational cost involved, heretofore modeling investigations have not followed the experimental synthesis route. In this work, we use molecular dynamics simulations to generate an NG model by consolidating IGC-prepared Cu 64 Zr 36 nanoparticles following a workflow similar to that of experiments. The resulting structure is compared with those of NGs produced following two alternative procedures previously used: direct generation employing Voronoi tessellation and consolidation of spherical nanoparticles carved from an MG sample. We focus on the characterization of the excess free volume and the Voronoi polyhedral statistics in order to identify and quantify contrasting features of the glass-glass interfaces in the three NG samples prepared using distinct methods. Results indicate that glass-glass interfaces in IGC-based NGs are thicker and display higher structural contrast with their parent MG structure. Nanoparticle-based methods display excess free volume exceeding 4%, in agreement with experiments. IGC-prepared nanoparticles, which display Cu segregation to their surfaces, generate the highest glass-glass interface excess free volume levels and the largest relative interface volume with excess free volume higher than 3%. Voronoi polyhedral analysis indicates a sharp drop in the full icosahedral motif fraction in the glass-glass interfaces in nanoparticle-based NG as compared to their parent MG.

36 MATERIALS SCIENCE↗
DOE OSTI2025

ABLE Workflow Copier

A copier template for generating a snakemake workflow with an associated python package for implementing dataset transformation, feature extraction, and modeling.

Pathak, Maharshi [Northeastern Univ., Boston, MA (↗
DOE OSTI2022

Towards a Stronger Foundation: Digitizing Commercial Buildings with Brick to Enable Portable Advanced Applications

Most large commercial buildings have digital controls for their heating, ventilation, and air-conditioning (HVAC) and lighting systems with the potential to implement advanced control strategies and data analytics. However, advanced control strategies and data analytics are rarely deployed at scale due to non-standard naming conventions and heterogenous building configurations. Semantic metadata standards, like Brick, show promise to proliferate these applications across many buildings, but they have not been widely adopted by industry due to barriers such as perceived risk and unfamiliarity with the technology. This paper describes the workflow we established and evaluated while using it to develop over ten Brick models of existing buildings. Through this process, we observed that digitizing existing commercial buildings is a cost and labor-intensive effort in which understanding the buildings’ data streams is the major bottleneck. Yet, we conclude this investment is worthwhile since various use case applications such as fault detection and diagnostics, thermal comfort analysis, and HVAC control optimization can utilize the same Brick model. The paper also explores the challenges and lessons learned we encountered while creating these data models, such as: 1) difficulties in finding metadata descriptions and relationships for existing buildings; 2) handling missing concepts in the schema needed to model a building; 3) lack of guidance on how to structure the data model or how much detail to include; 4) unfamiliarity with technologies, which makes the learning curve steep for applications developers. Finally, we also describe future directions for semantic metadata research and development to make such transformative technologies more accessible to practitioners.

Roa, Carlos Duarte↗
DOE OSTI2022

Validation of energetic particle transport models for time-dependent integrated simulations of burning plasmas (Final ST Report)

The major goal of this project is to deliver a suite of validated energetic particle (EP) modeling tools for time-dependent integrated tokamak simulations (with the code TRANSP) that can be used for modeling plasma discharges featuring a substantial EP content, such as burning plasmas. During FY20, issues were resolved with an energetic particle transport model called TGLF-EP, with improvements made to the TGLF-EP workflow, generation of input files, and interpretation of runs on the NERSC supercomputing cluster. The recipient also gave input on simulations with the code TRANSP to reproduce the reference JET discharge, and assessed the accuracy and uncertainties of the simulated B field, current evolution, thermal plasma profiles, stored energy, etc. Input was also given on interpretation of fast-ion instability calculations and recommendations for modifications to JET afterglow discharge for the upcoming DT campaign.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRSDate not supplied

Clinical Decision Support - Concepts of Operation

We are entering a new era in space exploration to return to the moon and explore Mars. Crew members operating independently during long duration space exploration missions will require a clinical decision support system (CDSS) to increase autonomy by augmenting their knowledge, skills and abilities in different scenarios. Significant changes to in-flight and habitat medical care due to constraints on mass, volume, power, crew time and medical evacuation capabilities are needed to increase crew autonomy and self-reliance in decision making and task performance. The Exploration Medical Capability (ExMC) Element of the Human Research Program (HRP) pushes the boundary of space medical systems to advance the care of astronauts on future exploration missions beyond low Earth orbit by identifying and testing next-generation medical care and crew health maintenance technologies. Clinical decision support (CDS) presents knowledge and data in a context aware manner to augment a crew members’ knowledge, skills and abilities during the process of observation, orientation, decisions and action. A comprehensive crew health and performance CDSS is required to augment crew capability and will be used in different scenarios for several reasons. In general, the CDSS’s role is to assist the crew in prevention, detection, diagnosis and treatment of crew health and performance related conditions that may arise in exploration spaceflight. For example, CDSS would assist a high acuity scenario such as a heart attack by supplying clear instructions, vital signs and treatment reminders. A lower severity scenario such as kidney stone risk could interface to vehicle systems and display more complex predictive data during a diagnosis. A CDSS needs to contribute to successful missions by maintaining a high performing crew who can potentially exhibit countless medical conditions related to derangements from the space environment (sleep, cognition, nutrition and exercise) as well as conditions intrinsic to humans anywhere. While supporting the crew’s ability to make sound clinical decisions is desirable in any mission, it is essential for exploration missions with significant communication delays, no evacuation capability, and extended exposure to the flight environment. Such missions correspond with medical Level of Care V (LOC V), the highest level specified in NASA-STD-3001. The project focuses on CDS implementation research to derive requirements for LOC V, where the need for increased autonomy results in new practices and the inclusion of non-clinical data, such as vehicle environmental measures and physical exercise results, from other human and vehicle domains and advanced analytics. The CDS project describes how the CDSS is intended to be used by defining concepts of operations (ConOps). The process to derive ConOps focuses on increased autonomy that reduces the likelihood and consequences of accepted medical conditions. These crew health and performance inputs are grouped by common datasets and analysis models. Use cases are derived to research new clinical scenarios, architectural development and workflows. Implementation research is conducted with protypes to inform assumptions and derive requirements. The project also establishes how externally developed analysis and approaches can be added to expand a clinical decision support system and thus highlight how a comprehensive system can be globally developed with collaborators. This presentation will cover example scenarios from the CDS ConOps and the method to derive them. One example scenario will be CDSS alerting an increased kidney stone risk during a mission, with diagnosis and treatment options provided during the intervention.

clinical decision support↗
NASA NTRSDate not supplied

Clinical Decision Support - Concepts of Operation

We are entering a new era in space exploration to return to the moon and explore Mars. Crew members operating independently during long duration space exploration missions will require a clinical decision support system (CDSS) to increase autonomy by augmenting their knowledge, skills and abilities in different scenarios. Significant changes to in-flight and habitat medical care due to constraints on mass, volume, power, crew time and medical evacuation capabilities are needed to increase crew autonomy and self-reliance in decision making and task performance. The Exploration Medical Capability (ExMC) Element of the Human Research Program (HRP) pushes the boundary of space medical systems to advance the care of astronauts on future exploration missions beyond low Earth orbit by identifying and testing next-generation medical care and crew health maintenance technologies. Clinical decision support (CDS) presents knowledge and data in a context aware manner to augment a crew members’ knowledge, skills and abilities during the process of observation, orientation, decisions and action. A comprehensive crew health and performance CDSS is required to augment crew capability and will be used in different scenarios for several reasons. In general, the CDSS’s role is to assist the crew in prevention, detection, diagnosis and treatment of crew health and performance related conditions that may arise in exploration spaceflight. For example, CDSS would assist a high acuity scenario such as a heart attack by supplying clear instructions, vital signs and treatment reminders. A lower severity scenario such as kidney stone risk could interface to vehicle systems and display more complex predictive data during a diagnosis. A CDSS needs to contribute to successful missions by maintaining a high performing crew who can potentially exhibit countless medical conditions related to derangements from the space environment (sleep, cognition, nutrition and exercise) as well as conditions intrinsic to humans anywhere. While supporting the crew’s ability to make sound clinical decisions is desirable in any mission, it is essential for exploration missions with significant communication delays, no evacuation capability, and extended exposure to the flight environment. Such missions correspond with medical Level of Care V (LOC V), the highest level specified in NASA-STD-3001. The project focuses on CDS implementation research to derive requirements for LOC V, where the need for increased autonomy results in new practices and the inclusion of non-clinical data, such as vehicle environmental measures and physical exercise results, from other human and vehicle domains and advanced analytics. The CDS project describes how the CDSS is intended to be used by defining concepts of operations (ConOps). The process to derive ConOps focuses on increased autonomy that reduces the likelihood and consequences of accepted medical conditions. These crew health and performance inputs are grouped by common datasets and analysis models. Use cases are derived to research new clinical scenarios, architectural development and workflows. Implementation research is conducted with protypes to inform assumptions and derive requirements. The project also establishes how externally developed analysis and approaches can be added to expand a clinical decision support system and thus highlight how a comprehensive system can be globally developed with collaborators. This presentation will cover example scenarios from the CDS ConOps and the method to derive them. One example scenario will be CDSS alerting an increased kidney stone risk during a mission, with diagnosis and treatment options provided during the intervention.

clinical decision support↗
NASA NTRS2024

EdgeCortix SAKURA-I Machine-Learning, PCIe Accelerator SEE Heavy Ion Test Report

To enable autonomy in space, machine-learning and computer vision applications become invaluable for sensor processing. However, these algorithms are computationally complex and unfeasible for many embedded central processing units (CPUs) and usually require external coprocessors, such as graphics processing units (GPUs) or accelerators specific to the application, including application specific integrated circuits (ASICs). In power-constrained systems, GPUs tend to consume more power than is acceptable (>40W), so lower-power accelerators have shown promise to provide the performance needed under spacecraft constraints. For radiation engineers, developing methodologies that can properly test CPUs, GPUs, and accelerators, and enable comparisons between them remains a necessary complication to solve as the devices become more complex. The methodology in this test aims to be a start in developing a baseline single-event effect (SEE) test for client-device machine learning accelerators. This category of devices do not host their own operating system. This testing campaign is a continuation of a previous 200 MeV proton test performed in January 2024. This report covers two heavy ion tests of the SAKURA-I card: one in April 2024, and one in June 2024. Additional data was needed after the April test due to ion-range issues experienced at higher linear-energy transfers (LETs). These range issues are described in more detail in Section 8. This experiment characterizes SEEs and data error susceptibility of the EdgeCortix SAKURA-I machine-learning accelerator under heavy ions. The device was monitored for single event upsets (SEUs) and single event functional interrupts (SEFIs) at the Lawrence Berkeley National Laboratory’s 88-inch cyclotron. The SAKURA-I board accelerates machine-learning inference applications on a host computer through a PCIex16 connection. For the purposes of devising an end to end automated analysis workflow for this experiment, the YOLO-V5 and SSD300 objection-detection models, and the ResNet-50, EfficientNet, and MobileNetV2 image classification models were used as a representative suite of analytical machine-learning models.

Seth S Roffe↗
DOE OSTI2022

Real-Time Optimization Workflow Status Update

Economically optimal and safe operation of integrated energy systems (IES) requires optimization at many different time scales. A real-time optimization (RTO) workflow will attempt to maximize revenue and minimize operational costs on a time scale of minutes to hours. Such a workflow requires the use of a digital twin (DT), which is a virtual representation of a physical system. The DT is updated using real-time data from the physical system, and serves as a model in an optimization framework. The optimization results are then sent back to the physical system to complete the loop. This report details the progress made in developing building blocks for a DT/RTO framework. The Risk Analysis Virtual Environment (RAVEN) platform within the Framework for Optimization of Resources and Economics (FORCE) tool suite can perform many of the tasks required for building a DT and performing RTO. The first item of this report details RAVEN enhancements that enable RAVEN workflows to be run in various environments. Data communication between the physical system and its DT is essential for successful RTO. This includes preprocessing real-time data, loading data into a data warehouse, and querying the stored data. The second section of this report describes the progress made in implementing an adapter in Python in order for Deep Lynx to handle the data communication. Typical dispatch optimization frameworks are built on linear programming (LP). The prototype RTO workflow developed in this report uses an LP problem as a part of a receding-horizon- or economic model predictive control (EMPC) based optimization. The third section of this report details the framework of an RTO workflow in which the system consists of a simple electrical storage device. A DT can be built from a reduced-order model (ROM). Integrating a ROM into a typical LP optimization framework has been challenging because most optimization packages require the user to write algebraic expressions for the system model. The final section of this report shows how an externally built RAVEN ROM can be integrated in an RTO framework by using the Python package Pyomo. This demonstrates the RTO workflow capability from a software-only perspective and is an important step in demonstrating the capability to implement an RTO workflow for a physical system.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Multipoint Aerostructural Optimization of Wind Turbine Rotors Using a Coupled Blade‐Resolved Aerostructural Solver

Physics‐based design optimization workflows thread the needle between computational cost limitations and simulation complexity, often compromising between modeling detail and the range of operating design conditions. Multipoint aerostructural optimization of wind turbine rotors has so far been confined to low‐fidelity analyses or to high‐fidelity studies with simplified structural models, leaving the most complex design trade‐offs unexplored. We close this gap by performing the first tightly coupled gradient‐based multipoint aerostructural rotor optimization using 3D aerodynamic and structural solvers with discrete coupled adjoints. The optimizer simultaneously varies blade planform, airfoil shapes, and structural thickness through more than 270 design variables, minimizing a weighted combination of rotor mass and power across multiple wind speeds. Applied to a modified DTU 10‐MW benchmark under conservative structural and aerodynamic constraints, our multipoint optimization reduces rotor mass by up to 36% and increases power by 12%–15% across the main operating conditions; biasing the objective toward power yields power gains up to 18% and a 17% mass reduction. For a nominal wind distribution, 3‐point rotor designs accounting for low RPM and high thrust conditions capture dominant trade‐offs and outperform single‐point designs. Adding two off‐design points changes individual‐condition power by less than 3% but leaves the weighted average within 0.5%, and the mass‐power bias has a stronger effect on the final design than the operating‐point weighting itself. Our framework extends naturally to richer load cases and site‐specific wind distributions, providing a basis for high‐fidelity multipoint design earlier in industrial workflows.

17 WIND ENERGY↗
DOE OSTI2020

Southeast Regional CO 2 Utilization and Storage Acceleration Partnership (SECARB-USA): Preliminary Regional Assessment of Potential Storage Complexes, Including Capacities and Costs, Based on Application of NRAP and SCO2T (Deliverable 3.3) Storage Complexes

The Recipient will assist with the field validation of one or more risk assessment toolsets through: 1) collaborative research; 2) sharing of relevant datasets, information, and technical insights from field efforts; and 3) other modeling and simulation toolsets as they are developed. Collaborative research could include, but is not limited to: 1) demonstrating use of field data for improved leakage pathway characterization, uncertainty reduction, and risk management and uncertainty workflows; 2) testing and validation of a specific National Risk Assessment Partnership (NRAP) tool using site specific data; and 3) improved modeling or reduced-order modeling of geophysical monitoring.

42 ENGINEERING↗
DOE OSTI2025

Computationally Guided and Experimentally Validated Design of Custom Chelators for Critical Mineral Recovery

Selective, high throughput separation of target critical metals from complex environments such as fly ash leachates and mining process streams presents a significant challenge for economical production. Custom chelators and sorbents are an attractive technology for selective metal extraction, however it can be difficult to predict their performance, and significant experimental efforts are often required to develop chelating technologies. Here, we present a computational strategy focused on modelling chelator-metal binding interactions and benchmark these results versus experimental data. A computational pipeline combining forcefield, semiempirical, and meta-GGA methods with a thermodynamic framework optimized for error cancellation has been developed to predict binding energies of chelator complexes towards critical mineral recovery applications. This approach, originally validated on [2.2.2] cryptates binding mono- and divalent cations, demonstrated robust predictive capabilities with an R2 of 0.850 against experimental aqueous binding energies. The workflow includes metadynamics for exploring high-dimensional potential energy surfaces and a cluster-continuum model for accurate yet computationally efficient solvation modeling. Error cancellation between solvation energies of free and chelator-coordinated ions enables faster convergence, even with finite cluster sizes. Initial studies on the cryptates revealed consistent metal-ligand coordination patterns, with systematic variations influenced by ion size and charge, highlighting key structural features linked to binding selectivity. Further studies of a proprietary chelator have resulted in identification of previously unreported selectivity towards economically significant metals, which in-house experiments have confirmed, demonstrating the feasibility of this approach. By applying this methodology to new chelators targeting critical minerals such as lithium, cobalt, nickel and other strategic metals, we aim to accelerate the discovery of next-generation chelators for efficient recovery, recycling, and separation processes. This computational framework serves as the backbone of a high-throughput design pipeline tailored for sustainable resource utilization and may be applied to a wide range of systems to meet experimental needs.

computational materials↗
DOE OSTI2026

A Benchmarking Framework for Evaluating Large Language Model Capabilities in Nuclear Reactor Safety Applications

Large language models (LLMs) are increasingly capable of answering technical questions, synthesizing domain knowledge, and supporting engineering workflows. For nuclear science and engineering, these capabilities require careful, domain-specific evaluation before they can be credibly incorporated into safety-related activities, regulatory review, or technical decision support. This paper presents preliminary results from benchmarking framework for evaluating LLM capabilities in nuclear contexts. The framework is organized into three evaluation categories: nuclear fundamentals, general dual-use knowledge, and plant specific knowledge. These categories are intended to distinguish general nuclear engineering competence from broader technical reasoning and more context-dependent nuclear knowledge. Initial evaluations focus on nuclear fundamentals using questions representative of the knowledge expected of a nuclear professional engineer. Results indicate that contemporary frontier models perform at a high level and substantially exceed the performance of older model generations, with some models approaching saturation of the current benchmark. These findings suggest both the rapid improvement of LLM capabilities in specialized technical domains and the need for more discriminating evaluation methods. The paper presents the benchmark structure, preliminary model-comparison results, and ongoing work. This work supports development of verifiable, responsible, and safety-conscious methods for assessing AI systems in nuclear engineering applications.

21 - SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLAN↗
DOE OSTI2024

Regional-scale fault-to-structure earthquake simulations with the EQSIM framework: Workflow maturation and computational performance on GPU-accelerated exascale platforms

Continuous advancements in scientific and engineering understanding of earthquake phenomena, combined with the associated development of representative physics-based models, is providing a foundation for high-performance, fault-to-structure earthquake simulations. However, regional-scale applications of high-performance models have been challenged by the computational requirements at the resolutions required for engineering risk assessments. The EarthQuake SIMulation (EQSIM) framework, a software application development under the US Department of Energy (DOE) Exascale Computing Project, is focused on overcoming the existing computational barriers and enabling routine regional-scale simulations at resolutions relevant to a breadth of engineered systems. This multidisciplinary software development—drawing upon expertise in geophysics, engineering, applied math and computer science—is preparing the advanced computational workflow necessary to fully exploit the DOE’s exaflop computer platforms coming online in the 2023 to 2024 timeframe. Achievement of the computational performance required for high-resolution regional models containing upward of hundreds of billions to trillions of model grid points requires numerical efficiency in every phase of a regional simulation. This includes run time start-up and regional model generation, effective distribution of the computational workload across thousands of computer nodes, efficient coupling of regional geophysics and local engineering models, and application-tailored highly efficient transfer, storage, and interrogation of very large volumes of simulation data. This article summarizes the most recent advancements and refinements incorporated in the workflow design for the EQSIM integrated fault-to-structure framework, which are based on extensive numerical testing across multiple graphics processing unit (GPU)-accelerated platforms, and demonstrates the computational performance achieved on the world’s first exaflop computer platform through representative regional-scale earthquake simulations for the San Francisco Bay Area in California, USA.

58 GEOSCIENCES↗
DOE OSTI2024

Machine Learning a Simple Interpretable Short-Range Potential for Silica

A wide array of models, spanning from computationally expensive ab initio methods to a spectrum of force-field approaches, have been developed and employed to probe silica polymorphs and understand growth processes and atomic-level dynamical transitions in silica. However, the quest for a model capable of making accurate predictions with high computational efficiency for various silica polymorphs is still ongoing. Recent developments in short-range machine-learned models, such as GAP and NNPScan, have shown promise in providing reasonable descriptions of silica, but their computational cost remains high compared to force fields such as BKS which are based on simple interpretable functional forms. Here, in this study, we build on the recent success of our reinforcement learning (RL) workflow to derive a new set of optimal parameters for a promising short-range BKS-based model proposed by Soules. We use RL to navigate the eight-dimensional parameter space of the Soules potential using an experimental training data set that includes both local and global structural features from approximately 21 experimentally realized silica polymorphs, including high density phases and porous zeolites. We compare the performance of our machine-learned ML-Soules model with other high quality models including our recent machine-learned parametrization of BKS (ML-BKS), a machine-learned potential (GAP), as well as predictions of ab initio calculations with the highly fidelity SCAN functional. The ML-Soules accurately captures the relative energetic ordering of various polymorphs as well as their structural features at a significantly reduced computational expense. The ML-Soules model also reasonably captures the structure, density, and elastic constants of quartz, as well as metastable silica polymorphs. We further discuss the limitations of the Soules functional form and propose potential enhancements, including the incorporation of additional three-body terms and/or the utilization of different short-ranged functional forms to achieve greater accuracy for both global and local features in the modeling of silica while retaining low computational cost.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗