Article
Chemistry, Multidisciplinary
Yifeng Tang, Jeremiah Y. Kim, Carman K. M. Ip, Azadeh Bahmani, Qing Chen, Matthew G. Rosenberger, Aaron P. Esser-Kahn, Andrew L. Ferguson
Summary: A machine learning-enabled active learning pipeline was developed to guide the screening and discovery of small molecule immunomodulators that can improve immune responses. By using high throughput screening and data-driven predictive models, novel small molecules with enhanced or suppressed innate immune signaling capacity were discovered, and chemical design rules were extracted.
Article
Chemistry, Multidisciplinary
Manish Kothakonda, Yanglin Zhu, Yingdong Guan, Jingyang He, Jamin Kidd, Ruiqi Zhang, Jinliang Ning, Venkatraman Gopalan, Weiwei Xie, Zhiqiang Mao, Jianwei Sun
Summary: Recent advances in 2D magnetism have led to increased interest in layered magnetic materials for spintronics applications. Layered semiconducting antiferromagnets exhibit unique low-dimensional semiconducting behavior and can be controlled by both charge and spin. However, synthesizing these compounds is challenging and rare. In this study, a high-throughput search based on first-principles was conducted to identify potentially stable mixed metal phosphorus trichalcogenides. Among the candidates, a stable semiconducting layered magnetic material, CdFeP2Se6, was successfully synthesized, exhibiting short-range antiferromagnetic order at 21 K with an indirect bandgap of 2.23 eV. This work suggests that high-throughput screening-assisted synthesis can be an effective method for discovering layered magnetic materials.
ADVANCED FUNCTIONAL MATERIALS
(2023)
Review
Chemistry, Multidisciplinary
Xabier Rodriguez-Martinez, Enrique Pascual-San-Jose, Mariano Campoy-Quiles
Summary: The discovery of novel high-performing materials in organic solar cells has rapidly increased efficiency, but traditional experimentation methods are unable to evaluate the vast catalog of materials efficiently. High-throughput experimental and computational methods are being utilized to accelerate the discovery of new materials, with machine-learning algorithms playing a key role in retrieving quantitative structure-activity relationships.
ENERGY & ENVIRONMENTAL SCIENCE
(2021)
Review
Chemistry, Multidisciplinary
Shulin Luo, Tianshu Li, Xinjiang Wang, Muhammad Faizan, Lijun Zhang
Summary: Optoelectronic semiconductors have attracted significant research attention for large-scale applications, and high-throughput computational screening has emerged as a useful tool to accelerate materials discovery, leading to the construction of diverse material databases.
WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL MOLECULAR SCIENCE
(2021)
Article
Engineering, Environmental
Lei Tao, Jinlong He, Nuwayo Eric Munyaneza, Vikas Varshney, Wei Chen, Guoliang Liu, Ying Li
Summary: This study explores the discovery of high-performance polyimides using machine learning and molecular dynamics simulations. A comprehensive library of over 8 million hypothetical polyimides is built, and multiple machine learning models are established to predict the thermal and mechanical properties of polyimides. Through the screening of machine learning models, three novel polyimides with superior properties are discovered and validated through molecular dynamics simulations and experiments. This study provides an efficient approach to expedite the discovery of novel polymers.
CHEMICAL ENGINEERING JOURNAL
(2023)
Article
Pharmacology & Pharmacy
Modest von Korff, Thomas Sander
Summary: This study examined the extrapolation capabilities of six machine learning algorithms on 243 datasets and found that extrapolation with sorted data resulted in larger prediction errors, while linear machine learning methods are preferable for extrapolation.
FRONTIERS IN PHARMACOLOGY
(2022)
Article
Materials Science, Multidisciplinary
Yonggang Yan, Zongrui Pei, Michael C. Gao, Scott Misture, Kun Wang
Summary: The interest in high entropy ceramics (HECs) has steadily increased due to their superior properties. Using a data-driven approach, a rational rule for designing single-phase high entropy transition metal diborides (HEBs) is discovered. The machine learning (ML) model trained on data collected via high-throughput experiments (HTEs) achieves an experimental validation accuracy of 93.75% with the K nearest neighbors (KNN) model. The empirical rule proposed indicates that HEBs tend to form a single phase when delta B_TM < 3.66 and multiphase otherwise, with a high accuracy of 93.33% for new HEBs predictions. Additionally, 165 high quality HEBs data are contributed, promoting the development of materials informatics in HEBs and accelerating the search for new HECs.
Article
Engineering, Multidisciplinary
Moritz Flaschel, Siddhant Kumar, Laura De Lorenzis
Summary: We extend our unsupervised automated discovery approach (EUCLID) to unknown constitutive behavior, covering a wide range of important classes. This approach leverages the theory of generalized standard materials to automatically discover the two scalar thermodynamic potentials that define their behavior. The enforced convexity constraint ensures stability and consistency, and sparsity promoting regularization leads to a simple and interpretable model with few internal variables.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2023)
Article
Chemistry, Physical
Matthew Bain, Jose L. Godinez Castellanos, Stephen E. Bradforth
Summary: High-repetition-rate lasers have the potential to revolutionize ultrafast spectroscopy by enabling routine analysis for machine learning models in the design of photochemical syntheses. In this study, we combine innovations in line scan cameras and micro-electro-mechanical grating modulators with high-pressure liquid chromatography pumps to develop a transient absorption spectrometer that can characterize photoreactions in minutes. Additionally, we demonstrate the utility of this technique in exploring the effects of conformational modification on excited-state processes.
JOURNAL OF PHYSICAL CHEMISTRY LETTERS
(2023)
Correction
Chemistry, Multidisciplinary
Shulin Luo, Tianshu Li, Xinjiang Wang, Muhammad Faizan, Lijun Zhang
Summary: Optoelectronic semiconductors have attracted research attention for large-scale applications, with high-throughput computational screening emerging as a useful tool for accelerating materials discovery. The construction of material databases containing diverse functional materials is an important consequence of this approach.
WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL MOLECULAR SCIENCE
(2021)
Article
Engineering, Multidisciplinary
Siwei Song, Yi Wang, Fang Chen, Mi Yan, Qinghua Zhang
Summary: This study presents a methodology that combines domain knowledge, machine learning algorithms, and experiments to accelerate the discovery of novel energetic materials. The established high-throughput virtual screening system allows for the rapid selection of candidate molecules with promising properties and desirable crystal packing modes from a large molecular space. Experimental results confirm the effectiveness of the proposed methodology.
Article
Engineering, Environmental
Wanje Park, Kwang Hyun Oh, Dongil Lee, Seo-Yul Kim, Youn-Sang Bae
Summary: An aluminum-based metal-organic framework (MOF), Al-NDC, has been identified as a highly selective adsorbent for radon removal. It demonstrated excellent radon removal rate and stability compared to activated carbon benchmarks. The study also revealed that high crystal densities, low surface areas, small pore volumes, and appropriately-sized channel-like pores are favorable for the selective capture of radon.
CHEMICAL ENGINEERING JOURNAL
(2023)
Article
Chemistry, Multidisciplinary
Mesfin Diro Chaka, Chernet Amente Geffe, Alex Rodriguez, Nicola Seriani, Qin Wu, Yedilfana Setarge Mekonnen
Summary: Redox flow batteries (RFBs) are a promising option for large-scale energy storage due to their high energy density, low cost, and environmental benefits. However, identifying organic compounds with the desired properties for RFB technology is a challenging task. In this study, a graph neural network-based model called MolGAT was developed to predict the redox potential of organic molecules using their molecular structures, atomic properties, and bond attributes.
Article
Chemistry, Medicinal
Yiwei Zhang, Jiabei Guo, Jiongjia Cheng, Zhenghua Zhang, Fenghua Kang, Xiaoxing Wu, Qian Chu
Summary: Therapeutic peptides have revolutionized treatment for many human diseases. In recent decades, stapled helical peptides have made rapid progress in drug discovery. Compared to unstabilized linear peptides, stapled helical peptides have shown superior binding affinity, selectivity, membrane permeability, and metabolic stability, offering exciting potential for targeting challenging protein-protein interfaces. This Perspective summarizes the recent use of high-throughput screening technologies for identifying potent stapled helical peptides with optimized binding properties, aiming to accelerate the development of stapled helical peptides as the next generation of therapeutic peptides for various human diseases.
JOURNAL OF MEDICINAL CHEMISTRY
(2023)
Article
Chemistry, Multidisciplinary
Jiaxin Fan, Wenxian Li, Sean Li, Jack Yang
Summary: Ammonia has gained attention as a carrier for hydrogen usage in the hydrogen economy, but new synthesis techniques are needed to overcome high energy consumption. Chemical looping ammonia synthesis (CLAS) is a promising approach, but ideal redox materials are yet to be discovered. This study screens 1699 bicationic redox pairs using the MP database and employs machine learning to broaden the search for potential redox materials. Bicationic compounds containing alkali/alkaline-earth metals and transition metal/metalloid elements show promise in CLAS.
Article
Materials Science, Multidisciplinary
Marianne Liu, Conrad Clement, Kathy Liu, Xuming Wang, Taylor D. Sparks
Summary: Solid polymer electrolytes (SPEs) have the potential to revolutionize battery technology innovation by making batteries nonflammable, flexible, and more sustainable. The study presents a data-driven approach to SPE development, with the random forest model identified as the most suitable for predicting conductivity. This research lays the foundation for accelerated innovation in SPE by applying machine learning to incorporate important parameters of SPE synthesis.
COMPUTATIONAL MATERIALS SCIENCE
(2021)
Editorial Material
Materials Science, Multidisciplinary
Taylor D. Sparks, Anton O. Oliynyk, Vitaliy Romaka
COMPUTATIONAL MATERIALS SCIENCE
(2021)
Article
Multidisciplinary Sciences
Debanshu Banerjee, Taylor D. Sparks
Summary: Machine learning tools can improve the efficiency of human analysis of research data, and feature engineering may be more effective than transfer learning alone.
Article
Chemistry, Physical
Marcus E. Parry, Jackson Hendry, Samantha Couper, Aria Mansouri Tehrani, Anton O. Oliynyk, Jakoah Brgoch, Lowell Miyagi, Taylor D. Sparks
Summary: This study investigates the impact of Mo and W substitution on the hardness and ductility in the Mo(2)(-x)WxBC system using a combination of experimental and computational methods. The experimental results show that the substitution leads to a slight increase in bulk modulus and a decrease in unit cell volume. These findings are consistent with previous computational results and provide valuable insights for the design of sustainable materials with exceptional mechanical properties.
CHEMISTRY OF MATERIALS
(2022)
Article
Chemistry, Multidisciplinary
Sterling G. Baird, Taylor D. Sparks
Summary: A large collection of element-wise planar densities for compounds obtained from the Materials Project is calculated using brute force computational geometry methods. The element-wise maximum lattice plane densities are demonstrated to be useful as machine learning features. The methods described here are implemented in an open-source Mathematica package.
JOURNAL OF APPLIED CRYSTALLOGRAPHY
(2022)
Article
Materials Science, Multidisciplinary
Sterling G. Baird, Marianne Liu, Taylor D. Sparks
Summary: This article introduces a method for optimizing the hyperparameters of the CrabNet model using the Adaptive Experimentation (Ax) Platform. By using the sparse axis-aligned subspaces Bayesian optimization algorithm, a state-of-the-art result is achieved on the materials informatics benchmarking platform. The article also analyzes the characteristics of the adaptive design scheme and the feature importances of the Ax models, and points out the great potential of the algorithm in high-dimensional materials science search spaces.
COMPUTATIONAL MATERIALS SCIENCE
(2022)
Article
Electrochemistry
Pooya Elahi, Jude Horsley, Taylor D. Sparks
Summary: The composite electrolyte, consisting of a fast sodium-ion conductor and an oxygen-ion conductor synthesized through a vapor phase conversion mechanism, shows higher kinetic rates and larger three-phase boundaries. The total conductivity fits an Arrhenius type equation with activation energies ranging from 0.23eV at 550°C to 1.07eV at 550°C.
JOURNAL OF THE ELECTROCHEMICAL SOCIETY
(2022)
Article
Chemistry, Multidisciplinary
Vishakha Gupta, Rakshit Jain, Yafei Ren, Xiyue S. Zhang, Husain F. Alnaser, Amit Vashist, Vikram V. Deshpande, David A. Muller, Di Xiao, Taylor D. Sparks, Daniel C. Ralph
Summary: The advantages of mechanically stacked samples of van der Waals materials for controlling the surface state of a three-dimensional topological insulator are demonstrated. The interaction between the topological surface state and an adjacent magnet layer can be controlled, resulting in an observed anomalous Hall effect.
Article
Multidisciplinary Sciences
Su Kong Chong, Lizhe Liu, Kenji Watanabe, Takashi Taniguchi, Taylor D. Sparks, Feng Liu, Vikram V. Deshpande
Summary: Transport evidence of two-dimensional (2D) topological states in a bulk insulating three-dimensional (3D) topological insulator (TI) is provided. The existence of a finite longitudinal conductance at the surface gap suggests the emergence of a quantum spin Hall (QSH) state. The transition from QSH to quantum Hall (QH) state in a transverse magnetic field further supports the existence of this unique 2D topological phase. Another method of achieving the 2D topological state is demonstrated through surface gap-closing and topological phase transition mediated by a transverse electric field.
NATURE COMMUNICATIONS
(2022)
Article
Chemistry, Inorganic & Nuclear
Husain F. Alnaser, Stacey J. Smith, Taylor D. Sparks
Summary: This work investigates the structure of Bi2-xSbxTe3-ySey using various techniques and reveals that it belongs to the trigonal crystal system with R3m symmetry, correcting the previous misattribution to the hexagonal symmetry in the literature. X-ray photoelectron spectroscopy analysis supports the refined atomic site occupancies. The misattribution of Bi2-xSbxTe3-ySey to hexagonal symmetry in former literature is attributed to the improper use of crystallographic terminology and the misinterpretation of diffraction patterns caused by defects, with twinning proposed as the primary source of confusion between trigonal and hexagonal symmetry for BSTS.
JOURNAL OF SOLID STATE CHEMISTRY
(2023)
Article
Materials Science, Multidisciplinary
Shadi Al Khateeb, Brian T. Bennett, James P. Beck, Sujee Jeyapalina, Taylor D. Sparks
Summary: Spray pyrolysis was used for the first time to deposit fluorapatite (FAP) thin films on titanium using different setups and atomizer frequencies. The deposition process was explored using pre-synthesized FAP powder and various chemical precursors. The crystallinity, texture, and morphology of the deposited films were analyzed using X-ray diffraction and electron microscopy.
JOURNAL OF MATERIALS RESEARCH
(2023)
Article
Materials Science, Multidisciplinary
Magda Titirici, Sterling G. Baird, Taylor D. Sparks, Shirley Min Yang, Agnieszka Brandt-Talbot, Omid Hosseinaei, David P. Harper, Richard M. Parker, Silvia Vignolini, Lars A. Berglund, Yuanyuan Li, Huai-Ling Gao, Li-Bo Mao, Shu-Hong Yu, Noel Diez, Guillermo A. Ferrero, Marta Sevilla, Petra Agota Szilagyi, Connor J. Stubbs, Joshua C. Worch, Yunping Huang, Christine K. Luscombe, Koon-Yang Lee, Hui Luo, M. J. Platts, Devendra Tiwari, Dmitry Kovalevskiy, David J. Fermin, Heather Au, Hande Alptekin, Maria Crespo-Ribadeneyra, Valeska P. Ting, Tim-Patrick Fellinger, Jesus Barrio, Olivia Westhead, Claudie Roy, Ifan E. L. Stephens, Sabina Alexandra Nicolae, Saurav Ch Sarma, Rose P. Oates, Chen-Gang Wang, Zibiao Li, Xian Jun Loh, Rupert J. Myers, Niko Heeren, Alice Gregoire, Clement Perisse, Xiaoying Zhao, Yael Vodovotz, Becky Earley, Goran Finnveden, Anna Bjorklund, Gavin D. J. Harper, Allan Walton, Paul A. Anderson
Summary: Over the past 150 years, our reliance on producing and using materials at a fast rate has had negative effects on the environment and future generations. To ensure sustainability, we need to develop more sustainable materials alternatives, reduce material usage, eliminate toxic materials, and focus on reuse and recycling. Additionally, we need to consider the entire life cycle of materials and rely on reliable data to assess sustainability. The development of sustainable materials is crucial for various industries, especially in sustainable energy systems.
JOURNAL OF PHYSICS-MATERIALS
(2022)
Article
Materials Science, Multidisciplinary
Raju Baral, Jacob A. Christensen, Parker K. Hamilton, Feng Ye, Karine Chesnel, Taylor D. Sparks, Rosa Ward, Jiaqiang Yan, Michael A. McGuire, Michael E. Manley, Julie B. Staunton, Raphel P. Hermann, Benjamin A. Frandsen
Summary: Short-range magnetic correlations can significantly enhance the thermopower of magnetic semiconductors. This study reveals the nature of such correlations in the antiferromagnetic semiconductor MnTe and provides a real-space view of nanometer-scale antiferromagnetic correlations. The findings inform future efforts to optimize thermoelectric performance using magnetic means.
Article
Computer Science, Information Systems
Richard G. Edwards, Isaac Krieger, Mark P. Halling, Shelley D. Minteer, Taylor D. Sparks, David Schurig
Summary: A novel design and fabrication technique using open cellular structures has been developed for complex microwave waveguide components. This technique enables the fabrication of electrically conductive, complex, and multi-functional parts, with potential for improved performance.
Article
Engineering, Manufacturing
Andrew R. Falkowski, Steven K. Kauwe, Taylor D. Sparks
Summary: This approach shifts the optimization focus to the fractions of each element in a composition, using a pretrained network and a custom loss function to optimize material compositions. Fractional optimization is expected to excel in inverse design problems concerning the effects of dopants and balancing competing properties.
INTEGRATING MATERIALS AND MANUFACTURING INNOVATION
(2021)
Correction
Materials Science, Multidisciplinary
A. D. Boccardo, M. Tong, S. B. Leen, D. Tourret, J. Segurado
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
Tao Li, Qing Hou, Jie-chao Cui, Jia-hui Yang, Ben Xu, Min Li, Jun Wang, Bao-qin Fu
Summary: This study investigates the thermal and defect properties of AlN using molecular dynamics simulation, and proposes a new method for selecting interatomic potentials, developing a new model. The developed model demonstrates high computational accuracy, providing an important tool for modeling thermal transport and defect evolution in AlN-based devices.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
Shin-Pon Ju, Chao-Chuan Huang, Hsing-Yin Chen
Summary: Amorphous boron nitride (a-BN) is a promising ultralow-dielectric-constant material for interconnect isolation in integrated circuits. This study establishes a deep learning potential (DLP) for different forms of boron nitride and uses molecular dynamics simulations to investigate the mechanical behaviors of a-BN. The results reveal the structure-property relationships of a-BN, providing useful insights for integrating it in device applications.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
M. Salman, S. Schmauder
Summary: Shape memory polymer foams (SMPFs) are lightweight cellular materials that can recover their undeformed shape through external stimulation. Reinforcing the material with nano-clay filler improves its physical properties. Multiscale modeling techniques can be used to study the thermomechanical response of SMPFs and show good agreement with experimental results.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
Laura Gueci, Francesco Ferrante, Marco Bertini, Chiara Nania, Dario Duca
Summary: This study investigates the acidity of 30 Bronsted sites in the beta-zeolite framework and compares three computational methods. The results show a wide range of deprotonation energy values, and the proposed best method provides accurate calculations.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
K. A. Lopes Lima, L. A. Ribeiro Junior
Summary: Advancements in nanomaterial synthesis and characterization have led to the discovery of new carbon allotropes, including biphenylene network (BPN). The study finds that BPN lattices with a single-atom vacancy exhibit higher CO2 adsorption energies than pristine BPN. Unlike other 2D carbon allotropes, BPN does not exhibit precise CO2 sensing and selectivity by altering its band structure configuration.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
Jay Kumar Sharma, Arpita Dhamija, Anand Pal, Jagdish Kumar
Summary: In this study, the quaternary Heusler alloys LiAEFeSb were investigated for their crystal structure, electronic properties, and magnetic behavior. Density functional theory calculations revealed that LiSrFeSb and LiBaFeSb exhibit half-metallic band structure and 100% spin polarization, making them excellent choices for spintronic applications.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
Roman A. Eremin, Innokentiy S. Humonen, Alexey A. Kazakov, Vladimir D. Lazarev, Anatoly P. Pushkarev, Semen A. Budennyy
Summary: Computational modeling of disordered crystal structures is essential for studying composition-structure-property relations. In this work, the effects of Cd and Zn substitutions on the structural stability of CsPbI3 were investigated using DFT calculations and GNN models. The study achieved accurate energy predictions for structures with high substitution contents, and the impact of data subsampling on prediction quality was comprehensively studied. Transfer learning routines were also tested, providing new perspectives for data-driven research of disordered materials.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
Zhixin Sun, Hang Dong, Yaohui Yin, Ai Wang, Zhen Fan, Guangyong Jin, Chao Xin
Summary: In this study, the crystal structure, electronic structure, and optical properties of KH2PO4: KDP crystals under different pressures were investigated using the generalized gradient approximate. It was found that high pressure caused a phase transition in KDP and greatly increased the band gap. The results suggest that high pressure enhances the compactness of KDP and improves the laser damage threshold.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
Tingting Yu
Summary: This study presents atomistic simulations revealing that an increase in driving force may result in slower grain boundary movement and switches in the mode of grain boundary shear coupling migration. Shear coupling behavior is found to effectively alleviate stress and holds potential for stress relaxation and microstructure manipulation in materials.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
Y. Zhang, X. Q. Deng, Q. Jing, Z. S. Zhang
Summary: The electronic properties of C2N/antimonene van der Waals heterostructure are investigated using density functional theory. The results show that by applying horizontal strain, vertical strain, electric field, and interlayer twist, the electronic structure can be adjusted. Additionally, the band alignment and energy states of the heterostructure can be significantly changed by applying vertical strain on the twisted structure. These findings are important for controlling the electronic properties of heterostructures.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
Chad E. Junkermeier, Evan Larmand, Jean-Charles Morais, Jedediah Kobebel, Kat Lavarez, R. Martin Adra, Jirui Yang, Valeria Aparicio Diaz, Ricardo Paupitz, George Psofogiannakis
Summary: This study investigates the adsorption properties of carbon dioxide (CO2), methane (CH4), and dihydrogen (H2) in carbophenes functionalized with different groups. The results show that carbophenes can be promising adsorbents for these gases, with high adsorption energies and low desorption temperatures. The design and combination of functional groups can further enhance their adsorption performance.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
Y. Borges, L. Huber, H. Zapolsky, R. Patte, G. Demange
Summary: Grain boundary structure is closely related to solute atom segregation, and machine learning can predict the segregation energy density. The study provides a fresh perspective on the relationship between grain boundary structure and segregation properties.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
M. R. Jones, L. T. W. Fey, I. J. Beyerlein
Summary: In this work, a three-dimensional ab-initio informed phase-field-dislocation dynamics model combined with Langevin dynamics is used to investigate glide mechanisms of edge and screw dislocations in Nb at finite temperatures. It is found that the screw dislocation changes its mode of glide at two distinct temperatures, which coincides with the thermal insensitivity and athermal behavior of Nb yield strengths.
COMPUTATIONAL MATERIALS SCIENCE
(2024)
Article
Materials Science, Multidisciplinary
Joshua A. Vita, Dallas R. Trinkle
Summary: This study introduces a new machine learning model framework that combines the simplicity of spline-based potentials with the flexibility of neural network architectures. The simplified version of the neural network potential can efficiently describe complex datasets and explore the boundary between classical and machine learning models. Using spline filters for encoding atomic environments results in interpretable embedding layers that can incorporate expected physical behaviors and improve interpretability through neural network modifications.
COMPUTATIONAL MATERIALS SCIENCE
(2024)