Article
Metallurgy & Metallurgical Engineering
Dong Sun, Shu-yong Jiang, Yan-qiu Zhang, Bing-yao Yan, Hao Feng
Summary: This study investigates the discontinuous dynamic recrystallization (DDRX) behavior of TiNb alloys during hot compression, and finds that the CA model can effectively predict this behavior. The mean grain size and volume fraction for DDRX of TiNb alloys increase with increasing deformation temperature, but decrease with increasing strain rate. In addition, the serrated grain boundaries and nucleation points of recrystallized grains in the deformed TiNb samples align with the characteristics of grain boundary bulging mechanism. Furthermore, the random orientation effect of DDRX grains helps to weaken the intensity of deformation texture in TiNb alloys.
JOURNAL OF CENTRAL SOUTH UNIVERSITY
(2023)
Article
Materials Science, Coatings & Films
Seyedeh Marjan Bararpour, Hamed Jamshidi Aval, Roohollah Jamaati
Summary: In this study, a cellular automaton model was used to predict the dynamic recrystallized microstructure of the friction-surfaced Al-Mg alloy coating, showing that the prediction error of grain size when considering secondary phase particles was lower. With an increase in rotational and traverse speeds as well as axial feeding rate, the grain size of the coating decreases initially before bouncing back up.
SURFACE & COATINGS TECHNOLOGY
(2021)
Article
Materials Science, Multidisciplinary
Dayu Shu, Jing Wang, Menghao Jiang, Gang Chen, Liwei Lu, Hongming Zhang
Summary: The DRX behavior of the as-extruded AM50 magnesium alloy was investigated using isothermal compression experiments and CA simulations, showing that the behavior is temperature and strain rate dependent. The developed CA model can confidently estimate the DRX behavior of the alloy under high temperature conditions.
Article
Materials Science, Multidisciplinary
Kotaro Iguchi, Toshio Ogawa, Fei Sun, Yoshitaka Adachi
Summary: This study investigated the ferrite recrystallization behavior of pure iron with different dislocation characters. Two types of specimens with similar dislocation densities but different dislocation characters were prepared. Ferrite recrystallization progressed faster in one specimen compared to the other. Cellular automaton simulation showed that the differences in ferrite recrystallization behavior were attributed to variations in the driving force for recrystallization and activation energy for recovery in each specimen. Thus, the dislocation character was found to have an impact on the ferrite recrystallization behavior of pure iron.
JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T
(2023)
Article
Metallurgy & Metallurgical Engineering
Xu Ren, Yuan-Ming Huo, Tao He, Seyed Reza Elmi Hosseini, Zhi-Yuan Bian, Jie Bai, Xiang-Yang Du
Summary: Isothermal compression experiments were conducted on EA4T steel at different temperatures and strain rates, and a high-temperature constitutive model was developed based on the experimental data. The activation energy for dynamic recrystallization was calculated, and a modified cellular automaton model suitable for EA4T steel was developed to simulate the behavior of dynamic recrystallization.
STEEL RESEARCH INTERNATIONAL
(2023)
Article
Materials Science, Multidisciplinary
K. Arun Babu, T. S. Prithiv, Abhinav Gupta, Sumantra Mandal
Summary: A cellular automaton (CA) model has been established for predicting flow stress, DRX grain size, and DRX fraction of super austenitic stainless steel under different strain rates and temperatures, which has been further optimized and used for establishing ANN-based constitutive models. A modified cellular automata (CAM) model has been developed to numerically consider the solute drag effect, showing improved accuracy in predicting microstructure evolution and flow behavior of the alloy under non-isothermal deformation conditions.
COMPUTATIONAL MATERIALS SCIENCE
(2021)
Article
Agriculture, Dairy & Animal Science
Yizhou B. Ma, Jayendra K. Amamcharla
Summary: The study utilized front-face fluorescence spectroscopy and chemometrics to measure casein content in fluid milk with different casein-to-crude-protein ratios, achieving accurate predictions and demonstrating practical model performance for quality-control in the dairy industry.
JOURNAL OF DAIRY SCIENCE
(2021)
Article
Food Science & Technology
Cheng Wang, Yingying Sun, Yanyu Zhou, Yiwen Cui, Weirong Yao, Hang Yu, Yahui Guo, Yunfei Xie
Summary: A novel method for the determination of peroxide value (PV) of nuts based on PLSR and RF-PLSR model was established, showing that Raman spectroscopy combined with chemometrics could be used to establish a rapid and precise method for the determination of oil oxidation index.
LWT-FOOD SCIENCE AND TECHNOLOGY
(2021)
Article
Metallurgy & Metallurgical Engineering
Yu-Ying He, Sheng-Wen Bai, Gang Fang
Summary: In this study, the dynamic recrystallization (DRX) behavior of a Mg-Al-Zn-RE alloy with abundant second-phase particles during hot extrusion is investigated using a combination of finite element (FE) and cellular automaton (CA) models. The results show that the extrusion conditions have a significant influence on the microstructural evolution of the magnesium alloy.
JOURNAL OF MAGNESIUM AND ALLOYS
(2022)
Article
Engineering, Industrial
Jiawei Xu, Qiwei He, Xueze Jin, Shaoshun Bian, Debin Shan, He Wu, Wenchen Xu
Summary: In this study, the limitations of traditional cellular automaton (CA) models in simulating dynamic recrystallization (DRX) behavior of mixed-grain microstructures were analyzed. The researchers used an inhomogeneous nucleation method based on the relationship between nucleation probability and dislocation amounts of grains to overcome this challenge. Isothermal compression experiments were conducted to validate the reliability of the models. The study showed that 3D CA was advantageous for mixed-grain microstructures and could help in selecting suitable deformation parameters.
JOURNAL OF MATERIALS PROCESSING TECHNOLOGY
(2023)
Article
Engineering, Mechanical
Fei Chen, Huajia Zhu, Wen Chen, Hengan Ou, Zhenshan Cui
Summary: The study developed a multiscale modeling framework, the MCAFE-dDRX model, to evaluate the dDRX microstructure evolution during hot working processes, facilitating the prediction of microstructure evolution during heterogeneous and non-isothermal deformation of materials.
INTERNATIONAL JOURNAL OF PLASTICITY
(2021)
Article
Agronomy
Weijie Lan, Benoit Jaillais, Catherine M. G. C. Renard, Alexandre Leca, Songchao Chen, Carine Le Bourvellec, Sylvie Bureau
Summary: This study highlighted the heterogeneity of apple fruit using near-infrared hyperspectral imaging, quantifying key components within the fruit through a two-step data analysis process. PCA and PLS models successfully described the distribution of dry matter and total sugars within each apple slice.
POSTHARVEST BIOLOGY AND TECHNOLOGY
(2021)
Article
Mathematics, Interdisciplinary Applications
Mojtaba Sajjadmanesh, Hassen Aydi, Eskandar Ameer, Choonkil Park
Summary: This paper discusses an inverse geometric problem for the three-dimensional Laplace equation to recover an inner boundary of an annular domain using the method of fundamental solutions (MFS). It works by imposing the boundary Cauchy data in a least-square sense and minimizing the objective function. The simplicity and efficiency of this method is demonstrated in several numerical examples.
FRACTAL AND FRACTIONAL
(2022)
Article
Physics, Multidisciplinary
Jiaming Yu, Hui Qi, Xiangyu Li, Kai Wang, Jing Guo
Summary: Nonlinear aeroelastic systems are difficult to model and calculate due to their complex structure and dynamic response. Model identification is an attractive method for analyzing such systems. However, traditional methods often produce complex models with limited applicability, necessitating the development of interpretable reduced models. This paper proposes a sparse identification method for complex aeroelastic systems using the sparse regression method and sequential threshold least squares technique. The identified models contain only the necessary nonlinear terms based on measurement data. The method is applied to identify a binary wing with dead zone nonlinearity and cubic stiffness nonlinearity, and the resulting model enables rapid and accurate prediction of system response and serves as an explicit surrogate model for aeroelastic optimization design, demonstrating its superiority.
Article
Mathematics, Applied
Tabassum Naz Sindhu, Zawar Hussain, Naif Alotaibi, Taseer Muhammad
Summary: This study discusses the mathematical characteristics of the Lindley model mixed with 2-component (2-CMLM) and investigates its practical and theoretical aspects. Various statistical features are examined, and the proposed 2-CMLM is shown to outperform other models in modelling COVID-19 patient data.
Article
Materials Science, Multidisciplinary
Mingxiang Liu, Changjiang Song, Zhenshan Cui
Summary: The strain-induced martensite transformation plays a crucial role in the strain hardening process of low-density steel. This transformation is affected by the texture evolution and grain size of austenite, influencing the rate of martensite transformation in each stage of strain hardening. The presence of TWIP effect and high density dislocations during martensite transformation contributes to continuous hardening, but the final stage is slowed down by unfavorable orientation and reduced grain size of austenite.
JOURNAL OF MATERIALS SCIENCE & TECHNOLOGY
(2021)
Article
Materials Science, Multidisciplinary
Shilin Zhao, Haiming Zhang, Zhenshan Cui, Dong Chen, Zhe Chen
Summary: In this study, a severe plastic deformation method, E-TE, was used to achieve superplasticity in an in-situ TiB2/Al-Zn-Mg-Cu composite by optimizing the microstructure. Tensile tests revealed that the composite showed excellent superplastic behavior at specific temperatures and strain rates, achieving elongations up to 420%. The deformation and failure mechanisms of the composite varied with temperature, with different mechanisms observed at different temperature ranges.
MATERIALS CHARACTERIZATION
(2021)
Article
Nanoscience & Nanotechnology
Lan Huang, Zhenshan Cui, Xiangpeng Meng, Xianwei Zhang, Xiaoyan Zhang, Xiping Song, Ning Tang, Zhu Xiao, Qian Lei, Zhou Li
Summary: High ductility Cu-Ti alloys were fabricated and investigated systematically in this work, with strength and plasticity being improved by adding high Ti and Cr content. The crystal relationship between different phases was studied, and precipitation strengthening was identified as the primary strengthening mechanism. The CuTiCrMg alloy and CuTiCrMg-Fe alloy exhibited different mechanical properties after aging, with the former showing higher hardness and yield strength while the latter had higher elongation.
MATERIALS SCIENCE AND ENGINEERING A-STRUCTURAL MATERIALS PROPERTIES MICROSTRUCTURE AND PROCESSING
(2021)
Article
Materials Science, Multidisciplinary
Yanqi Fu, Zhenshan Cui
Summary: The study found that in Ti2AlNb alloy, Al and Ti atoms are enriched around grain boundaries, promoting the precipitation of the alpha 2 phase, while the clustering and segregation of Al and Ti atoms inhibit the growth of the O phase. The content of alpha 2 and O phase precipitation is influenced by segregated atoms induced by plastic deformation and aging treatment.
JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE
(2022)
Article
Chemistry, Physical
Shuai Xu, Xinwei Xiao, Haiming Zhang, Zhenshan Cui
Summary: Electrical-assisted forming technology can significantly improve the ductility of hard-deformable materials, weaken size effects, enhance mechanical responses, and improve deformation characteristics by inhibiting extension twinning in the early stages of deformation.
Article
Engineering, Mechanical
Yangqi Li, Haiming Zhang, Xiaoqing Shang, Mingxiang Liu, Shilin Zhao, Zhenshan Cui
Summary: This study investigates the microscopic deformation heterogeneity in mixed-grain structures with millimeter-grade coarse grains (MCGs) and proposes a mesoscale crystal plasticity (CP) model to describe the uneven grain size effect. The results show that a large deformation band is preferentially generated during deformation, covering the MCG and its surrounding fine grains (FGs), resulting in intense strain and stress localizations. It is found that the preferential deformation characteristic of the MCG is related to its 'lake' shape distribution of the number of activated slip systems (N-s). The study also reveals that the MCG deforms in single-slip at early deformation and in primary-slip at large deformation. Compared with the FG structure, the MCGs have weaker initial slip resistance and hardening rate.
INTERNATIONAL JOURNAL OF PLASTICITY
(2022)
Article
Chemistry, Physical
Zhipeng Zhou, Qian Lei, Longfei Zhang, Zhenshan Cui, Yijing Shang, Huan Qi, Yunping Li, Liang Jiang, Venkata Karthik Nadimpalli, Lan Huang
Summary: Direct energy deposition is a promising technology to improve the performance of single-crystal superalloys. The multi-track overlapping deposition allows for the fabrication of large-size parts, but it also introduces challenges related to thermal processes and stress concentration. This study investigates the microstructural evolution of multi-track overlapped nickel-based single-crystal superalloys during heat treatment.
JOURNAL OF ALLOYS AND COMPOUNDS
(2022)
Article
Nanoscience & Nanotechnology
Lan Huang, Zhenshan Cui, Xiangpeng Meng, Xiang Li, Xiaofei Sheng, Qian Lei
Summary: Modern electronic components have higher requirements for copper-based alloys, and it has been found that Fe can improve the strength and stress relaxation resistance of the alloy, which is of great significance for the development of Cu-Ti alloys with high strength and high stress relaxation resistance.
MATERIALS SCIENCE AND ENGINEERING A-STRUCTURAL MATERIALS PROPERTIES MICROSTRUCTURE AND PROCESSING
(2022)
Article
Multidisciplinary Sciences
Hongyue Ma, Yangqi Li, Haiming Zhang, Qian Li, Fei Chen, Zhenshan Cui
Summary: In this study, we proposed a virtual laboratory based on full-field crystal plasticity simulation to track plastic anisotropy and calibrate yield functions for multiphase metals. The virtual laboratory utilizes easily accessible EBSD data and macroscopic flow stress data to construct microstructural representative volume elements and identify micromechanical parameters. The virtual laboratory was validated through mechanical tests on advanced high strength steel sheet. The proposed virtual laboratory can be a versatile tool for exploring and predicting mechanical properties and plastic anisotropy.
SCIENTIFIC REPORTS
(2022)
Article
Engineering, Manufacturing
Guangshan Wu, Fei Chen, Zhenshan Cui, Jiao Zhang
Summary: In this study, a novel approach named periodic undulating compression (PUC) and a multilevel kinking mechanism based on this approach were proposed for the fabrication of large-sized fine-grained materials. Experimental results indicate that PUC can realize multi-pass deformation of large-sized materials and homogeneously accumulate relatively high strain in a single pass deformation. Furthermore, PUC can generate large amounts of kinking bands, which improve the conversion of dislocations to grain boundaries and effectively promote grain refinement.
INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE
(2022)
Article
Engineering, Mechanical
Xiao Tian, Fei Chen, Junnan Jiang, Guangshan Wu, Zhenshan Cui, Dongsheng Qian, Xinghui Han, Bin Wang, Hengqiang Wang, He Wang, Pan Liu
Summary: In this study, a continuous dynamic recrystallization (cDRX) model characterized by micron-scale second phases distributed along grain boundaries was developed using an internal state variable plasticity-based approach. This model accurately calculates the evolution of dislocation density and subgrain orientations near grain boundaries and second phases, and is in good agreement with experimental results.
INTERNATIONAL JOURNAL OF PLASTICITY
(2022)
Article
Engineering, Mechanical
Fei Chen, Xiao Tian, Guangshan Wu, Huajia Zhu, Hengan Ou, Zhenshan Cui
Summary: In this study, a novel mesoscale MCA-cDRX model was constructed to investigate the evolution of microstructures and mechanical response during the hot working of AA7075 aluminum alloy. The analysis shows that the initial matrix characteristics have a significant impact on the cDRX mechanism, and the subgrain size is dependent on the Zener-Hollomon parameter.
INTERNATIONAL JOURNAL OF PLASTICITY
(2022)
Article
Engineering, Mechanical
Yu Tian, Fei Chen, Zhenshan Cui, Xiao Tian
Summary: Investigated the effects of atomic size misfit on edge dislocation mobility in random solid solution alloys. Found that the mobility of dislocation is size misfit-dependent only when it is larger than a critical value. Established a phenomenological dislocation mobility model containing the atomic size misfit and temperature.
INTERNATIONAL JOURNAL OF PLASTICITY
(2023)
Article
Chemistry, Applied
Dongdong Ge, Yun Zhang, Zhenshan Cui, Guilong Wang, Jun Liu, Xiaomeng Lv
Summary: Metal oxides, such as iron oxide/graphene oxide nanohybrids, have gained significant attention due to their low cost and environmental friendliness. In this study, Fe3O4/GO nanohybrids were used to modify a PU sponge, resulting in a superhydrophobic and oleophilic absorption material that could absorb up to 80-170 times its own weight of simulated oily water. The modified sponge also exhibited outstanding recyclability and weak magnetic properties, making it a promising material for dealing with oil spills and chemical leakage.
JOURNAL OF COATINGS TECHNOLOGY AND RESEARCH
(2023)
Article
Chemistry, Physical
Shuai Xu, Chenxin Gao, Namin Xiao, Haiming Zhang, Zhenshan Cui
Summary: In this study, the microstructure evolution of a near-alpha Ti alloy during the B ->alpha phase transformation was analyzed through thermo-mechanical operations, microstructure characterization, phase reconstruction, and crystal plasticity finite element method (CPFEM) modeling. It was found that the continuous dynamic re-crystallization (cDRX) of the B phase gradually replaces the discontinuous dynamic recrystallization (dDRX) of the alpha phase with increasing temperature or decreasing strain rate. The B phase transforms into the secondary alpha (alpha s) phase with a localized phase-transformed texture during the subsequent cooling process. Additionally, the low-angle grain boundary (LAGB) in the B phase weakens the anisotropic growth of alpha s grains and the preferential variant selection of the B ->alpha phase transformation.
JOURNAL OF ALLOYS AND COMPOUNDS
(2023)
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)
