When Machine Learning Meets 2D Materials: A Review

Advanced Science, Год журнала: 2024, Номер 11(13)

Опубликована: Янв. 26, 2024

Abstract The availability of an ever‐expanding portfolio 2D materials with rich internal degrees freedom (spin, excitonic, valley, sublattice, and layer pseudospin) together the unique ability to tailor heterostructures made by in a precisely chosen stacking sequence relative crystallographic alignments, offers unprecedented platform for realizing design. However, breadth multi‐dimensional parameter space massive data sets involved is emblematic complex, resource‐intensive experimentation, which not only challenges current state art but also renders exhaustive sampling untenable. To this end, machine learning, very powerful data‐driven approach subset artificial intelligence, potential game‐changer, enabling cheaper – yet more efficient alternative traditional computational strategies. It new paradigm autonomous experimentation accelerated discovery machine‐assisted design functional heterostructures. Here, study reviews recent progress such endeavors, highlight various emerging opportunities frontier research area.

Язык: Английский

---

Multiscale computational modeling techniques in study and design of 2D materials: recent advances, challenges, and opportunities

2D Materials, Год журнала: 2024, Номер 11(4), С. 042004 - 042004

Опубликована: Сен. 9, 2024

Abstract This article provides an overview of recent advances, challenges, and opportunities in multiscale computational modeling techniques for study design two-dimensional (2D) materials. We discuss the role understanding structures properties 2D materials, followed by a review various length-scale models aiding their synthesis. present integration including density functional theory, molecular dynamics, phase-field modeling, continuum-based mechanics, machine learning. The focuses on advancements, future prospects tailored emerging Key challenges include accurately capturing intricate behaviors across scales environments. Conversely, lie enhancing predictive capabilities to accelerate materials discovery applications spanning from electronics, photonics, energy storage, catalysis, nanomechanical devices. Through this comprehensive review, our aim is provide roadmap research simulation

Язык: Английский

---

Machine Learning Committee Neural Network Potential Energy Surfaces for Two-Dimensional Metal–Organic Frameworks

The Journal of Physical Chemistry C, Год журнала: 2025, Номер unknown

Опубликована: Янв. 15, 2025

Two-dimensional (2D) layered metal–organic frameworks (MOFs) are gaining attention due to their unique structural and electronic properties with promising applications in compact device fabrication. Long-time large-scale molecular dynamics simulations of these materials can enhance expedite the mapping out structure–property–function relationships for applications. To make such more feasible, herein, we construct a high-dimensional committee neural network potential (CNNP) archetypal 2D MOFs Ni3(HIB)2 Ni3(HITP)2 where HIB = hexaiminobenzene HITP hexaiminotriphenylene. We harness power active learning networks obtain CNNP model by using only hundreds snapshots from ab initio (AIMD) trajectories. The developed allows thousands atoms over extended time scales, which is typically unfeasible AIMD while maintaining accuracy reference data. Our stable MD based on reveal flexible nature studied at room temperature, including puckered layers, as opposed planar ones 0 K structure calculations. Furthermore, our demonstrates transferability between bulk monolayers, well different organic linkers. As first its kind, show that models could be reliable effective approach future studies MOFs.

Язык: Английский

---

Effect of nanopore on mechanical characteristics of indium selenide membrane

Journal of the Brazilian Society of Mechanical Sciences and Engineering, Год журнала: 2025, Номер 47(2)

Опубликована: Янв. 21, 2025

Язык: Английский

---

Machine Learning for Thermal Conductivity Prediction in Graphene/Hexagonal Boron Nitride van der Waals Heterostructures

The Journal of Physical Chemistry C, Год журнала: 2025, Номер unknown

Опубликована: Янв. 23, 2025

Язык: Английский

---

Recent advances in machine learning guided mechanical properties prediction and design of two-dimensional materials

Thin-Walled Structures, Год журнала: 2025, Номер unknown, С. 113261 - 113261

Опубликована: Март 1, 2025

Язык: Английский

---

Recent Progress in the Design and Application of Machine Learning for the Hydrogen Evolution Reaction in Electrocatalysis and Photocatalysis

Materials Today Communications, Год журнала: 2025, Номер unknown, С. 112462 - 112462

Опубликована: Апрель 1, 2025

Язык: Английский

---

Machine learning-assisted interfacial modulation and configuration design of metal matrix composites: A review

Materials Today Communications, Год журнала: 2025, Номер unknown, С. 112504 - 112504

Опубликована: Апрель 1, 2025

Язык: Английский

---

An artificial neural network approach to characterizing the behavior of bioconvective nanofluid model using backpropagation of Levenberg–Marquardt algorithm

International Journal of Modern Physics B, Год журнала: 2024, Номер 39(05)

Опубликована: Сен. 30, 2024

The study of the behavior bioconvective nanofluid model (BC-NFM) was explored using bioconvection properties in computational analysis magnetized flow that convectively heated, which is critical for applications energy systems and biomedical devices. We implemented a backpropagated Levenberg–Marquardt neural network approach (BLMNNA) to enhance prediction accuracy such fluid flows. Using Adams numerical technique, we generated comprehensive dataset eight distinct scenarios by variation thermophoresis parameter, Rayleigh number, Deborah Hartman Prandtl Lewis Schmidt number train test our model. results demonstrate significant improvements efficiency compared traditional solvers. steps training, testing, validating developed BLMNNA are used get desired solutions BC-NFM various instances. worth stochastic established authenticated outputs designed methodology through Adaptation graphs Mean Square Error, regression studies, plots error histogram index state transition. Excellent measurements performance terms MEAN SQUARE ERROR achieved at level 9.76E[Formula: see text], 1.41E[Formula: 1.79E[Formula: 1.22E[Formula: 8.49E[Formula: 7.19E[Formula: 9.72E[Formula: 9.35E[Formula: text] against 69, 73, 96, 76, 237, 86, 120, 33 epochs. connection between proposed reference findings demonstrates validity based on analysis, ranges from E[Formula: all situations. show achieves high accuracy, closely matching outcomes obtained solver. method provides an efficient precise solution complex problems, representing advancement over techniques.

Язык: Английский

---

Templating Effect of MoSe₂ on Crystallization of Polyethylene: A Molecular Dynamics Simulation Study

The Journal of Physical Chemistry C, Год журнала: 2024, Номер 128(5), С. 2147 - 2162

Опубликована: Янв. 26, 2024

In today's world, 2D material-based nanocomposites have become a material system that has an ever-growing technological and scientific importance. Such hybrid synergizes organic molecules inorganic materials renders rich playground for developing functional toward diverse applications in electronic, photovoltaics, nanotribology. The interfaces the materials/polymer are also considered as prototypical to study confinement-induced phase transitions, which requires comprehensive understanding of dynamic static properties on molecular length time scales. fundamental can provide insights into design material/polymer with desired through interface engineering. However, date, our about such heterointerface is still limited due challenges experimental testing theoretical modeling. this study, polyethylene assembly MoSe2 been investigated by conducting dynamics (MD) simulations. An all-atoms model developed simulate guided n-pentacosane alkane chains, surrogate polyethylene, surface MoSe2. It observed crystallize from crystallization front moves rapidly bulk. equilibrium, assembled chains orientationally registered under interplay between conformational entropy polymer adhesive interaction, corrugated substrate. This work demonstrates like be used template create specific bicrystallization orientations designed behavior resulting nanocomposite.

Язык: Английский

---