Search

In recent years, Artificial intelligence (AI) has become ubiquitous, empowering various fields, especially integrating artificial intelligence and traditional science (AI for Science: Artificial intelligence for science), which has attracted widespread attention. In AI for Science, using artificial intelligence algorithms to solve partial differential equations (AI for PDEs: Artificial intelligence for partial differential equations) has become a focal point in computational mechanics. The core of AI for PDEs is the fusion of data and partial differential equations (PDEs), which can solve almost any PDEs. Therefore, this article provides a comprehensive review of the research on AI for PDEs, summarizing the existing algorithms and theories. The article discusses the applications of AI for PDEs in computational mechanics, including solid mechanics, fluid mechanics, and biomechanics. The existing AI for PDEs algorithms include those based on Physics-Informed Neural Networks (PINNs), Deep Energy Methods (DEM), Operator Learning, and Physics-Informed Neural Operator (PINO). AI for PDEs represents a new method of scientific simulation that provides approximate solutions to specific problems using large amounts of data, then fine-tuning according to specific physical laws, avoiding the need to compute from scratch like traditional algorithms. Thus, AI for PDEs is the prototype for future foundation models in computational mechanics, capable of significantly accelerating traditional numerical algorithms.

This study investigates different Scientific Machine Learning (SciML) approaches for the analysis of functionally graded (FG) porous beams and compares them under a new framework. The beam material properties are assumed to vary as an arbitrary continuous function. The methods consider the output of a neural network/operator as an approximation to the displacement fields and derive the equations governing beam behavior based on the continuum formulation. The methods are implemented in the framework and formulated by three approaches: (a) the vector approach leads to a Physics-Informed Neural Network (PINN), (b) the energy approach brings about the Deep Energy Method (DEM), and (c) the data-driven approach, which results in a class of Neural Operator methods. Finally, a neural operator has been trained to predict the response of the porous beam with functionally graded material under any porosity distribution pattern and any arbitrary traction condition. The results are validated with analytical and numerical reference solutions. The data and code accompanying this manuscript will be publicly available at https://github.com/eshaghi-ms/DeepNetBeam.

Thermal management at silicon-diamond interface is critical for advancing high-performance electronic and optoelectronic devices. In this study, we calculate the interfacial thermal conductance between silicon and diamond using machine learning (ML) interatomic potentials trained on density functional theory (DFT) data. Using non-equilibrium molecular dynamics (NEMD) simulations, we compute the interfacial thermal conductance (ITC) for various system sizes. Our results show a closer agreement with experimental data than those obtained using traditional semi-empirical potentials such as Tersoff and Brenner which overestimate ITC by a factor of about 3. In addition, we analyze the frequency-dependent heat transfer spectrum, providing insights into the contributions of different phonon modes to the interfacial thermal conductance. The ML potential accurately captures the phonon dispersion relations and lifetimes, in good agreement with DFT calculations and experimental observations. It is shown that the Tersoff potential predicts higher phonon group velocities and phonon lifetimes compared to the DFT results. Furthermore, it predicts higher interfacial bonding strength, which is consistent with higher interfacial thermal conductance as compared to the ML potential. This study highlights the use of the ML interatomic potential to improve the accuracy and computational efficiency of thermal transport simulations in complex material systems.

AI for partial differential equations (PDEs) has garnered significant attention, particularly with the emergence of Physics-informed neural networks (PINNs). The recent advent of Kolmogorov-Arnold Network (KAN) indicates that there is potential to revisit and enhance the previously MLP-based PINNs. Compared to MLPs, KANs offer interpretability and require fewer parameters. PDEs can be described in various forms, such as strong form, energy form, and inverse form. While mathematically equivalent, these forms are not computationally equivalent, making the exploration of different PDE formulations significant in computational physics. Thus, we propose different PDE forms based on KAN instead of MLP, termed Kolmogorov-Arnold-Informed Neural Network (KINN) for solving forward and inverse problems. We systematically compare MLP and KAN in various numerical examples of PDEs, including multi-scale, singularity, stress concentration, nonlinear hyperelasticity, heterogeneous, and complex geometry problems. Our results demonstrate that KINN significantly outperforms MLP regarding accuracy and convergence speed for numerous PDEs in computational solid mechanics, except for the complex geometry problem. This highlights KINN's potential for more efficient and accurate PDE solutions in AI for PDEs.

Flexoelectricity shows promising applications for self-powered devices with its increased power density. This paper presents a second-order computational homogenization strategy for flexoelectric composite. The macro-micro scale transition, Hill-Mandel energy condition, periodic boundary conditions, and macroscopic constitutive tangents for the two-scale electromechanical coupling are investigated and considered in the homogenization formulation. The macrostructure and microstructure are discretized using $C^1$ triangular finite elements. The second-order multiscale solution scheme is implemented using ABAQUS with user subroutines. Finally, we present numerical examples including parametric analysis of a square plate with holes and the design of piezoelectric materials made of non-piezoelectric materials to demonstrate the numerical implementation and the size-dependent effects of flexoelectricity.

Many kinds of two-dimensional (2D) van der Waals (vdW) have been demonstrated to exhibit electromechanical coupling effects, which makes them promising candidates for next-generation devices, such as piezotronics and nanogenerators. Recently, flexoelectricity was found to account for the out-of-plane electromechanical coupling in many 2D transition metal dichalcogenides (TMDs) who only exhibit in-plane piezoelectricity. However, low dimensional vdW three-dimensional (3D) topological insulators (TIs) have been overlooked regarding their electromechanical properties. In this study, for the first time, we experimentally investigate the electromechanical coupling of low dimensional 3D TIs with a centrosymmetric crystal structure, where a binary compound, bismuth selenite (Bi2Se3), is taken as an example. The results of piezoresponse force microscope (PFM) tests on the Bi2Se3 nanoflakes show that the material exhibits both out-of-plane and in-plane electromechanical responses. The Bi2Se3 nanoflake with a thickness of 37 nm possesses an effective out-of-plane piezoelectric coefficient of ~0.65 pm V-1. With careful analyses, the electromechanical responses are verified to arise from the converse flexoelectricity. The measured effective out-of-plane piezoelectric coefficient is mainly contributed by flexoelectric coefficient, {\mu}_39, which is estimated to be approximately 0.13 nC m-1. However, it is rather difficult to obtain the in-plane component of the flexoelectric tensor from the in-plane PFM measurements since the direction of the in-plane stress is always not normal to the AFM cantilever axis. The results provide useful guidance for understanding the flexoelectric effect of low dimensional vdW materials with centrosymmetric crystal structures. Moreover, the work can pave to way to explore the electromechanical devices based on the flexoelectricity of vdW TIs., Comment: 6 figures

Most recently the formation of boron monoxide (BO) in the two-dimensional (2D) form has been confirmed experimentally (J. Am. Chem. Soc. 2023, 145, 14660). Motivated by the aforementioned finding, herein we theoretically explore the key physical properties of the single-layer and suspended BO. Density functional theory (DFT) results reveal that BO monolayer yields a large indirect band gap of 3.78 (2.18) eV on the basis of HSE06(PBE) functional. Ab-initio molecular dynamics results reveal the remarkable thermal stability of the BO monolayer at 1000 K. The thermal and mechanical properties at room temperature are furthermore investigated using a machine learning interatomic potential (MLIP). The developed MLIP-based model close to the ground state could very precisely reproduce the DFT predictions for the mechanical properties of the BO monolayer. The elastic modulus, tensile strength and lattice thermal conductivity of the BO monolayer at room temperature are predicted to be 107 GPa, 25 GPa and 5.6 W/mK, respectively. At the room temperature the BO monolayer is noticeably predicted to yield an ultrahigh negative thermal expansion coefficient, by almost 17 folds larger than that of the single-layer graphene. The presented results reveal the large indirect electronic band gap, decent thermal and dynamical stability, anomalously low elastic modulus to tensile strength ratio, ultrahigh negative thermal expansion coefficients and low lattice thermal conductivity of the BO monolayer.

Triboelectric nanogenerators (TENGs) are promising self-powering supplies for a diverse range of intelligent sensing and monitoring devices, especially due to their capability of harvesting electric energy from low frequency and small-scale mechanical motions. Inspired by the fact that contact-separation mode TENGs with small contact areas harvest high electrical outputs due to fringing effect, this study employed discontinuity on the dielectric side of contact-separation mode TENGs to promote fringing electric fields for the enhancement of electrical outputs. The results reveal that the TENGs with more discontinuities show higher overall electric performance. Compared to pristine TENGs, the TENGs with cross discontinuities increased the surface charge by 50% and the power density by 114%. However, one should avoid generating discontinuities on tribonegative side of TENGs using metal blade within a positive-ion atmosphere due to the neutralization through electrically conductive metal blade. The computational simulation validated that the TENGs with discontinuities obtained higher electrical outputs, and further investigated the effect of discontinuity gap size and array distance on TENGs performance. This study has provided a promising method for the future design of TENGs using discontinuous structures., Comment: 23 pages, 8 figures

Among exciting recent advances in the field of two-dimensional (2D) materials, the successful fabrications of the C60 fullerene networks has been a particularly inspiring accomplishment. Motivated by the recent achievements, herein we explore the stability and physical properties of novel hexagonal boron-carbon fullerene 2D heterostructures, on the basis of already synthesized B40 and C36 fullerenes. By performing extensive structural minimizations of diverse atomic configurations using the density functional theory method, for the first time, we could successfully detect thermally and dynamically stable boron-carbon fullerene 2D heterostructures. Density functional theory results confirm that the herein predicted 2D networks exhibit very identical semiconducting electronic natures with topological flat bands. Using the machine learning interatomic potentials, we also investigated the mechanical and thermal transport properties. Despite of different bonding architectures, the room temperature lattice thermal conductivity of the predicted nanoporous fullerene heterostructures was found to range between 4 to 10 W/mK. Boron-carbon fullerene heterostructures are predicted to show anisotropic but also remarkable mechanical properties, with tensile strengths and elastic modulus over 8 and 70 GPa, respectively. This study introduces the possibility of developing a novel class of 2D heterostructures based on the fullerene cages, with attractive electronic, thermal and mechanical features.

Phase field model (PFM) is an efficient fracture modeling method and has high potential for hydraulic fracturing (HF). However, the current PFMs in HF do not consider well the effect of in-situ stress field and the numerical examples of porous media with stress boundary conditions were rarely presented. The main reason is that if the remote stress is applied on the boundaries of the calculation domain, there will be relatively large deformation induced on these stress boundaries, which is not consistent with the engineering observations. To eliminate this limitation, this paper proposes a new phase field method to describe quasi-static hydraulic fracture propagation in porous media subjected to stress boundary conditions, and the new method is more in line with engineering practice. A new energy functional, which considers the effect of initial in-situ stress field, is established and then it is used to achieve the governing equations for the displacement and phase fields through the variational approach. Biot poroelasticity theory is used to couple the fluid pressure field and the displacement field while the phase field is used for determining the fluid properties from the intact domain to the fully broken domain. In addition, we present several 2D and 3D examples to show the effects of in-situ stress on hydraulic fracture propagation. The numerical examples indicate that under stress boundary condition our approach obtains correct displacement distribution and it is capable of capturing complex hydraulic fracture growth patterns.

The paper presents an assumed strain formulation over polygonal meshes to accurately evaluate the strain fields in nonlocal damage models. An assume strained technique based on the Hu-Washizu variational principle is employed to generate a new strain approximation instead of direct derivation from the basis functions and the displacement fields. The underlying idea embedded in arbitrary finite polygons is named as Polytopal composite finite elements (PCFEM). The PCFEM is accordingly applied within the framework of the nonlocal model of continuum damage mechanics to enhance the description of damage behaviours in which highly localized deformations must be captured accurately. This application is helpful to reduce the mesh-sensitivity and elaborate the process-zone of damage models. Several numerical examples are designed for various cases of fracture to discuss and validate the computational capability of the present method through comparison with published numerical results and experimental data from the literature.

A phase field model for fluid-driven dynamic crack propagation in poroelastic media is proposed. Therefore, classical Biot poroelasticity theory is applied in the porous medium while arbitrary crack growth is naturally captured by the phase field model. We also account for the transition of the fluid property from the intact medium to the fully broken one by employing indicator functions. We employ a staggered scheme and implement our approach into the software package COMSOL Multiphysics. Our approach is first verified through three classical benchmark problems which are compared to analytical solutions for dynamic consolidation and pressure distribution in a single crack and in a specimen with two sets of joints. Subsequently, we present several 2D and 3D examples of dynamic crack branching and their interaction with pre-existing natural fractures. All presented examples demonstrate the capability of the proposed approach of handling dynamic crack propagation, branching and coalescence of fluid-driven fracture.

This paper proposes a phase field model (PFM) for describing hydraulic fracture propagation in transversely isotopic media. The coupling between the fluid flow and displacement fields is established according to the classical Biot poroelasticity theory while the phase field model characterizes the fracture behavior. The proposed method uses a transversely isotropic constitutive relationship between stress and strain as well as anisotropy in fracture toughness and permeability. An additional pressure-related term and an anisotropic fracture toughness tensor are added in the energy functional, which is then used to obtain the governing equations of strong form via the variational approach. In addition, the phase field is used to construct indicator functions that transit the fluid property from the intact domain to the fully fractured one. Moreover, the proposed PFM is implemented using the finite element method where a staggered scheme is applied and the displacement and fluid pressure are monolithically solved in a staggered step. Afterwards, two examples are tested to initially verify the proposed PFM: a transversely isotropic single-edge-notched square plate subjected to tension and an isotropic porous medium subjected to internal fluid pressure. Finally, numerical examples of 2D and 3D transversely isotropic media with one or two interior notches subjected to internal fluid pressure are presented to further prove the capability of the proposed PFM in 2D and 3D problems.

The Brazilian splitting test is a widely used testing procedure for characterizing the tensile strength of natural rock or rock-like material due to the fact. However, the results of Brazilian tests on specimens with naturally existing voids and inclusions are strongly influenced by size effects and boundary conditions, while numerical modeling can assist in explaining and understanding the mechanisms. On the other hand, the potential of utilizing Brazilian test to characterize inhomogeneous deformation of rock samples with voids and inclusions of dissimilar materials still awaits to be explored. In the present study, fracture mechanisms in Brazilian discs with circular voids and filled inclusions are investigated by using the phase field model (PFM). The PFM is implemented within the framework of finite element method to study the influence of diameter, eccentricity, and quantity of the voids and inclusions on the fracture patterns and stress-strain curves. The phase field simulations can reproduce previous experimental phenomena and furthermore it deepens the understanding of the influence of inclusion and voids on the fracture pattern, overall strength and deformation behavior of inhomogeneous rock. The findings in the study highlight the potential of characterizing inhomogeneous rock through combining Brazilian tests and numerical modeling.

Compressive-shear fracture is commonly observed in rock-like materials. However, this fracture type cannot be captured by current phase field models (PFMs), which have been proven an effective tool for modeling fracture initiation, propagation, coalescence, and branching in solids. The existing PFMs also cannot describe the influence of cohesion and internal friction angle on load-displacement curve during compression tests. Therefore, to develop a new phase field model that can simulate well compressive-shear fractures in rock-like materials, we construct a new driving force in the evolution equation of phase field. Strain spectral decomposition is applied and only the compressive part of the strain is used in the new driving force with consideration of the influence of cohesion and internal friction angle. For ease of implementation, a hybrid formulation is established for the phase field modeling. Then, we test the brittle compressive-shear fractures in uniaxial compression tests on intact rock-like specimens as well as those with a single or two parallel inclined flaws. All numerical results are in good agreement with the experimental observation, validating the feasibility and practicability of the proposed PFM for simulating brittle compressive-shear fractures.

In the hydraulic fracturing of natural rocks, understanding and predicting crack penetrations into the neighboring layers is crucial and relevant in terms of cost-efficiency in engineering and environmental protection. This study constitutes a phase field framework to examine hydraulic fracture propagation in naturally-layered porous media. Biot's poroelasticity theory is used to couple the displacement and flow field, while a phase field method helps characterize fracture growth behavior. Additional fracture criteria are not required and fracture propagation is governed by the equation of phase field evolution. Thus, penetration criteria are not required when hydraulic fractures reach the material interfaces. The phase field method is implemented within a staggered scheme that sequentially solves the displacement, phase field, and fluid pressure. We consider the soft-to-stiff and the stiff-to-soft configurations, where the layer interface exhibits different inclination angles $\theta$. Penetration, singly-deflected, and doubly-deflected fracture scenarios can be predicted by our simulations. In the soft-to-stiff configuration, $\theta=0^\circ$ exhibits penetration or symmetrical doubly-deflected scenarios, and $\theta=15^\circ$ exhibits singly-deflected or asymmetric doubly-deflected scenarios. Only the singly-deflected scenario is obtained for $\theta=30^\circ$. In the stiff-to-soft configuration, only the penetration scenario is obtained with widening fractures when hydraulic fractures penetrate into the soft layer.

This paper studies elasto-plastic large deformation behavior of thin shell structures using the isogeometric computational approach with the main focus on the efficiency in modelling the multi-patches and arbitrary material formulations. In terms of modelling, we employ the bending strip method to connect the patches in the structure. The incorporation of bending strips allows to eliminate the strict demand of the C1 continuity condition, which is postulated in the Kirchhoff-Love theory for thin shell, and therefore it enables us to use the standard multi-patch structure even with C0 continuity along the patch boundaries. Furthermore, arbitrary nonlinear material models such as hyperelasticity and finite strain plasticity are embedded in the shell formulation, from which a unified thin shell formulation can be achieved. In terms of analysis, the Bezier decomposition concept is used to retain the local support of the traditional finite element. The performance of the presented approach is verified through several numerical benchmarks.

A phase field model for ductile fracture considering Hencky strain and finite J2 plasticity is presented using the nonlocal operator method. A variational derivation of J2 plasticity at finite strain with a phase field model is performed. The method includes a logarithmic strain tensor and an exponential mapping in the plasticity evolution. A spectral decomposition based algorithm for computing the first and second order derivatives of the composite matrix function is implemented. A consistent tangential stiffness matrix is derived and used in Newton-Raphson iterations. Several numerical examples are performed to validate the method, including notched single-edged plates with brittle fracture or ductile fracture and necking of a bar with/without phase field model.

This paper is concerned with the energy decomposition of various nonlocal models, including elasticity, thin plates, and gradient elasticity, to arrive at bond-based nonlocal models in which the bond force depends only on the deformation of a single bond. By assuming an appropriate form of bond force and using energy equivalence between local and nonlocal models, several very concise bond-based models are derived. We also revisit the nonlocal operator methods and study the simplified form of second-order NOM in the symmetric support domain. A bent-bond consisting of three points is proposed to describe the curvature and moment. To model the damage, a rule based on Griffith theory for the critical normal strain of the bond is proposed in analogy to the phase field model, which can be applied individually to each bond and provides strain localization. With this rule, the crack direction can be automatically predicted by simply cutting the bond, giving comparable results to the phase field method. At the same time, a damage rule for critical shear strains in shear fractures is proposed. Furthermore, an incremental form of the plasticity model for bond reaction force is derived. Several numerical examples are presented to further validate the nonlocal bond-based models.

Recent experimental advances [Liu \textit{et al., npj 2D Materials and Applications}, 2019, \textbf{3}, 23] propose the design of graphene nanoribbon spring (GNRS) to substantially enhance the stretchability of pristine graphene. GNRS is a periodic undulating graphene nanoribbon, where undulations are of sinus or half-circles or horseshoe shapes. Besides those, GNRS geometry depends on design parameters, like pitch's length and amplitude, thickness and joining angle. Because of the fact that parametric influence on the resulting physical properties are expensive and complicated to be examined experimentally, we explore the mechanical, thermal and electromechanical properties of GNRS using molecular dynamics simulations. Our results demonstrate that horseshoe shape design of GNRS (GNRH) can distinctly outperform the graphene kirigami design concerning the stretchability. The thermal conductivity of GNRS were also examined by developing a multiscale modeling, which suggests that the thermal transport along these nanostructures can be effectively tuned. We found that however, the tensile stretching of GNRS and GNRH does not yield any piezoelectric polarization. The bending induced hybridization change results in a flexoelectric polarization, where the corresponding flexoelectric coefficient is $25\%$ higher than graphene. Our results provide a comprehensive vision to the critical physical properties of GNRS and may help to employ the outstanding physics of the graphene to design novel stretchable nanodevices.

Flexoelectricity is a form of electromechanical coupling that has recently emerged because, unlike piezoelectricity, it is theoretically possible in any dielectric material. Two-dimensional (2D) materials have also garnered significant interest because of their unusual electromechanical properties and high flexibility, but the intrinsic flexoelectric properties of these materials remain unresolved. In this work, using atomistic modeling accounting for charge-dipole interactions, we report the intrinsic flexoelectric constants for a range of two-dimensional materials, including graphene allotropes, nitrides, graphene analogs of group-IV elements, and the transition metal dichalcogenides (TMDCs). We accomplish this through a proposed mechanical bending scheme that eliminates the piezoelectric contribution to the total polarization, which enables us to directly measure the flexoelectric constants. While flat 2D materials like graphene have low flexoelectric constants due to weak $\pi-\sigma$ interactions, buckling is found to increase the flexoelectric constants in monolayer group-IV elements. Finally, due to significantly enhanced charge transfer coupled with structural asymmetry due to bending, the TMDCs are found to have the largest flexoelectric constants, including MoS$_{2}$ having a flexoelectric constant ten times larger than graphene.

Due to their combination of mechanical stiffness and flexibility, two-dimensional (2D) materials have received significant interest as potential electromechanical materials. Flexoelectricity is an electromechanical coupling between strain gradient and polarization. Unlike piezoelectricity, which exists only in non-centrosymmetric materials, flexoelectricity theoretically exists in all dielectric materials. However, most work on the electromechanical energy conversion potential of 2D materials has focused on their piezoelectric, and not flexoelectric behavior and properties. In the present work, we demonstrate that the intrinsic structural asymmetry present in monolayer Janus transition metal dichalcogenides (TMDCs) enables significant flexoelectric properties. We report these flexoelectric properties using a recently developed charge-dipole model that couples with classical molecular dynamics simulations. By employing a prescribed bending deformation, we directly calculate the flexoelectric constants while eliminating the piezoelectric contribution to the polarization. We find that the flexoelectric response of a Janus TMDC is positively correlated to its initial degree of asymmetry, which contributes to stronger $\sigma-\sigma$ interactions as the initial degree of asymmetry rises. In addition, the high transfer of charge across atoms in Janus TMDCs leads to larger electric fields due to $\pi-\sigma$ coupling. These enhanced $\sigma-\sigma$ and $\pi-\sigma$ interactions are found to cause the flexoelectric coefficients of the Janus TMDCs to be several times higher than traditional TMDCs such as MoS$_{2}$, whose flexoelectric constant is already ten times larger than graphene.

Modeling fracture is computationally expensive even in computational simulations of two-dimensional problems. Hence, scaling up the available approaches to be directly applied to large components or systems crucial for real applications become challenging. In this work. we propose domain decomposition framework for the variational physics-informed neural networks to accurately approximate the crack path defined using the phase field approach. We show that coupling domain decomposition and adaptive refinement schemes permits to focus the numerical effort where it is most needed: around the zones where crack propagates. No a priori knowledge of the damage pattern is required. The ability to use numerous deep or shallow neural networks in the smaller subdomains gives the proposed method the ability to be parallelized. Additionally, the framework is integrated with adaptive non-linear activation functions which enhance the learning ability of the networks, and results in faster convergence. The efficiency of the proposed approach is demonstrated numerically with three examples relevant to engineering fracture mechanics. Upon the acceptance of the manuscript, all the codes associated with the manuscript will be made available on Github., Comment: 9 Pages, 8 Figures

In an outstanding experimental advance in the field of two-dimensional nanomaterials, cuprous iodide (CuI) and silver iodide (AgI) monolayers have been grown via a novel graphene encapsulation synthesis approach [Adv.Mater.2022, 34, 2106922]. Inspired by this accomplishment, we conduct first-principles calculations to investigate the elastic, phononic thermal transport, electronic, and optical properties of the native CuI and AgI and Janus Cu2BrI and Ag2BrI monolayers. Electronic and excitonic optical properties are elaborately studied using the many-body perturbation theory on the basis of GW approximation. Our results indicate that these novel systems are stable but with soft elastic modulus and ultralow lattice thermal conductivity. It is also shown that the studied monolayers are wide-gap semiconductors with exciton binding energies close to 1 eV. The effects of mechanical straining and electric field on the resulting electronic and optical properties are also analyzed. The presented first-principles results provide a deep understanding of the stability, phononic transport, and tunable optoelectronic properties of the native CuI and AgI and Janus Cu2BrI and Ag2BrI monolayers, which can serve as a guide for the oncoming studies., Comment: 10 pages, 8 figures

Mechanical stability of the ZnIn2X4 monolayers. The ZnIn2S4 and ZnIn2Se4 are semiconductors with direct band gaps of 3.94 and 2.77 eV, respectively whereas the ZnIn2Te4 shows an indirect band gap of 1.84 eV at the G0W0 level. The optical properties achieved from the solution of the Bethe-Salpeter equation predict the exciton binding energy of the ZnIn2S4, ZnIn2Se4, and ZnIn2Te4 monolayers to be 0.51, 0.41, and 0.34 eV, respectively, suggesting the high stability of the excitonic states against thermal dissociation. Using the iterative solutions of the Boltzmann transport equation accelerated by machine learning interatomic potentials, the room-temperature lattice thermal conductivity of the ZnIn2S4, ZnIn2Se4, and ZnIn2Te4 monolayers is predicted to be remarkably low as 5.8, 2.0, and 0.4 W/mK, respectively. Due to the low lattice thermal conductivity, high thermopower, and large figure of merit, we propose the ZnIn2Se4 and ZnIn2Te4 monolayers as promising candidates for thermoelectric energy conversion systems. This study provides an extensive vision concerning the intrinsic physical properties of the ZnIn2X4 nanosheets and highlights their characteristics for energy conversion and optoelectronics applications., Comment: 11 pages, 6 figures

Deep learning has shown successful application in visual recognition and certain artificial intelligence tasks. Deep learning is also considered as a powerful tool with high flexibility to approximate functions. In the present work, functions with desired properties are devised to approximate the solutions of PDEs. Our approach is based on a posteriori error estimation in which the adjoint problem is solved for the error localization to formulate an error estimator within the framework of neural network. An efficient and easy to implement algorithm is developed to obtain a posteriori error estimate for multiple goal functionals by employing the dual-weighted residual approach, which is followed by the computation of both primal and adjoint solutions using the neural network. The present study shows that such a data-driven model based learning has superior approximation of quantities of interest even with relatively less training data. The novel algorithmic developments are substantiated with numerical test examples. The advantages of using deep neural network over the shallow neural network are demonstrated and the convergence enhancing techniques are also presented