“…In terms of multi-step temporal prediction, the accumulating error of CNN prediction against ground truth/physics simulation is a known issue 40 . The problem can become even more serious when we predict into far future, i.e.…”
Section: Discussionmentioning
confidence: 99%
“…This is done by using anisotropic surface energy in a physics-based phase field model 49 . To develop a corresponding data-driven substitute, www.nature.com/scientificreports/ one will have to train a multi-input CNN 40,50,51 that takes anisotropic surface energy as additional inputs, since the evolved structure is now conditioned on both the original structure and the surface energy. Consequently, phase-field based spinodal decomposition simulation for different anisotropic surface energies should be performed to provide proper dataset, which allows CNN to correctly learn the relationship between microstructure evolution and anisotropic surface energy.…”
Section: Discussionmentioning
confidence: 99%
“…After dimension reduction through distilling salient features of image, CNN facilitates performing downstream CV tasks by avoiding explicitly dealing with raw pixel-based images. With the distinctive feature extraction and image modeling capability, CNN and its variants have been increasingly applied for microstructure evolution simulation in material science and engineering 40 , 41 . Specifically, microstructures are fed as pixel-based images, and CNN learns the mapping relationship between the original and evolved microstructures.…”
Porous biomaterials design for bone repair is still largely limited to regular structures (e.g. rod-based lattices), due to their easy parameterization and high controllability. The capability of designing stochastic structure can redefine the boundary of our explorable structure–property space for synthesizing next-generation biomaterials. We hereby propose a convolutional neural network (CNN) approach for efficient generation and design of spinodal structure—an intriguing structure with stochastic yet interconnected, smooth, and constant pore channel conducive to bio-transport. Our CNN-based approach simultaneously possesses the tremendous flexibility of physics-based model in generating various spinodal structures (e.g. periodic, anisotropic, gradient, and arbitrarily large ones) and comparable computational efficiency to mathematical approximation model. We thus successfully design spinodal bone structures with target anisotropic elasticity via high-throughput screening, and directly generate large spinodal orthopedic implants with desired gradient porosity. This work significantly advances stochastic biomaterials development by offering an optimal solution to spinodal structure generation and design.
“…In terms of multi-step temporal prediction, the accumulating error of CNN prediction against ground truth/physics simulation is a known issue 40 . The problem can become even more serious when we predict into far future, i.e.…”
Section: Discussionmentioning
confidence: 99%
“…This is done by using anisotropic surface energy in a physics-based phase field model 49 . To develop a corresponding data-driven substitute, www.nature.com/scientificreports/ one will have to train a multi-input CNN 40,50,51 that takes anisotropic surface energy as additional inputs, since the evolved structure is now conditioned on both the original structure and the surface energy. Consequently, phase-field based spinodal decomposition simulation for different anisotropic surface energies should be performed to provide proper dataset, which allows CNN to correctly learn the relationship between microstructure evolution and anisotropic surface energy.…”
Section: Discussionmentioning
confidence: 99%
“…After dimension reduction through distilling salient features of image, CNN facilitates performing downstream CV tasks by avoiding explicitly dealing with raw pixel-based images. With the distinctive feature extraction and image modeling capability, CNN and its variants have been increasingly applied for microstructure evolution simulation in material science and engineering 40 , 41 . Specifically, microstructures are fed as pixel-based images, and CNN learns the mapping relationship between the original and evolved microstructures.…”
Porous biomaterials design for bone repair is still largely limited to regular structures (e.g. rod-based lattices), due to their easy parameterization and high controllability. The capability of designing stochastic structure can redefine the boundary of our explorable structure–property space for synthesizing next-generation biomaterials. We hereby propose a convolutional neural network (CNN) approach for efficient generation and design of spinodal structure—an intriguing structure with stochastic yet interconnected, smooth, and constant pore channel conducive to bio-transport. Our CNN-based approach simultaneously possesses the tremendous flexibility of physics-based model in generating various spinodal structures (e.g. periodic, anisotropic, gradient, and arbitrarily large ones) and comparable computational efficiency to mathematical approximation model. We thus successfully design spinodal bone structures with target anisotropic elasticity via high-throughput screening, and directly generate large spinodal orthopedic implants with desired gradient porosity. This work significantly advances stochastic biomaterials development by offering an optimal solution to spinodal structure generation and design.
“…The process of generating these mathematical representations of material objects is called featurization or feature engineering and it is of critical importance to the quality and interpretability of the models trained using them. This step required the most human intuition and intervention but recent development in automatic featurization of molecular objects using specific types of deep neural networks promises paradigm shifts in this process. − Featurization consists of two steps: descriptor generation and descriptor selection.…”
Electrocatalysts and photocatalysts are key to a sustainable future, generating clean fuels, reducing the impact of global warming, and providing solutions to environmental pollution. Improved processes for catalyst design and a better understanding of electro/ photocatalytic processes are essential for improving catalyst effectiveness. Recent advances in data science and artificial intelligence have great potential to accelerate electrocatalysis and photocatalysis research, particularly the rapid exploration of large materials chemistry spaces through machine learning. Here a comprehensive introduction to, and critical review of, machine learning techniques used in electrocatalysis and photocatalysis research are provided. Sources of electro/photocatalyst data and current approaches to representing these materials by mathematical features are described, the most commonly used machine learning methods summarized, and the quality and utility of electro/photocatalyst models evaluated. Illustrations of how machine learning models are applied to novel electro/ photocatalyst discovery and used to elucidate electrocatalytic or photocatalytic reaction mechanisms are provided. The review offers a guide for materials scientists on the selection of machine learning methods for electrocatalysis and photocatalysis research. The application of machine learning to catalysis science represents a paradigm shift in the way advanced, next-generation catalysts will be designed and synthesized.
“…We show that GNNs can learn loading conditions correlating deformed shape and stress field as well as physical relationships between material’s structure, and stress (strain) and deformation field. While image-based ML models, such as convolutional neural networks, variational autoencoders, and generative adversarial networks have been widely used to predict physical fields in hierarchical composites 53 , perforated structures 54 , additively manufactured microstructures with defects 45 , and heterogenous microstructures 42 , 48 , the current work presents a more flexible and general ML framework for the prediction of deformed shapes, stress and strain fields with GNNs. Figure 1 Schematics of the proposed ML model.…”
Developing accurate yet fast computational tools to simulate complex physical phenomena is a long-standing problem. Recent advances in machine learning have revolutionized the way simulations are approached, shifting from a purely physics- to AI-based paradigm. Although impressive achievements have been reached, efficiently predicting complex physical phenomena in materials and structures remains a challenge. Here, we present an AI-based general framework, implemented through graph neural networks, able to learn complex mechanical behavior of materials from a few hundreds data. Harnessing the natural mesh-to-graph mapping, our deep learning model predicts deformation, stress, and strain fields in various material systems, like fiber and stratified composites, and lattice metamaterials. The model can capture complex nonlinear phenomena, from plasticity to buckling instability, seemingly learning physical relationships between the predicted physical fields. Owing to its flexibility, this graph-based framework aims at connecting materials’ microstructure, base materials’ properties, and boundary conditions to a physical response, opening new avenues towards graph-AI-based surrogate modeling.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
