MatGAN uses GAN to efficiently generate new inorganic materials.
problem Efficiently searching the vast chemical design space for new materials.
method Generative adversarial network (GAN) trained on ICSD materials database.
result 92.53% novelty and 84.5% chemically valid samples generated.
Generative models accelerate chemical design from properties to structures.
problem Expensive and incremental strategies for optimizing chemical properties.
method Review of current deep generative models and their application to molecular systems.
result Generative models can expedite the design of novel useful compounds.
Hybrid model predicts product designs from target characteristics.
problem Designing new products with unknown target characteristics is expensive and time-consuming.
method Formulated as conditional density estimation, solved with a deep hybrid generative-discriminative model.
result Predicts optimal design parameters for any target in a single step.
A VAE model predicts material properties and microstructures.
problem Building forward and inverse structure-property linkages in materials science.
method Combines VAE with regression, using a two-level prior and multi-modal Gaussian mixture.
result The model achieves accurate forward and inverse predictions of material properties and microstructures.
Paper proposes active learning for structured output design, improving Gaussian process model predictions.
problem Finding optimal input parameters for achieving desired structured outputs.
method Developed new acquisition functions to minimize prediction error of Gaussian process model, incorporating output correlations.
result Effectiveness demonstrated in synthetic and real data experiments, including materials informatics.
Paper optimizes material microstructures with limited data using probabilistic methods.
problem Optimizing material properties with uncertain process-structure-property links.
method Flexible probabilistic formulation, data-driven surrogate, active learning.
result Significant improvement in accuracy with small training data.
The paper tackles inverse uncertainty quantification in neutron noise analysis.
problem Uncertainty in estimating material properties from noisy neutron correlation measurements.
method Surrogate models and inverse uncertainty quantification to account for measurement error and model bias.
result Improved prediction of neutron correlations and quantification of uncertainties.
Machine learning speeds up RIS design for efficient RF components.
problem Designing reconfigurable intelligent surfaces (RIS) for efficient RF components is time-consuming and resource-intensive.
method Machine/deep learning techniques are used to reduce the computational cost and time of RIS inverse design.
result Machine learning techniques significantly reduce the time and computational cost of RIS design.
Efficient deep learning on exascale supercomputers solves materials imaging inverse problems.
problem Solving scientific inverse problems in materials imaging using deep learning.
method Novel communication strategies in synchronous distributed deep learning, including decentralized gradient reduction and computational graph-aware grouping.
result Achieved near-linear scaling of distributed training up to 27,600 GPUs on Summit, reaching 2.15(4) EFLOPS16. Deep learning speeds up material property quantification using stress waves.
problem Quantifying material properties from stress waves in complex media.
method Surrogate deep learning FWI scheme trained on random sampled properties and local minima.
result Demonstrates feasibility of deep learning for high-accuracy material property estimation.
Paper proposes a new method for designing materials using deep learning.
problem Designing high-performance material distributions from given distributions.
method Iterative process of selecting, generating, and merging material distributions using a deep generative model.
result The method improves material performance through iterative refinement.
Calibrating materials to engineering targets improves wind turbine design.
problem Separate material and mechanical design processes lead to uncertainty.
method Repurpose calibration techniques to integrate material and mechanical design.
result Materials can be designed with specific engineering targets in mind.
SELFIES solves molecular string representation weaknesses for material design.
problem Weaknesses in SMILES for representing valid molecules in material design.
method Introducing SELFIES, a 100% robust string-based molecular representation.
result SELFIES strings correspond to valid molecules, allowing arbitrary machine learning applications.
Deep learning model reconstructs material microstructures from feature representations.
problem Reconstructing complex material microstructures accurately and efficiently.
method Convolutional deep belief network for automated feature learning and dimension reduction.
result Material reconstructions preserve microstructural features and material properties.
New method integrates latent variables for Bayesian Optimization of materials with both qualitative and quantitative factors.
problem Bayesian Optimization for materials design with mixed qualitative and quantitative variables.
method Integrates latent variables for mixed-variable Gaussian process modeling within the Bayesian Optimization framework.
result LVGP provides superior modeling accuracy compared to existing methods for mixed-variable problems.
Bayesian Optimization framework tackles materials design challenges with mixed variables.
problem Challenges in materials design due to mixed qualitative and quantitative variables, limited data, and high simulation costs.
method Data-centric, mixed-variable Bayesian Optimization framework using Latent Variable Gaussian Process (LVGP) and Expected Improvement acquisition function.
result Locates optimal design for insulating polymer nanocomposites efficiently.
IH-GAN models cellular structures accurately and improves structural performance.
problem Optimizing variable-density cellular structures with multiscale design challenges.
method Conditional deep generative model (IH-GAN) for property-to-geometry mapping using implicit function parameterization.
result Generates unit cells with high accuracy and improves structural performance.
Framework uses diffusion models to infer material properties from noisy mechanical measurements.
problem Inference of spatially varying material properties from noisy mechanical responses.
method Conditional score-based diffusion models approximating the score function of a conditional distribution.
result Framework can efficiently solve large-scale physics-based inverse problems.
Bayesian optimization reduces materials design costs by 10x.
problem Expensive materials design search space with mixed variables.
method Uncertainty-aware machine learning models for mixed numerical and categorical variables.
result Frequentist and Bayesian models perform differently in mixed-variable BO.
We introduce Bayesian optimization, a technique developed for optimizing time-consuming engineering simulations and for fitting machine learning models on large datasets. Bayesian optimization guides the choice of experiments during materials design and discovery to find good material designs in as few experiments as p…
Efficient DL reduces EM nanostructure design complexity.
problem Designing and optimizing electromagnetic nanostructures efficiently.
method Autoencoder-based dimensionality reduction for one-to-one problem reformulation.
result Significant reduction in computational complexity for EM nanostructures.
Unified machine learning predicts molecular wavefunctions efficiently.
problem Lack of explicit electronic structure in machine learning models for chemistry.
method Deep neural network for quantum mechanical wavefunction prediction.
result Efficient prediction of molecular wavefunctions with full electronic structure access.
Unified framework for forward and inverse PDE problems in multiphase media.
problem Non-differentiable inverse problems in discrete-valued material fields.
method GenPANIS: Latent-variable generative framework preserving discrete microstructures.
result Unified bidirectional inference with minimal labeled pairs and physics-aware decoder.
DECT-MULTRA improves material decomposition in CT images.
problem Noise and artifacts degrade material images in DECT imaging.
method Combines PWLS estimation with MULTRA model for efficient clustering and sparse coding.
result Superior material image quality and decomposition accuracy compared to other methods.
Deep neural networks predict material properties from images.
problem Tailoring material properties for advanced turbomachinery.
method Developed deep convolutional neural networks to predict processing-structure-property relations.
result Models accurately predict material properties from images, surpassing current methods.
New method for mixed-variable GSA improves material design efficiency.
problem Designing materials with both quantitative and qualitative variables.
method Integrates LVGP with Sobol' analysis for mixed-variable GSA.
result Accelerates exploration of novel MOF candidates in combinatorial design spaces.
WNVI solves inverse problems without forward models using neural networks.
problem Solving high-dimensional Bayesian inverse problems based on PDEs.
method WNVI uses weighted residuals and SVI with neural networks to infer state variables and unknowns.
result WNVI is more accurate and efficient than traditional methods and handles ill-posed problems.
A framework uses deep generative modeling to design metamaterials efficiently.
problem Designing metamaterials with complex properties is challenging due to high-dimensional design space and high computational cost.
method A variational autoencoder (VAE) and a regressor are trained on a large database to map microstructures to a latent space, enabling interpolation and manipulation of microstructures.
result The latent space provides a distance metric for shape similarity and encoding meaningful patterns of variation, enabling efficient design of microstructures and multiscale systems.
Paper tackles goal-directed generation of discrete structures using conditional generative models.
problem Challenges in generating structured discrete data, especially for problems like program synthesis and materials design.
method Investigates conditional generative models to directly model the distribution of discrete structures given properties of interest. Introduces a novel approach to optimize a reinforcement learning objective.
result Improvements over maximum likelihood estimation and other baselines in generating molecules and identifying short python expressions.
Researchers use active subspaces to quantify uncertainty in deep generative models for molecular design.
problem Uncertainty quantification in deep generative models for molecular design due to high parameter space.
method Leveraging active subspaces to approximate posterior distribution over low-dimensional parameters.
result The proposed UQ scheme effectively estimates epistemic uncertainty in high-dimensional parameter space without altering model architecture.
Accelerates materials optimization with data-driven models.
problem Optimizing materials with high-dimensional parameters.
method Data-driven experimental design with uncertainty analysis.
result Optimal candidate found with 3x fewer measurements.
Study uses Bayesian Optimization to analyze noise effects in materials research.
problem Optimizing materials with many variables and experimental noise.
method Batch Bayesian Optimization with synthetic data analysis.
result Noise sensitivity varies by problem landscape, impacting optimization outcomes.
Gryffin optimizes categorical variables in materials design, leveraging expert knowledge.
problem Optimizing categorical variables in complex design choices like molecule selection.
method Bayesian optimization with smooth approximations to categorical distributions, incorporating expert knowledge.
result Gryffin accelerates discovery of promising molecules and materials, highlighting relevant correlations.
RG-VFM extends VFM to curved manifolds for better material and protein design.
problem Designing materials and proteins on curved manifolds.
method Riemannian Gaussian Variational Flow Matching (RG-VFM) for generative modeling on manifolds.
result RG-VFM more effectively captures manifold structure and improves performance.
Machine learning optimizes polymer fiber synthesis.
problem Complex material synthesis requires impractical experimentation.
method Bayesian optimisation using machine learning.
result Efficiently directs synthesis to achieve material and process objectives.
We enhance autonomous materials research with problem-aware models.
problem Complex decision-making in autonomous materials.
method Bayesian framework, machine learning, physics-based models, operational considerations.
result Improved models reflect problem-specific structure.
Analyzes properties of stiffness tensors for elastic wave imaging.
problem Characterizing stiffness tensor fields for elastic wave imaging.
method Finsler-geometric methods applied to anisotropic stiffness tensor fields.
result Conditions for Finsler-geometric methods to be applicable.
Neural network solves inverse problem in multiscale mechanics.
problem Identifying elastic properties of random materials.
method Artificial neural networks trained on processed databases.
result Robust identification method validated with synthetic and real data.
Improves material discovery through better model evaluation metrics.
problem Standard error metrics mislead in material discovery.
method Introduces Pareto shell-scope error for model evaluation.
result Novel diagnostic tools and insights for acquisition function design.
Automates hair color digitization using imaging and deep learning.
problem Challenges in capturing and rendering realistic hair colors.
method Combines imaging, path-tracing, and self-supervised machine learning.
result Accurately captures and renders hair color with synthetic images.
Paper proposes a deep Gaussian process for predicting formation energy of inorganic compounds.
problem High computational cost of quantum chemistry calculations for material design.
method Develops a deep Gaussian process emulator for quantum calculations using a novel molecular descriptor.
result Demonstrates that the approach can be implemented using a small dataset for prediction of formation energy.
New Bayesian optimization models for efficient material screening.
problem Efficiently screening materials with expensive and cheap tests.
method Flexible multi-test Bayesian optimization models with complex relationships.
result Demonstrated power on synthetic and real data.
The paper mostly collects material on generic rank of A--modules with respect to differential geometric applications. Our research was motivated by geometry of A--structures. In particular, we discuss the case where A is an unitary associative algebra not necessary with inversion. Some of the examples are studied…
3D neural network models atomistic potentials in complex alloys.
problem Designing robust atomistic potentials for complex alloys is computationally expensive and time-consuming.
method Voxelized atomic configurations and 3D convolutional neural networks to learn atomic interactions.
result 3D convolutional neural networks effectively model atomistic potentials in complex alloys.
Paper develops formulas for shape derivatives in wave scattering.
problem Computing high order shape derivatives for wave scattering is challenging.
method Introduces elegant recurrence formulas using differential forms and Lie derivatives.
result Unified framework for computing high order shape perturbations in scattering problems.
Deep learning model predicts material microstructures from processing methods.
problem Linking processing conditions to material properties for material design.
method Conditional image synthesis using Wasserstein GAN with gradient penalty.
result Deep learning model synthesizes high-quality microstructures for given cooling methods.
New method allows sheets to morph into multiple shapes via spatially varying stimuli.
problem Limitation of current shape-programmed sheets to achieve only one target geometry.
method Patterning the stimulus itself for spatiotemporal control over local deformation magnitudes.
result A single physical sample can be induced to traverse a continuous family of target geometries.
Imaging spectrometers measure electromagnetic energy scattered in their instantaneous field view in hundreds or thousands of spectral channels with higher spectral resolution than multispectral cameras. Imaging spectrometers are therefore often referred to as hyperspectral cameras (HSCs). Higher spectral resolution ena…