Modeling biological soft tissue is complex in part due to material heterogeneity. Microstructural patterns, which play a major role in defining the mechanical behavior of these tissues, are both challenging to characterize, and difficult to simulate. Recently, machine learning (ML)-based methods to predict the mechanical behavior of heterogeneous materials have made it possible to more thoroughly explore the massive input parameter space associated with heterogeneous blocks of material. Specifically, we can train ML models to closely approximate computationally expensive heterogeneous material simulations where the ML model is trained on datasets of simulations with relevant spatial heterogeneity. However, when it comes to applying these techniques to tissue, there is a major limitation: the number of useful examples available to characterize the input domain under study is often limited. In this work, we investigate the efficacy of both ML-based generative models and procedural methods as tools for augmenting limited input pattern datasets. We find that a Style-based Generative Adversarial Network with an adaptive discriminator augmentation mechanism is able to successfully leverage just 1,000 example patterns to create authentic generated patterns. And, we find that diverse generated patterns with adequate resemblance to real patterns can be used as inputs to finite element simulations to meaningfully augment the training dataset. To enable this methodological contribution, we have created an open access Finite Element Analysis simulation dataset based on Cahn-Hilliard patterns. We anticipate that future researchers will be able to leverage this dataset and build on the work presented here.

/pdf/enhancing-mechanical-metamodels-with-a-generative-model-25t93s8k.pdf

Enhancing Mechanical Metamodels with a Generative Model-Based Augmented Training Dataset

De novo drug design with desired biological activities is crucial for developing novel therapeutics for patients. The drug development process is time- and resource-consuming, and it has a low probability of success. Recent advances in machine learning and deep learning technology have reduced the time and cost of the discovery process and therefore, improved pharmaceutical research and development. In this paper, we explore the combination of two rapidly developing fields with lead candidate discovery in the drug development process. First, artificial intelligence has already been demonstrated to successfully accelerate conventional drug design approaches. Second, quantum computing has demonstrated promising potential in different applications, such as quantum chemistry, combinatorial optimizations, and machine learning. This article explores hybrid quantum-classical generative adversarial networks (GAN) for small molecule discovery. We substituted each element of GAN with a variational quantum circuit (VQC) and demonstrated the quantum advantages in the small drug discovery. Utilizing a VQC in the noise generator of a GAN to generate small molecules achieves better physicochemical properties and performance in the goal-directed benchmark than the classical counterpart. Moreover, we demonstrate the potential of a VQC with only tens of learnable parameters in the generator of GAN to generate small molecules. We also demonstrate the quantum advantage of a VQC in the discriminator of GAN. In this hybrid model, the number of learnable parameters is significantly less than the classical ones, and it can still generate valid molecules. The hybrid model with only tens of training parameters in the quantum discriminator outperforms the MLP-based one in terms of both generated molecule properties and the achieved KL divergence. However, the hybrid quantum-classical GANs still face challenges in generating unique and valid molecules compared to their classical counterparts.

https://pubs.acs.org/doi/pdf/10.1021/acs.jcim.3c00562

Exploring the Advantages of Quantum Generative Adversarial Networks in Generative Chemistry

Local-global decompositions for conditional microstructure generation

We propose a physics informed, neural network-based elasto-viscoplasticity (NN-EVP) constitutive modeling framework for predicting the flow response in metals as a function of underlying grain size. The developed NN-EVP algorithm is based on input convex neural networks as a means to strictly enforce thermodynamic consistency, while allowing high expressivity towards model discovery from limited data. It utilizes state-of-the-art machine learning tools within PyTorch's high-performance library providing a flexible tool for data-driven, automated constitutive modeling. To test the performance of the framework, we generate synthetic stress-strain curves using a power law-based model with phenomenological hardening at small strains and test the trained model for strain amplitudes beyond the training data. Next, experimentally measured flow responses obtained from uniaxial deformations are used to train the framework under large plastic deformations. Ultimately, the Hall-Petch relationship corresponding to grain size strengthening is discovered by training flow response as a function of grain size, also leading to efficient extrapolation. The present work demonstrates a successful integration of neural networks into elasto-viscoplastic constitutive laws, providing a robust automated framework for constitutive model discovery that can efficiently generalize, while also providing insights into predictions of flow response and grain size-property relationships in metals and metallic alloys under large plastic deformations.

NN-EVP: A physics informed neural network-based elasto-viscoplastic framework for predictions of grain size-aware flow response under large deformations

Generative Adversarial Networks (GANs) have gained significant attention in several computer vision tasks for generating high-quality synthetic data. Various medical applications including diagnostic imaging and radiation therapy can benefit greatly from synthetic data generation due to data scarcity in the domain. However, medical image data is typically kept in 3D space, and generative models suffer from the curse of dimensionality issues in generating such synthetic data. In this paper, we investigate the potential of GANs for generating connected 3D volumes. We propose an improved version of 3D α -GAN by incorporating various architectural enhancements. On a synthetic dataset of connected 3D spheres and ellipsoids, our model can generate fully connected 3D shapes with similar geometrical characteristics to that of training data. We also show that our 3D GAN model can successfully generate high-quality 3D tumor volumes and associated treatment specifications (e.g., isocenter locations). Similar moment invariants to the training data as well as fully connected 3D shapes confirm that improved 3D α -GAN implicitly learns the training data distribution, and generates realistic-looking samples. The capability of improved 3D α -GAN makes it a valuable source for generating synthetic medical image data that can help future research in this domain.

Improved α-GAN architecture for generating 3D connected volumes with an application to radiosurgery treatment planning

This paper presents a generative adversarial network (GAN) capable of producing realistic microstructure morphology features and demonstrates its capabilities on a dataset of crystalline titanium grain shapes. Alongside this, we present an approach to train deep learning networks to understand material-specific descriptor features, such as grain shapes, based on existing conceptual relationships with established learning spaces, such as functional object shapes. A style-based GAN with Wasserstein loss, called M-GAN, was first trained to recognize distributions of morphology features from function objects in the ShapeNet dataset and was then applied to grain morphologies from a 3D crystallographic dataset of Ti–6Al–4V. Evaluation of feature recognition on objects showed comparable or better performance than state-of-the-art voxel-based network approaches. When applied to experimental data, M-GAN generated realistic grain morphologies comparable to those seen in Ti–6Al–4V. A quantitative comparison of moment invariant distributions showed that the generated grains were similar in shape and structure to the ground truth, but scale invariance learned from object recognition led to difficulty in distinguishing between the physical features of small grains and spatial resolution artifacts. The physical implications of M-GAN’s learning capabilities are discussed, as well as the extensibility of this approach to other material characteristics related to grain morphology. 

/pdf/3d-grain-shape-generation-in-polycrystals-using-generative-mf3gjlke.pdf

3D Grain Shape Generation in Polycrystals Using Generative Adversarial Networks

Experimental solid mechanics is at a pivotal point where machine learning (ML) approaches are rapidly proliferating into the discovery process due to significant advances in data storage and processing capabilities. Much of the ML that is being adopted by the mechanics community was initially developed for application outside of science and engineering, and has the potential to produce results of questionable physical validity. To ensure that these data-driven approaches are trustworthy, there is a clear need to embed physical principles into their architectures, to evaluate and compare ML frameworks against benchmark datasets, and to test their broader extensibility. Frameworks must be grounded in a clear objective, quantifiable error, and a well-defined scope of extensibility. These principles enable ML models with a wide range of architectures to be meaningfully categorized, compared, evaluated, and extended to broader experimental and computational frameworks. Application of these principles are demonstrated through an investigation of ML models in two different use cases, acoustic emission and resonant ultrasound spectroscopy, along with a discussion of outlooks for the future of trustworthy ML in experimental mechanics. 

Perspective: Machine learning in experimental solid mechanics

A challenging opportunity in structural health monitoring of composite materials is using machine learning (ML) methods to classify acoustic emissions according to the damage mechanism that emitted the signal. A wide variety of ML frameworks have been developed; however, lack of ground truth datasets in addition to limited overlap between experimental configurations has precluded any direct, quantitative benchmarking of their accuracy. Here, we generate a ground truth dataset comprised of pencil lead breaks with known angles of incidence, $$\theta $$ . Each angle generates a unique frequency spectrum that changes continuously with $$\theta $$ , which could be analogous to attributes of acoustic emission signals generated from failure processes, such as those that occur in composites. Five frameworks are then applied to the ground truth dataset and benchmarked according to their ability to discriminate between two sets of signals with a fixed $$\Delta \theta $$ . A discussion of their performance as related to choice of features is given, and a set of guidelines for best-practices for feature selection and standardized practices are proposed. 

/pdf/quantitative-benchmarking-of-acoustic-emission-machine-emln5o25.pdf

Quantitative Benchmarking of Acoustic Emission Machine Learning Frameworks for Damage Mechanism Identification


 Large language models (LLMs), such as ChatGPT and PaLM, are able to perform sophisticated text comprehension and generation tasks with little or no training. Alongside their broader societal impacts, these capabilities carry great promise for the physical sciences, including applied mechanics. We present a summary of recent developments in these models, their application to mechanics and adjacent fields, and a perspective on their future use in applied mechanics, taking into account their limitations and the unique challenges of the field.

S. Daly

Papers

3D Grain Shape Generation in Polycrystals Using Generative Adversarial Networks

Perspective: Machine learning in experimental solid mechanics

Quantitative Benchmarking of Acoustic Emission Machine Learning Frameworks for Damage Mechanism Identification

Perspective: Large Language Models in Applied Mechanics

In situ crack opening displacement growth rates of SiC/SiC ceramic matrix minicomposites