Cardiac muscle tissue exhibits highly non-linear hyperelastic and orthotropic material behavior during passive deformation. Traditional constitutive identification protocols therefore combine multiple loading modes and typically require multiple specimens and substantial handling. In soft living tissues, such protocols are challenged by inter- and intra-sample variability and by manipulation-induced alterations of mechanical response, which can bias inverse calibration. In this work we exploit spatially heterogeneous full-field kinematics as an information-rich alternative to multimodal testing. We recast EUCLID, an unsupervised method for the automated discovery of constitutive models, towards Bayesian parameter inference for highly nonlinear, orthotropic constitutive models. Using synthetic myocardial tissue slabs, we demonstrate that a single heterogeneous biaxial experiment, combined with sparse reaction-force measurements, enables robust recovery of Holzapfel–Ogden parameters with quantified uncertainty, across multiple noise levels. The inferred responses agree closely with ground-truth simulations and yield credible intervals that reflect the impact of measurement noise on orthotropic material model inference. Our work supports single-shot, uncertainty-aware characterization of nonlinear orthotropic material models from a single biaxial test, reducing sample demand and experimental manipulation.

Constitutive evaluations often dominate the computational cost of finite element (FE) simulations whenever material models are complex. Neural constitutive models (NCMs), i.e., neural network-based constitutive models, offer a highly expressive and flexible framework for modeling complex material behavior in solid mechanics. However, their practical adoption in large-scale FE simulations remains limited due to significant computational costs, especially in repeatedly evaluating stress and stiffness. NCMs thus represent an extreme case: their large computational graphs make stress and stiffness evaluations prohibitively expensive, restricting their use to small-scale problems. In this work, we introduce COMMET, an open-source FE framework whose architecture has been redesigned from the ground up to accelerate high-cost constitutive updates. Our framework features a novel assembly algorithm that supports batched and vectorized constitutive evaluations, compute-graph-optimized derivatives that replace automatic differentiation, and distributed-memory parallelism via MPI. These advances dramatically reduce runtime, with speed-ups exceeding three orders of magnitude relative to traditional non-vectorized automatic differentiation-based implementations. While we demonstrate these gains primarily for NCMs, the same principles apply broadly wherever for-loop based assembly or constitutive updates limit performance, establishing a new standard for large-scale, high-fidelity simulations in computational mechanics.

Generative machine learning models have revolutionized material discovery by capturing complex structure–property relationships, yet extending these approaches to the inverse design of three-dimensional metamaterials remains limited by computational complexity and underexplored design spaces due to the lack of expressive representations. Here we present DiffuMeta, a generative framework integrating diffusion transformers with an algebraic language representation, encoding three-dimensional geometries as mathematical sentences. This compact, unified parameterization spans diverse topologies, enabling the direct application of transformers to structural design. DiffuMeta leverages diffusion models to generate new shell structures with precisely targeted stress–strain responses under large deformations, accounting for buckling and contact while addressing the inherent one-to-many mapping by producing diverse solutions. Uniquely, our approach enables simultaneous control over multiple mechanical objectives, including linear and nonlinear responses beyond training domains. Experimental validation of fabricated structures further confirms the efficacy of our approach for accelerated design of metamaterials and structures with tailored properties.

Background: Determining accurate constitutive laws from experimental data remains a key challenge in mechanics, particularly when the material behavior is nonlinear and the dataset is limited or noisy. Traditional approaches rely on identifying parameters of preselected material models, which separates the model selection and the calibration tasks leading to a potentially long and tedious trial-and-error procedure. Objective: This work aims to assess the performance of EUCLID (Efficient Unsupervised Constitutive Law Identification and Discovery), a recently proposed framework for automated discovery of constitutive laws, when applied to experimental data. Methods: Mechanical tests are conducted on natural rubber specimens of varying geometrical complexity. Both global (force–elongation) and local (full-field displacement) data are collected. Constitutive laws are obtained via two routes: (i) conventional parameter identification in a priori selected models, and (ii) EUCLID, which integrates model selection and parameter identification in a unified model discovery pipeline. Results: The two approaches are compared in terms of predictive accuracy, generalization to unseen geometries, and robustness to experimental noise. The coverage of the material state space achieved by each dataset is quantified, and the relative performance of different datasets and models is analyzed. Conclusions: EUCLID enables automated and data-driven discovery of constitutive laws, offering improved flexibility compared to conventional identification methods, and showing strong potential for reliable material modeling based on experimental data.

We propose a computational framework, Hetero-EUCLID, for segmentation and parameter identification to characterize the full hyperelastic behavior of all constituents of a heterogeneous material. In this work, we leverage the Bayesian-EUCLID (Efficient Unsupervised Constitutive Law Identification and Discovery) framework to efficiently solve the heterogenized formulation through parsimonious model selection using sparsity-promoting priors and Monte Carlo Markov Chain sampling. We utilize experimentally observable 3D surface displacement and boundary-averaged force data generated from Finite Element simulations of non-equi-biaxial tension tests on heterogeneous specimens. The framework broadly consists of two steps– residual force-based segmentation and constitutive parameter identification. We validate and demonstrate the ability of the proposed framework to segment the domain and characterize the constituent materials on various types of thin square heterogeneous domains. We validate the framework's ability to segment and characterize materials with multiple levels of displacement noises and non-native mesh discretizations, i.e, using different meshes for the forward FE simulations and the inverse EUCLID problem. This demonstrates the applicability of the Hetero-EUCLID framework in Digital Image/Volume Correlation-based experimental scenarios. Furthermore, the proposed framework performs successful segmentation and material characterizations based on data from a single experiment, thereby making it viable for rapid, interpretable model discovery in domains such as aerospace and defense composites and for characterization of selective tissue stiffening in medical conditions such as fibroatheroma, atherosclerosis, or cancer.

Abstract: Programmable materials (i.e., materials whose properties can be deterministically programmed from their composition or microstructure) comprise a new horizon in materials engineering with transformative potential in areas ranging from soft robotics to biomedical engineering. Advances in high-resolution polymer additive manufacturing have enabled unprecedented control of material composition and architectural design in leading-edge programmable materials. However, progress has largely followed two parallel and weakly connected paths: approaches that emphasize geometric design of the material’s microstructure to tailor properties, and chemistry-driven approaches that focus on developing functional printable polymeric materials. This separation has constrained the exploration of the coupled effects of material composition and structure that are essential for true programmability. Here, we present an overview of the advances in both research tracks and propose a perspective on achieving codesign of material chemistry and architecture across multiple length scales, for next-generation programmable polymeric materials. We discuss emerging data-driven and automated design strategies, including self-driving laboratories, high-throughput experimentation, and machine learning, as a route toward a scalable pathway to navigate the vast and highly coupled design space of programmable polymeric materials. By unifying materials chemistry, architectural design, and data-driven discovery, this perspective outlines a framework for accelerating the discovery of truly programmable matter.

Spinodal metamaterials, with architectures inspired by natural phase-separation processes, have presented a significant alternative to periodic and symmetric morphologies when designing mechanical metamaterials with extreme performance. While their elastic mechanical properties have been systematically determined, their large-deformation, nonlinear responses have been challenging to predict and design, in part due to limited data sets and the need for complex nonlinear simulations. This work presents a novel physics-enhanced machine learning (ML) and optimization framework tailored to address the challenges of designing intricate spinodal metamaterials with customized mechanical properties in large-deformation scenarios where computational modeling is restrictive and experimental data is sparse. By utilizing large-deformation experimental data directly, this approach facilitates the inverse design of spinodal structures with precise finite-strain mechanical responses. The framework sheds light on instability-induced pattern formation in spinodal metamaterials—observed experimentally and in selected nonlinear simulations—leveraging physics-based inductive biases in the form of nonconvex energetic potentials. Altogether, this combined ML, experimental, and computational effort provides a route for efficient and accurate design of complex spinodal metamaterials for large-deformation scenarios where energy absorption and prediction of nonlinear failure mechanisms is essential.

The increasing availability of full-field displacement data from imaging techniques in experimental mechanics is determining a gradual shift in the paradigm of material model calibration and discovery, from using several simple-geometry tests towards a few, or even one single test with complicated geometry. The feasibility of such a “one-shot” calibration or discovery heavily relies upon the richness of the measured displacement data, i.e., their ability to probe the space of the state variables and the stress space (whereby the stresses depend on the constitutive law being sought) to an extent sufficient for an accurate and robust calibration or discovery process. The richness of the displacement data is in turn directly governed by the specimen geometry. In this paper, we propose a density-based topology optimisation framework to optimally design the geometry of the target specimen for calibration of an anisotropic elastic material model. To this end, we perform automatic, high-resolution specimen design by maximising the robustness of the solution of the inverse problem, i.e., the identified material parameters, given noisy displacement measurements from digital image correlation. We discuss the choice of the cost function and the design of the topology optimisation framework, and we analyse a range of optimised topologies generated for the identification of isotropic and anisotropic elastic responses.

Traditional constitutive models rely on hand-crafted parametric forms with limited expressivity and generalizability, while neural network-based models can capture complex material behavior but often lack interpretability. To balance these trade-offs, we present monotonic Input-Convex Kolmogorov-Arnold Networks (ICKANs) for learning polyconvex hyperelastic constitutive laws. ICKANs leverage the Kolmogorov-Arnold representation, decomposing the model into compositions of trainable univariate spline-based activation functions for rich expressivity. We introduce trainable monotonic input-convex splines within the KAN architecture, ensuring physically admissible polyconvex models for isotropic compressible hyperelasticity. The resulting models are both compact and interpretable, enabling explicit extraction of analytical constitutive relationships through a monotonic input-convex symbolic regression technique. Through unsupervised training on full-field strain data and limited global force measurements, ICKANs accurately capture nonlinear stress–strain behavior across diverse strain states. Finite element simulations of unseen geometries with trained ICKAN hyperelastic constitutive models confirm the framework's robustness and generalization capability.

We introduce HyperCAN, a machine learning framework that utilizes hypernetworks to construct adaptable constitutive artificial neural networks for a wide range of beam-based metamaterials exhibiting diverse mechanical behavior under finite deformations. HyperCAN integrates an input convex neural network that models the nonlinear stress–strain map of a truss lattice, while ensuring adherence to fundamental mechanics principles, along with a hypernetwork that dynamically adjusts the parameters of the convex network as a function of the lattice topology and geometry. This unified framework demonstrates robust generalization in predicting the mechanical behavior of previously unseen metamaterial designs and loading scenarios well beyond the training domain. We show how HyperCAN can be integrated into multiscale simulations to accurately capture the highly nonlinear responses of large-scale truss metamaterials, closely matching fully resolved simulations while significantly reducing computational costs. This offers new efficient opportunities for the multiscale design and optimization of truss metamaterials.

Smooth and curved microstructural topologies found in nature—from soap films to trabecular bone—have inspired several mimetic design spaces for architected metamaterials and bio-scaffolds. However, the design approaches so far are ad hoc, raising the challenge: how to systematically and efficiently inverse design such artificial microstructures with targeted topological features? Herein, surface curvature is explored as a design modality and a deep learning framework is presented to produce topologies with as-desired curvature profiles. The inverse design framework can generalize to diverse topological features such as tubular, membranous, and particulate features. Moreover, successful generalization beyond both the design and data space is demonstrated by inverse designing topologies that mimic the curvature profile of trabecular bone, spinodoid topologies, and periodic nodal surfaces for application in bio-scaffolds and implants. Lastly, curvature and mechanics are bridged by showing how topological curvature can be designed to promote mechanically beneficial stretching-dominated deformation over bending-dominated deformation.

Vitrimer is a new, exciting class of sustainable polymers with healing abilities due to their dynamic covalent adaptive networks. However, a limited choice of constituent molecules restricts their property space and potential applications. To overcome this challenge, an innovative approach coupling molecular dynamics (MD) simulations and a novel graph variational autoencoder (VAE) model for inverse design of vitrimer chemistries with desired glass transition temperature (T_g) is presented. The first diverse vitrimer dataset of one million chemistries is curated and T_g for 8,424 of them is calculated by high-throughput MD simulations calibrated by a Gaussian process model. The proposed VAE employs dual graph encoders and a latent dimension overlapping scheme which allows for individual representation of multi-component vitrimers. High accuracy and efficiency of the framework are demonstrated by discovering novel vitrimers with desirable T_g beyond the training regime. To validate the effectiveness of the framework in experiments, vitrimer chemistries are generated with a target T_g = 323 K. By incorporating chemical intuition, a novel vitrimer with T_g of 311–317 K is synthesized, experimentally demonstrating healability and flowability. The proposed framework offers an exciting tool for polymer chemists to design and synthesize novel, sustainable polymers for various applications.

This study demonstrates that two- and three-dimensional spatially graded, truss-based polymeric-material metamaterials can be designed for beneficial impact mitigation and energy absorption capabilities. Through a combination of numerical and experimental techniques, we highlight the broad property space of periodic viscoelastic trusses, realized using 3D printing via selective laser sintering. Extending beyond periodic designs, we investigate the impact response of spatially variant viscoelastic lattices in both two and three dimensions. Our result reveal that introducing spatial variations in lattice topology allows for redirecting of the impact trajectory, opening new opportunities for engineering and tailoring lightweight materials with target impact functionality. This is achieved through the combined selection of base material and metamaterial design.

Natural porous materials have exceptional properties—for example, light weight, mechanical resilience, and multi-functionality. Efforts to imitate their properties in engineered structures have limited success. This, in part, is caused by the complexity of multi-phase materials composites and by the lack of quantified understanding of each component's role in overall hierarchy. This challenge is twofold: 1) computational. because non-periodicity and defects render constructing design guidelines between geometries and mechanical properties complex and expensive and 2) experimental. because the fabrication and characterization of complex, often hierarchical and non-periodic 3D architectures is non-trivial.

Slender beams are often employed as constituents in engineering materials and structures. Prior experiments on lattices of slender beams have highlighted their complex failure response, where the interplay between buckling and fracture plays a critical role. In this paper, we introduce a novel computational approach for modeling fracture in slender beams subjected to large deformations. We adopt a state-of-the-art geometrically exact Kirchhoff beam formulation to describe the finite deformations of beams in three-dimensions. We develop a discontinuous Galerkin finite element discretization of the beam governing equations, incorporating discontinuities in the position and tangent degrees of freedom at the inter-element boundaries of the finite elements. Before fracture initiation, we enforce compatibility of nodal positions and tangents weakly, via the exchange of variationally-consistent forces and moments at the interfaces between adjacent elements. At the onset of fracture, these forces and moments transition to cohesive laws modeling interface failure. We conduct a series of numerical tests to verify our computational framework against a set of benchmarks and we demonstrate its ability to capture the tensile and bending fracture modes in beams exhibiting large deformations. Finally, we present the validation of our framework against fracture experiments of dry spaghetti rods subjected to sudden relaxation of curvature.

The rise of machine learning has fueled the discovery of new materials and, especially, metamaterials—truss lattices being their most prominent class. While their tailorable properties have been explored extensively, the design of truss-based metamaterials has remained highly limited and often heuristic, due to the vast, discrete design space and the lack of a comprehensive parameterization. We here present a graph-based deep learning generative framework, which combines a variational autoencoder and a property predictor, to construct a reduced, continuous latent representation covering an enormous range of trusses. This unified latent space allows for the fast generation of new designs through simple operations (e.g., traversing the latent space or interpolating between structures). We further demonstrate an optimization framework for the inverse design of trusses with customized mechanical properties in both the linear and nonlinear regimes, including designs exhibiting exceptionally stiff, auxetic, pentamode-like, and tailored nonlinear behaviors. This generative model can predict manufacturable (and counter-intuitive) designs with extreme target properties beyond the training domain.