Designing complex architectured materials with generative adversarial networks

Extrusion-based 3D printing of soft active materials

Active materials are capable of responding to external stimuli, as observed in both natural and synthetic systems, from sensitive plants to temperature-responsive hydrogels. Extrusion-based 3D printing of soft active materials facilitates the fabrication of intricate geometries with spatially programmed compositions and architectures at various scales, further enhancing the functionality of materials. This Feature Article summarizes recent advances in extrusion-based 3D printing of active materials in both non-living (i.e., synthetic) and living systems. It highlights emerging ink formulations and architectural designs that enable programmable properties, with a focus on complex shape morphing and controllable light-emitting patterns. The article also spotlights strategies for engineering living materials that can produce genetically encoded material responses and react to a variety of environmental stimuli. Lastly, it discusses the challenges and prospects for advancements in both synthetic and living composite materials from the perspectives of chemistry, modeling, and integration.

Specific wavelength peak emulation with amorphous metastructures

The conventional design process for metasurfaces is time-consuming and computationally expensive. To address this challenge, we utilize a deep convolutional generative adversarial network (DCGAN) to generate new nanohole metastructure designs that match a desired transmittance spectrum in the visible range. The trained DCGAN model demonstrates an exceptional performance in generating diverse and manufacturable metastructure designs that closely resemble the target optical properties. The proposed method provides several advantages over existing approaches. These include its capability to generate new designs without prior knowledge or assumptions regarding the relationship between metastructure geometries and optical properties, its high efficiency, and its generalizability to other types of metamaterials. The successful fabrication and experimental characterization of the predicted metastructures further validate the accuracy and effectiveness of our proposed method.

Text-to-Microstructure Generation Using Generative Deep Learning

Designing novel materials is greatly dependent on understanding the design principles, physical mechanisms, and modeling methods of material microstructures, requiring experienced designers with expertise and several rounds of trial and error. Although recent advances in deep generative networks have enabled the inverse design of material microstructures, most studies involve property-conditional generation and focus on a specific type of structure, resulting in limited generation diversity and poor human-computer interaction. In this study, a pioneering text-to-microstructure deep generative network (Txt2Microstruct-Net) is proposed that enables the generation of 3D material microstructures directly from text prompts without additional optimization procedures. The Txt2Microstruct-Net model is trained on a large microstructure-caption paired dataset that is extensible using the algorithms provided. Moreover, the model is sufficiently flexible to generate different geometric representations, such as voxels and point clouds. The model's performance is also demonstrated in the inverse design of material microstructures and metamaterials. It has promising potential for interactive microstructure design when associated with large language models and could be a user-friendly tool for material design and discovery.

Anisotropic Morphing in Bistable Kirigami through Symmetry Breaking and Geometric Frustration

Shape morphing in bistable kirigami enables remarkable functionalities appealing to a diverse range of applications across the spectrum of length scale. At the core of their shape shifting lies the architecture of their repeating unit, where highly deformable slits and quasi-rigid rotating units often exhibit multiple symmetries that confer isotropic deployment obeying uniform scaling transformation. In this work, symmetry breaking in bistable kirigami is investigated to access geometric frustration and anisotropic morphing, enabling arbitrarily scaled deployment in planar and spatial bistable domains. With an analysis on their symmetry properties complemented by a systematic investigation integrating semi-analytical derivations, numerical simulations, and experiments on elastic kirigami sheets, this work unveils the fundamental relations between slit symmetry, geometric frustration, and anisotropic bistable deployment. Furthermore, asymmetric kirigami units are leveraged in planar and flat-to-3D demonstrations to showcase the pivotal role of shear deformation in achieving target shapes and functions so far unattainable with uniformly stretchable kirigami. The insights provided in this work unveil the role of slit symmetry breaking in controlling the anisotropic bistable deployment of soft kirigami metamaterials, enriching the range of achievable functionalities for applications spanning deployable space structures, wearable technologies, and soft machines.

Computational discovery of microstructured composites with optimal stiffness-toughness trade-offs

The conflict between stiffness and toughness is a fundamental problem in engineering materials design. However, the systematic discovery of microstructured composites with optimal stiffness-toughness trade-offs has never been demonstrated, hindered by the discrepancies between simulation and reality and the lack of data-efficient exploration of the entire Pareto front. We introduce a generalizable pipeline that integrates physical experiments, numerical simulations, and artificial neural networks to address both challenges. Without any prescribed expert knowledge of material design, our approach implements a nested-loop proposal-validation workflow to bridge the simulation-to-reality gap and find microstructured composites that are stiff and tough with high sample efficiency. Further analysis of Pareto-optimal designs allows us to automatically identify existing toughness enhancement mechanisms, which were previously found through trial and error or biomimicry. On a broader scale, our method provides a blueprint for computational design in various research areas beyond solid mechanics, such as polymer chemistry, fluid dynamics, meteorology, and robotics.

Data-Driven Design for Metamaterials and Multiscale Systems: A Review

Metamaterials are artificial materials designed to exhibit effective material parameters that go beyond those found in nature. Composed of unit cells with rich designability that are assembled into multiscale systems, they hold great promise for realizing next-generation devices with exceptional, often exotic, functionalities. However, the vast design space and intricate structure-property relationships pose significant challenges in their design. A compelling paradigm that could bring the full potential of metamaterials to fruition is emerging: data-driven design. This review provides a holistic overview of this rapidly evolving field, emphasizing the general methodology instead of specific domains and deployment contexts. Existing research is organized into data-driven modules, encompassing data acquisition, machine learning-based unit cell design, and data-driven multiscale optimization. The approaches are further categorized within each module based on shared principles, analyze and compare strengths and applicability, explore connections between different modules, and identify open research questions and opportunities.

Machine learning-based inverse design methods considering data characteristics and design space size in materials design and manufacturing: a review

In the last few decades, the influence of machine learning has permeated many areas of science and technology, including the field of materials science. This toolkit of data driven methods accelerated the discovery and production of new materials by accurately predicting the complicated physical processes and mechanisms that are not fully described by existing materials theories. However, the availability of a growing number of increasingly complex machine learning models confronts us with the question of "which machine learning algorithm to employ". In this review, we provide a comprehensive review of common machine learning algorithms used for materials design, as well as a guideline for selecting the most appropriate model considering the nature of the design problem. To this end, we classify the material design problems into four categories of: (i) the training data set being sufficiently large to capture the trend of design space (interpolation problem), (ii) a vast design space that cannot be explored thoroughly with the initial training data set alone (extrapolation problem), (iii) multi-fidelity datasets (small accurate dataset and large approximate dataset), and (iv) only a small dataset available. The most successful machine learning-based surrogate models and design approaches will be discussed for each case along with pertinent literature. This review focuses mostly on the use of ML algorithms for the inverse design of complicated composite structures, a topic that has received a lot of attention recently with the rise of additive manufacturing.

Deep Learning in Mechanical Metamaterials: From Prediction and Generation to Inverse Design

Mechanical metamaterials are meticulously designed structures with exceptional mechanical properties determined by their microstructures and constituent materials. Tailoring their material and geometric distribution unlocks the potential to achieve unprecedented bulk properties and functions. However, current mechanical metamaterial design considerably relies on experienced designers' inspiration through trial and error, while investigating their mechanical properties and responses entails time-consuming mechanical testing or computationally expensive simulations. Nevertheless, recent advancements in deep learning have revolutionized the design process of mechanical metamaterials, enabling property prediction and geometry generation without prior knowledge. Furthermore, deep generative models can transform conventional forward design into inverse design. Many recent studies on the implementation of deep learning in mechanical metamaterials are highly specialized, and their pros and cons may not be immediately evident. This critical review provides a comprehensive overview of the capabilities of deep learning in property prediction, geometry generation, and inverse design of mechanical metamaterials. Additionally, this review highlights the potential of leveraging deep learning to create universally applicable datasets, intelligently designed metamaterials, and material intelligence. This article is expected to be valuable not only to researchers working on mechanical metamaterials but also those in the field of materials informatics.

Dynamic diagnosis of metamaterials through laser-induced vibrational signatures

Mechanical metamaterials at the microscale exhibit exotic static properties owing to their engineered building blocks1-4, but their dynamic properties have remained substantially less explored. Their design principles can target frequency-dependent properties5-7 and resilience under high-strain-rate deformation8,9, making them versatile materials for applications in lightweight impact resistance10-12, acoustic waveguiding7,13 or vibration damping14,15. However, accessing dynamic properties at small scales has remained a challenge owing to low-throughput and destructive characterization8,16,17 or lack of existing testing protocols. Here we demonstrate a high-throughput, non-contact framework that uses MHz-wave-propagation signatures within a metamaterial to non-destructively extract dynamic linear properties, omnidirectional elastic information, damping properties and defect quantification. Using rod-like tessellations of microscopic metamaterials, we report up to 94% direction-dependent and rate-dependent dynamic stiffening at strain rates approaching 102 s-1, as well as damping properties three times higher than their constituent materials. We also show that frequency shifts in the vibrational response allow for characterization of invisible defects within the metamaterials and that selective probing allows for the construction of experimental elastic surfaces, which were previously only possible computationally. Our work provides a route for accelerated data-driven discovery of materials and microdevices for dynamic applications such as protective structures, medical ultrasound or vibration isolation.

Machine learning-enabled constrained multi-objective design of architected materials

Architected materials that consist of multiple subelements arranged in particular orders can demonstrate a much broader range of properties than their constituent materials. However, the rational design of these materials generally relies on experts' prior knowledge and requires painstaking effort. Here, we present a data-efficient method for the high-dimensional multi-property optimization of 3D-printed architected materials utilizing a machine learning (ML) cycle consisting of the finite element method (FEM) and 3D neural networks. Specifically, we apply our method to orthopedic implant design. Compared to uniform designs, our experience-free method designs microscale heterogeneous architectures with a biocompatible elastic modulus and higher strength. Furthermore, inspired by the knowledge learned from the neural networks, we develop machine-human synergy, adapting the ML-designed architecture to fix a macroscale, irregularly shaped animal bone defect. Such adaptation exhibits 20% higher experimental load-bearing capacity than the uniform design. Thus, our method provides a data-efficient paradigm for the fast and intelligent design of architected materials with tailored mechanical, physical, and chemical properties.

A data-driven framework for structure-property correlation in ordered and disordered cellular metamaterials

Extracting the relation between microstructural features and resulting material properties is essential for advancing our fundamental knowledge on the mechanics of cellular metamaterials and to enable the design of novel material systems. Here, we present a unified framework that not only allows the prediction of macroscopic properties but, more importantly, also reveals their connection to key morphological characteristics, as identified by the integration of machine-learning models and interpretability algorithms. We establish the complex manner in which strut orientation can be critical in determining effective stiffness for certain microstructures and highlight cellular metamaterials with counterintuitive material behavior. We further provide a refined version of Maxwell's criteria regarding the rigidity of frame structures and their connection to cellular metamaterials. By examining the shear moduli of these metamaterials, the mean cell compactness emerges as a key morphological feature. The generality of the proposed framework allows its extension to broader classes of architected materials as well as different properties of interest.

Rapid inverse design of metamaterials based on prescribed mechanical behavior through machine learning

Designing and printing metamaterials with customizable architectures enables the realization of unprecedented mechanical behaviors that transcend those of their constituent materials. These behaviors are recorded in the form of response curves, with stress-strain curves describing their quasi-static footprint. However, existing inverse design approaches are yet matured to capture the full desired behaviors due to challenges stemmed from multiple design objectives, nonlinear behavior, and process-dependent manufacturing errors. Here, we report a rapid inverse design methodology, leveraging generative machine learning and desktop additive manufacturing, which enables the creation of nearly all possible uniaxial compressive stress‒strain curve cases while accounting for process-dependent errors from printing. Results show that mechanical behavior with full tailorability can be achieved with nearly 90% fidelity between target and experimentally measured results. Our approach represents a starting point to inverse design materials that meet prescribed yet complex behaviors and potentially bypasses iterative design-manufacturing cycles.

Unleashing the Power of Artificial Intelligence in Materials Design

The integration of artificial intelligence (AI) algorithms in materials design is revolutionizing the field of materials engineering thanks to their power to predict material properties, design de novo materials with enhanced features, and discover new mechanisms beyond intuition. In addition, they can be used to infer complex design principles and identify high-quality candidates more rapidly than trial-and-error experimentation. From this perspective, herein we describe how these tools can enable the acceleration and enrichment of each stage of the discovery cycle of novel materials with optimized properties. We begin by outlining the state-of-the-art AI models in materials design, including machine learning (ML), deep learning, and materials informatics tools. These methodologies enable the extraction of meaningful information from vast amounts of data, enabling researchers to uncover complex correlations and patterns within material properties, structures, and compositions. Next, a comprehensive overview of AI-driven materials design is provided and its potential future prospects are highlighted. By leveraging such AI algorithms, researchers can efficiently search and analyze databases containing a wide range of material properties, enabling the identification of promising candidates for specific applications. This capability has profound implications across various industries, from drug development to energy storage, where materials performance is crucial. Ultimately, AI-based approaches are poised to revolutionize our understanding and design of materials, ushering in a new era of accelerated innovation and advancement.

A Comprehensive and Versatile Multimodal Deep-Learning Approach for Predicting Diverse Properties of Advanced Materials

A multimodal deep-learning (MDL) framework is presented for predicting physical properties of a ten-dimensional acrylic polymer composite material by merging physical attributes and chemical data. The MDL model comprises four modules, including three generative deep-learning models for material structure characterization and a fourth model for property prediction. The approach handles an 18-dimensional complexity, with ten compositional inputs and eight property outputs, successfully predicting 913 680 property data points across 114 210 composition conditions. This level of complexity is unprecedented in computational materials science, particularly for materials with undefined structures. A framework is proposed to analyze the high-dimensional information space for inverse material design, demonstrating flexibility and adaptability to various materials and scales, provided sufficient data are available. This study advances future research on different materials and the development of more sophisticated models, drawing the authors closer to the ultimate goal of predicting all properties of all materials.

Systematic modification of functionality in disordered elastic networks through free energy surface tailoring

A combined machine learning-physics-based approach is explored for molecular and materials engineering. Specifically, collective variables, akin to those used in enhanced sampled simulations, are constructed using a machine learning model trained on data gathered from a single system. Through the constructed collective variables, it becomes possible to identify critical molecular interactions in the considered system, the modulation of which enables a systematic tailoring of the system's free energy landscape. To explore the efficacy of the proposed approach, we use it to engineer allosteric regulation and uniaxial strain fluctuations in a complex disordered elastic network. Its successful application in these two cases provides insights regarding how functionality is governed in systems characterized by extensive connectivity and points to its potential for design of complex molecular systems.

Converting Nanotoxicity Data to Information Using Artificial Intelligence and Simulation

Decades of nanotoxicology research have generated extensive and diverse data sets. However, data is not equal to information. The question is how to extract critical information buried in vast data streams. Here we show that artificial intelligence (AI) and molecular simulation play key roles in transforming nanotoxicity data into critical information, i.e., constructing the quantitative nanostructure (physicochemical properties)-toxicity relationships, and elucidating the toxicity-related molecular mechanisms. For AI and molecular simulation to realize their full impacts in this mission, several obstacles must be overcome. These include the paucity of high-quality nanomaterials (NMs) and standardized nanotoxicity data, the lack of model-friendly databases, the scarcity of specific and universal nanodescriptors, and the inability to simulate NMs at realistic spatial and temporal scales. This review provides a comprehensive and representative, but not exhaustive, summary of the current capability gaps and tools required to fill these formidable gaps. Specifically, we discuss the applications of AI and molecular simulation, which can address the large-scale data challenge for nanotoxicology research. The need for model-friendly nanotoxicity databases, powerful nanodescriptors, new modeling approaches, molecular mechanism analysis, and design of the next-generation NMs are also critically discussed. Finally, we provide a perspective on future trends and challenges.

An interpretable deep learning approach for designing nanoporous silicon nitride membranes with tunable mechanical properties

The high permeability and strong selectivity of nanoporous silicon nitride (NPN) membranes make them attractive in a broad range of applications. Despite their growing use, the strength of NPN membranes needs to be improved for further extending their biomedical applications. In this work, we implement a deep learning framework to design NPN membranes with improved or prescribed strength values. We examine the predictions of our framework using physics-based simulations. Our results confirm that the proposed framework is not only able to predict the strength of NPN membranes with a wide range of microstructures, but also can design NPN membranes with prescribed or improved strength. Our simulations further demonstrate that the microstructural heterogeneity that our framework suggests for the optimized design, lowers the stress concentration around the pores and leads to the strength improvement of NPN membranes as compared to conventional membranes with homogenous microstructures.

Computational Design and Manufacturing of Sustainable Materials through First-Principles and Materiomics

Engineered materials are ubiquitous throughout society and are critical to the development of modern technology, yet many current material systems are inexorably tied to widespread deterioration of ecological processes. Next-generation material systems can address goals of environmental sustainability by providing alternatives to fossil fuel-based materials and by reducing destructive extraction processes, energy costs, and accumulation of solid waste. However, development of sustainable materials faces several key challenges including investigation, processing, and architecting of new feedstocks that are often relatively mechanically weak, complex, and difficult to characterize or standardize. In this review paper, we outline a framework for examining sustainability in material systems and discuss how recent developments in modeling, machine learning, and other computational tools can aid the discovery of novel sustainable materials. We consider these through the lens of materiomics, an approach that considers material systems holistically by incorporating perspectives of all relevant scales, beginning with first-principles approaches and extending through the macroscale to consider sustainable material design from the bottom-up. We follow with an examination of how computational methods are currently applied to select examples of sustainable material development, with particular emphasis on bioinspired and biobased materials, and conclude with perspectives on opportunities and open challenges.

Polymeric Heart Valves Will Displace Mechanical and Tissue Heart Valves: A New Era for the Medical Devices

The development of a novel artificial heart valve with outstanding durability and safety has remained a challenge since the first mechanical heart valve entered the market 65 years ago. Recent progress in high-molecular compounds opened new horizons in overcoming major drawbacks of mechanical and tissue heart valves (dysfunction and failure, tissue degradation, calcification, high immunogenic potential, and high risk of thrombosis), providing new insights into the development of an ideal artificial heart valve. Polymeric heart valves can best mimic the tissue-level mechanical behavior of the native valves. This review summarizes the evolution of polymeric heart valves and the state-of-the-art approaches to their development, fabrication, and manufacturing. The review discusses the biocompatibility and durability testing of previously investigated polymeric materials and presents the most recent developments, including the first human clinical trials of LifePolymer. New promising functional polymers, nanocomposite biomaterials, and valve designs are discussed in terms of their potential application in the development of an ideal polymeric heart valve. The superiority and inferiority of nanocomposite and hybrid materials to non-modified polymers are reported. The review proposes several concepts potentially suitable to address the above-mentioned challenges arising in the R&D of polymeric heart valves from the properties, structure, and surface of polymeric materials. Additive manufacturing, nanotechnology, anisotropy control, machine learning, and advanced modeling tools have given the green light to set new directions for polymeric heart valves.

Detecting Microstructural Criticality/Degeneracy through Hybrid Learning Strategies Trained by Molecular Dynamics Simulations

Efficient microstructure design can strongly accelerate the development of materials. However, the complexity of the microstructure-behavior relation renders the criticalities and degeneracies within the microstructure space highly possible. Criticality means that a slight microstructural change can lead to a dramatic transition in material behavior, while degeneracy means that very different microstructures may lead to similar behaviors. To investigate these microstructural characteristics of the fiber/matrix interface within composite materials, we have proposed a hybrid deep-learning-based framework by integrating the supervised feed-forward neural network and the unsupervised autoencoder, which are trained by the molecular dynamics (MD) simulation results. The well-trained model continuously maps the elemental density images within the interfacial area into a low-dimensional latent space. Assisted by the extracted latent features, we can easily detect the criticalities and degeneracies within the original microstructure space of the composite's interface. The predicted microstructural criticalities and degeneracies are validated by investigating their atomistic origins through MD simulations. The proposed framework can be employed for the interfacial microstructure design of composite materials by identifying certain interfacial microstructures that might lead to undesirable behaviors.

Deep-learning-based inverse design of three-dimensional architected cellular materials with the target porosity and stiffness using voxelized Voronoi lattices

Architected cellular materials are a class of artificial materials with cellular architecture-dependent properties. Typically, designing cellular architectures paves the way to generate architected cellular materials with specific properties. However, most previous studies have primarily focused on a forward design strategy, wherein a geometry is generated using computer-aided design modeling, and its properties are investigated experimentally or via simulations. In this study, we developed an inverse design framework for a disordered architected cellular material (Voronoi lattices) using deep learning. This inverse design framework is a three-dimensional conditional generative adversarial network (3D-CGAN) trained based on supervised learning using a dataset consisting of voxelized Voronoi lattices and their corresponding relative densities and Young's moduli. A well-trained 3D-CGAN adopts variational sampling to generate multiple distinct Voronoi lattices with the target relative density and Young's modulus. Consequently, the mechanical properties of the 3D-CGAN generated Voronoi lattices are validated through uniaxial compression tests and finite element simulations. The inverse design framework demonstrates potential for use in bone implants, where scaffold implants can be automatically generated with the target relative density and Young's modulus.

Predicting stress, strain and deformation fields in materials and structures with graph neural networks

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.

Dynamic morphological transformations in soft architected materials via buckling instability encoded heterogeneous magnetization

The geometric reconfigurations in three-dimensional morphable structures have a wide range of applications in flexible electronic devices and smart systems with unusual mechanical, acoustic, and thermal properties. However, achieving the highly controllable anisotropic transformation and dynamic regulation of architected materials crossing different scales remains challenging. Herein, we develop a magnetic regulation approach that provides an enabling technology to achieve the controllable transformation of morphable structures and unveil their dynamic modulation mechanism as well as potential applications. With buckling instability encoded heterogeneous magnetization profiles inside soft architected materials, spatially and temporally programmed magnetic inputs drive the formation of a variety of anisotropic morphological transformations and dynamic geometric reconfiguration. The introduction of magnetic stimulation could help to predetermine the buckling states of soft architected materials, and enable the formation of definite and controllable buckling states without prolonged magnetic stimulation input. The dynamic modulations can be exploited to build systems with switchable fluidic properties and are demonstrated to achieve capabilities of fluidic manipulation, selective particle trapping, sensitivity-enhanced biomedical analysis, and soft robotics. The work provides new insights to harness the programmable and dynamic morphological transformation of soft architected materials and promises benefits in microfluidics, programmable metamaterials, and biomedical applications.

Inverse design of 3D reconfigurable curvilinear modular origami structures using geometric and topological reconstructions

The recent development of modular origami structures has ushered in an era for active metamaterials with multiple degrees of freedom (multi-DOF). Notably, no systematic inverse design approach for 3D curvilinear modular origami structures has been reported. Moreover, very few modular origami topologies have been studied to design active metamaterials with multi-DOF. Herein, we develop an inverse design method for constructing 3D reconfigurable architected structures - we synthesize modular origami structures whose unit cells can be volumetrically mapped into a prescribed 3D curvilinear shape followed by volumetric shrinkage to construct modules. After modification of the tubular geometry, we search through all the possible geometric and topological combinations of the modular origami structures to attain the target mobility using a topological reconstruction of modules. Our inverse design using geometric and topological reconstructions can provide an effective solution to construct 3D curvilinear reconfigurable structures with multi-DOF. Our work opens a path toward 3D reconfigurable systems based on volumetric inverse design, such as 3D active metamaterials and 3D morphing devices for automotive, aerospace, and biomedical engineering applications.

Nature-inspired architected materials using unsupervised deep learning

Nature-inspired material design is driven by superior properties found in natural architected materials and enabled by recent developments in additive manufacturing and machine learning. Existing approaches to push design beyond biomimicry typically use supervised deep learning algorithms to predict and optimize properties based on experimental or simulation data. However, these methods constrain generated material designs to abstracted labels and to “black box” outputs that are only indirectly manipulable. Here we report an alternative approach using an unsupervised generative adversarial network (GAN) model. Training the model on unlabeled data constructs a latent space free of human intervention, which can then be explored through seeding, image encoding, and vector arithmetic to control specific parameters of de novo generated material designs and to push them beyond training data distributions for broad applicability. We illustrate this end-to-end with new materials inspired by leaf microstructures, showing how biological 2D structures can be used to develop novel architected materials in 2 and 3 dimensions. We further utilize a genetic algorithm to optimize generated microstructures for mechanical properties, operating directly on the latent space. This approach allows for transfer of information across manifestations using the latent space as mediator, opening new avenues for exploration of nature-inspired materials.

Shen and colleagues reported an unsupervised generative adversarial network (GAN) to identify patterns in leaves associated with superior mechanical properties and use 3D printing to build architected materials inspired by the patterns. In the future, this approach may be applied more broadly to natural materials to enable efficient algorithmic construction of structures with customized properties and form factors.

Machine Learning for Harnessing Thermal Energy: From Materials Discovery to System Optimization

Recent advances in machine learning (ML) have impacted research communities based on statistical perspectives and uncovered invisibles from conventional standpoints. Though the field is still in the early stage, this progress has driven the thermal science and engineering communities to apply such cutting-edge toolsets for analyzing complex data, unraveling abstruse patterns, and discovering non-intuitive principles. In this work, we present a holistic overview of the applications and future opportunities of ML methods on crucial topics in thermal energy research, from bottom-up materials discovery to top-down system design across atomistic levels to multi-scales. In particular, we focus on a spectrum of impressive ML endeavors investigating the state-of-the-art thermal transport modeling (density functional theory, molecular dynamics, and Boltzmann transport equation), different families of materials (semiconductors, polymers, alloys, and composites), assorted aspects of thermal properties (conductivity, emissivity, stability, and thermoelectricity), and engineering prediction and optimization (devices and systems). We discuss the promises and challenges of current ML approaches and provide perspectives for future directions and new algorithms that could make further impacts on thermal energy research.

Inverse Design of Mechanical Metamaterials with Target Nonlinear Response via a Neural Accelerated Evolution Strategy

Materials with target nonlinear mechanical response can support the design of innovative soft robots, wearable devices, footwear, and energy-absorbing systems, yet it is challenging to realize them. Here, mechanical metamaterials based on hinged quadrilaterals are used as a platform to realize target nonlinear mechanical responses. It is first shown that by changing the shape of the quadrilaterals, the amount of internal rotations induced by the applied compression can be tuned, and a wide range of mechanical responses is achieved. Next, a neural network is introduced that provides a computationally inexpensive relationship between the parameters describing the geometry and the corresponding stress-strain response. Finally, it is shown that by combining the neural network with an evolution strategy, one can efficiently identify geometries resulting in a wide range of target nonlinear mechanical responses and design optimized energy-absorbing systems, soft robots, and morphing structures.

Emerging Deep-Sea Smart Composites: Advent, Performance, and Future Trends

To solve the global shortage of land and offshore resources, the development of deep-sea resources has become a popular topic in recent decades. Deep-sea composites are widely used materials in abyssal resources extraction, and corresponding marine exploration vehicles and monitoring devices for deep-sea engineering. This article firstly reviews the existing research results and limitations of marine composites and equipment or devices used for resource extraction. By combining the research progress of smart composites, deep-sea smart composite materials with the three characteristics of self-diagnosis, self-healing, and self-powered are proposed and relevant studies are summarized. Finally, the review summarizes research challenges for the materials, and looks forward to the development of new composites and their practical application in conjunction with the progress of composites disciplines and AI techniques.

Machine learning-based prediction and inverse design of 2D metamaterial structures with tunable deformation-dependent Poisson's ratio

With the aid of recent efficient and prior knowledge-free machine learning (ML) algorithms, extraordinary mechanical properties such as negative Poisson's ratio have extensively promoted the diverse designs of metamaterials with distinctive cellular structures. However, most existing ML approaches applied to the design of metamaterials are primarily based on a single property value with the assumption that the Poisson's ratio of a material is stationary, neglecting the dynamic variability of Poisson's ratio, termed deformation-dependent Poisson's ratio, during the loading process that a metamaterial other than conventional materials may experience. This paper first proposes a crystallographic symmetry-based methodology to build 2D metamaterials with complex but patterned topological structures, and then converts them into computational models suitable for molecular dynamics simulations. Then, we employ an integrated approach, consisting of molecular dynamics simulations capable of generating and collecting a large dataset for training/validation, in addition to ML algorithms (CNN and Cycle-GAN) able to predict the dynamic characteristics of Poisson's ratio and offer the inverse design of a metamaterial structure based on a target quasi-continuous Poisson's ratio-strain curve, to eventually unravel the underlying mechanism and design principles of 2D metamaterial structures with tunable Poisson's ratio. The close match between the predefined Poisson's ratio response and that from the generated structure validates the feasibility of the proposed ML model. Owing to the high efficiency and complete independence from prior knowledge, our proposed approach offers a novel and robust technique for the prediction and inverse design of metamaterial structures with tailored deformation-dependent Poisson's ratio, an unprecedented property attractive in flexible electronics, soft robotics, and nanodevices.

Improved self-attention generative adversarial adaptation network-based melanoma classification

Melanoma is one of the widespread skin cancers that has affected millions in past decades. Detection of skin cancer at preliminary stages may become a source of reducing mortality rates. Hence, it is required to develop an autonomous system of reliable type for the detection of melanoma via image processing. This paper develops an independent medical imaging technique using Self-Attention Adaptation Generative Adversarial Network (SAAGAN). The entire processing model involves the process of pre-processing, feature extraction using Scale Invariant Feature Transform (SIFT), and finally, classification using SAAGAN. The simulation is conducted on ISIC 2016/PH2 datasets, where 10-fold cross-validation is undertaken on a high-end computing platform. The simulation is performed to test the model efficacy against various images on several performance metrics that include accuracy, precision, recall, f-measure, percentage error, Matthews Correlation Coefficient, and Jaccard Index. The simulation shows that the proposed SAAGAN is more effective in detecting the test images than the existing GAN protocols.

Data-Driven Materials Innovation and Applications

Owing to the rapid developments to improve the accuracy and efficiency of both experimental and computational investigative methodologies, the massive amounts of data generated have led the field of materials science into the fourth paradigm of data-driven scientific research. This transition requires the development of authoritative and up-to-date frameworks for data-driven approaches for material innovation. A critical discussion on the current advances in the data-driven discovery of materials with a focus on frameworks, machine-learning algorithms, material-specific databases, descriptors, and targeted applications in the field of inorganic materials is presented. Frameworks for rationalizing data-driven material innovation are described, and a critical review of essential subdisciplines is presented, including: i) advanced data-intensive strategies and machine-learning algorithms; ii) material databases and related tools and platforms for data generation and management; iii) commonly used molecular descriptors used in data-driven processes. Furthermore, an in-depth discussion on the broad applications of material innovation, such as energy conversion and storage, environmental decontamination, flexible electronics, optoelectronics, superconductors, metallic glasses, and magnetic materials, is provided. Finally, how these subdisciplines (with insights into the synergy of materials science, computational tools, and mathematics) support data-driven paradigms is outlined, and the opportunities and challenges in data-driven material innovation are highlighted.

Deep learning for non-parameterized MEMS structural design

The geometric designs of MEMS devices can profoundly impact their physical properties and eventual performances. However, it is challenging for researchers to rationally consider a large number of possible designs, as it would be very time- and resource-consuming to study all these cases using numerical simulation. In this paper, we report the use of deep learning techniques to accelerate the MEMS design cycle by quickly and accurately predicting the physical properties of numerous design candidates with vastly different geometric features. Design candidates are represented in a nonparameterized, topologically unconstrained form using pixelated black-and-white images. After sufficient training, a deep neural network can quickly calculate the physical properties of interest with good accuracy without using conventional numerical tools such as finite element analysis. As an example, we apply our deep learning approach in the prediction of the modal frequency and quality factor of disk-shaped microscale resonators. With reasonable training, our deep learning neural network becomes a high-speed, high-accuracy calculator: it can identify the flexural mode frequency and the quality factor 4.6 × 10³ times and 2.6 × 10⁴ times faster, respectively, than conventional numerical simulation packages, with good accuracies of 98.8 ± 1.6% and 96.8 ± 3.1%, respectively. When simultaneously predicting the frequency and the quality factor, up to ~96.0% of the total computation time can be saved during the design process. The proposed technique can rapidly screen over thousands of design candidates and promotes experience-free and data-driven MEMS structural designs.

Growth rules for irregular architected materials with programmable properties

Biomaterials display microstructures that are geometrically irregular and functionally efficient. Understanding the role of irregularity in determining material properties offers a new path to engineer materials with superior functionalities, such as imperfection insensitivity, enhanced impact absorption, and stress redirection. We uncover fundamental, probabilistic structure-property relationships using a growth-inspired program that evokes the formation of stochastic architectures in natural systems. This virtual growth program imposes a set of local rules on a limited number of basic elements. It generates materials that exhibit a large variation in functional properties starting from very limited initial resources, which echoes the diversity of biological systems. We identify basic rules to control mechanical properties by independently varying the microstructure's topology and geometry in a general, graph-based representation of irregular materials.

Deep Learning-Accelerated Designs of Tunable Magneto-Mechanical Metamaterials

Metamaterials are artificially structured materials with unusual properties, such as negative Poisson's ratio, acoustic band gap, and energy absorption. However, metamaterials made of conventional materials lack tunability after fabrication. Thus, active metamaterials using magneto-mechanical actuation for untethered, fast, and reversible shape configurations are developed to tune the mechanical response and property of metamaterials. Although the magneto-mechanical metamaterials have shown promising capabilities in tunable mechanical stiffness, acoustic band gaps, and electromagnetic behaviors, the existing demonstrations rely on the forward design methods based on experience or simulations, by which the metamaterial properties are revealed only after the design. Considering the massive design space due to the material and structural programmability, a robust inverse design strategy is desired to create the magneto-mechanical metamaterials with preferred tunable properties. In this work, we develop an inverse design framework where a deep residual network replaces the conventional finite-element analysis for acceleration, realizing metamaterials with predetermined global strains under magnetic actuations. For validation, a direct-ink-writing printing method of the magnetic soft materials is adopted to fabricate the designed complex metamaterials. The deep learning-accelerated design framework opens avenues for the designs of magneto-mechanical metamaterials and other active metamaterials with target mechanical, acoustic, thermal, and electromagnetic properties.

Engineered Living Hydrogels

Living biological systems, ranging from single cells to whole organisms, can sense, process information, and actuate in response to changing environmental conditions. Inspired by living biological systems, engineered living cells and nonliving matrices are brought together, which gives rise to the technology of engineered living materials. By designing the functionalities of living cells and the structures of nonliving matrices, engineered living materials can be created to detect variability in the surrounding environment and to adjust their functions accordingly, thereby enabling applications in health monitoring, disease treatment, and environmental remediation. Hydrogels, a class of soft, wet, and biocompatible materials, have been widely used as matrices for engineered living cells, leading to the nascent field of engineered living hydrogels. Here, the interactions between hydrogel matrices and engineered living cells are described, focusing on how hydrogels influence cell behaviors and how cells affect hydrogel properties. The interactions between engineered living hydrogels and their environments, and how these interactions enable versatile applications, are also discussed. Finally, current challenges facing the field of engineered living hydrogels for their applications in clinical and environmental settings are highlighted.

Machine learning approaches for biomolecular, biophysical, and biomaterials research

A fluent conversation with a virtual assistant, person-tailored news feeds, and deep-fake images created within seconds-all those things that have been unthinkable for a long time are now a part of our everyday lives. What these examples have in common is that they are realized by different means of machine learning (ML), a technology that has fundamentally changed many aspects of the modern world. The possibility to process enormous amount of data in multi-hierarchical, digital constructs has paved the way not only for creating intelligent systems but also for obtaining surprising new insight into many scientific problems. However, in the different areas of biosciences, which typically rely heavily on the collection of time-consuming experimental data, applying ML methods is a bit more challenging: Here, difficulties can arise from small datasets and the inherent, broad variability, and complexity associated with studying biological objects and phenomena. In this Review, we give an overview of commonly used ML algorithms (which are often referred to as "machines") and learning strategies as well as their applications in different bio-disciplines such as molecular biology, drug development, biophysics, and biomaterials science. We highlight how selected research questions from those fields were successfully translated into machine readable formats, discuss typical problems that can arise in this context, and provide an overview of how to resolve those encountered difficulties.

Stretchy and disordered: Toward understanding fracture in soft network materials via mesoscopic computer simulations

Soft network materials exist in numerous forms ranging from polymer networks, such as elastomers, to fiber networks, such as collagen. In addition, in colloidal gels, an underlying network structure can be identified, and several metamaterials and textiles can be considered network materials as well. Many of these materials share a highly disordered microstructure and can undergo large deformations before damage becomes visible at the macroscopic level. Despite their widespread presence, we still lack a clear picture of how the network structure controls the fracture processes of these soft materials. In this Perspective, we will focus on progress and open questions concerning fracture at the mesoscopic scale, in which the network architecture is clearly resolved, but neither the material-specific atomistic features nor the macroscopic sample geometries are considered. We will describe concepts regarding the network elastic response that have been established in recent years and turn out to be pre-requisites to understand the fracture response. We will mostly consider simulation studies, where the influence of specific network features on the material mechanics can be cleanly assessed. Rather than focusing on specific systems, we will discuss future challenges that should be addressed to gain new fundamental insights that would be relevant across several examples of soft network materials.

Exploring High Thermal Conductivity Amorphous Polymers Using Reinforcement Learning

Developing amorphous polymers with desirable thermal conductivity has significant implications, as they are ubiquitous in applications where thermal transport is critical. Conventional Edisonian approaches are slow and without guarantee of success in material development. In this work, using a reinforcement learning scheme, we design polymers with thermal conductivity above 0.400 W/m·K. We leverage a machine learning model trained against 469 thermal conductivity data calculated from high-throughput molecular dynamics (MD) simulations as the surrogate for thermal conductivity prediction, and we use a recurrent neural network trained with around one million virtual polymer structures as a polymer generator. For all generated polymers with thermal conductivity ≥0.400 W/m·K, we have evaluated their synthesizability by calculating the synthetic accessibility score and validated the thermal conductivity of selected polymers using MD simulations. The best thermally conductive polymer designed has an MD-calculated thermal conductivity of 0.693 W/m·K, which is also estimated to be easily synthesizable. Our demonstrated inverse design scheme based on reinforcement learning may advance polymer development with target properties, and the scheme can also be generalized to other material development tasks for different applications.

Collective Variables for Free Energy Surface Tailoring: Understanding and Modifying Functionality in Systems Dominated by Rare Events

We introduce a method for elucidating and modifying the functionality of systems dominated by rare events that relies on the semiautomated tuning of their underlying free energy surface. The proposed approach seeks to construct collective variables (CVs) that encode the essential information regarding the rare events of the system of interest. The appropriate CVs are identified using harmonic linear discriminant analysis (HLDA), a machine-learning-based method that is trained solely on data collected from short ordinary simulations in the relevant metastable states of the system. Utilizing the interpretable form of the resulting CVs, the critical interaction potentials that determine the system's rare transitions are identified and purposely modified to tailor the free energy surface in a manner that alters functionality as desired. The applicability of the method is illustrated in the context of three different systems, thereby demonstrating that thermodynamic and kinetic properties can be tractably modified with little to no prior knowledge or intuition.

Magnetic Soft Materials and Robots

In conventional classification, soft robots feature mechanical compliance as the main distinguishing factor from traditional robots made of rigid materials. Recent advances in functional soft materials have facilitated the emergence of a new class of soft robots capable of tether-free actuation in response to external stimuli such as heat, light, solvent, or electric or magnetic field. Among the various types of stimuli-responsive materials, magnetic soft materials have shown remarkable progress in their design and fabrication, leading to the development of magnetic soft robots with unique advantages and potential for many important applications. However, the field of magnetic soft robots is still in its infancy and requires further advancements in terms of design principles, fabrication methods, control mechanisms, and sensing modalities. Successful future development of magnetic soft robots would require a comprehensive understanding of the fundamental principle of magnetic actuation, as well as the physical properties and behavior of magnetic soft materials. In this review, we discuss recent progress in the design and fabrication, modeling and simulation, and actuation and control of magnetic soft materials and robots. We then give a set of design guidelines for optimal actuation performance of magnetic soft materials. Lastly, we summarize potential biomedical applications of magnetic soft robots and provide our perspectives on next-generation magnetic soft robots.

Bioinspired Design of a Cartilage-like Lubricated Composite with Mechanical Robustness

Natural articular cartilages show extraordinary tribological performance based on their penetrated surface lubricated biomacromolecules and good mechanical tolerance. Hydrogels are considered to be potential alternatives to cartilages due to their low surface friction and good biocompatibility, although the poor mechanical properties limited their applications. Inspired by the excellent mechanical properties and the remarkable surface lubrication mechanism of natural articular cartilages, one kind of cartilage-like composite material with a lubrication phase (Composite-LP) was developed by chemically grafting a thick hydrophilic polyelectrolyte brush layer onto the subsurface of a three-dimensional manufactured elastomer scaffold-hydrogel composite architecture. The Composite-LP exhibited good load-bearing capacities because of the nondissipation strategy and the stress dispersion mechanism resulting from the elastomer scaffold enhancement. In the presence of the top lubrication layer, the Composite-LP showed superior friction reduction functionality and wear resistance under a dynamic shearing process. This design concept of coupling the non-dissipative mechanism and interface lubrication provides a new avenue for developing cartilage-like hydrogels and soft robots.

Inverting the structure-property map of truss metamaterials by deep learning

Inspired by crystallography, the periodic assembly of trusses into architected materials has enjoyed popularity for more than a decade and produced countless cellular structures with beneficial mechanical properties. Despite the successful and steady enrichment of the truss design space, the inverse design has remained a challenge: While predicting effective truss properties is now commonplace, efficiently identifying architectures that have homogeneous or spatially varying target properties has remained a roadblock to applications from lightweight structures to biomimetic implants. To overcome this gap, we propose a deep-learning framework, which combines neural networks with enforced physical constraints, to predict truss architectures with fully tailored anisotropic stiffness. Trained on millions of unit cells, it covers an enormous design space of topologically distinct truss lattices and accurately identifies architectures matching previously unseen stiffness responses. We demonstrate the application to patient-specific bone implants matching clinical stiffness data, and we discuss the extension to spatially graded cellular structures with locally optimal properties.

Responsive materials architected in space and time

Rationally designed architected materials have attained previously untapped territories in materials property space. The properties and behaviours of architected materials need not be stagnant after fabrication; they can be encoded with a temporal degree of freedom such that they evolve over time. In this Review, we describe the variety of materials architected in both space and time, and their responses to various stimuli, including mechanical actuation, changes in temperature and chemical environment, and variations in electromagnetic fields. We highlight the additive manufacturing methods that can precisely prescribe complex geometries and local inhomogeneities to make such responsiveness possible. We discuss the emergent physics phenomena observed in architected materials that are analogous to those in classical materials, such as the formation and behaviour of defects, phase transformations and topologically protected properties. Finally, we offer a perspective on the future of architected materials that have a degree of intelligence through mechanical logic and artificial neural networks.

A Novel High-Speed and High-Accuracy Mathematical Modeling Method of Complex MEMS Resonator Structures Based on the Multilayer Perceptron Neural Network

MEMS resonators have become core devices in a large number of fields; however, due to their complex structures, the finite element analysis (FEA) method is still the main method for their theoretical analysis. The traditional finite element analysis method faces the disadvantages of large calculation amount and long simulation time, which limits the development of high-performance MEMS resonators. This paper demonstrates a high-speed and high-accuracy simulation tool based on the artificial neural network, where a multilayer perceptron (MLP) neural network model is constructed. The typical structural parameters of MEMS resonator are used as the input layer, and its performance indicators produced by the finite element analysis method are the output layer. After iteratively trained with 4000 samples, the cumulative error of the neural network decreases to 0.0017 and a prediction network model is obtained. Compared with the finite element analysis results, the structural accuracy error predicted by the neural network model can be controlled within 6%, but its runtime is shortened by 15,000 times. This high-speed and high-accuracy mathematical modeling method can effectively improve the analyzing efficiency and provide a promising tool for the design and optimization of different complex MEMS resonators, which exhibit remarkable accuracy and speed.

Wallpaper group kirigami

Kirigami, the art of paper cutting, has become a paradigm for mechanical metamaterials in recent years. The basic building blocks of any kirigami structures are repetitive deployable patterns that derive inspiration from geometric art forms and simple planar tilings. Here, we complement these approaches by directly linking kirigami patterns to the symmetry associated with the set of 17 repeating patterns that fully characterize the space of periodic tilings of the plane. We start by showing how to construct deployable kirigami patterns using any of the wallpaper groups, and then design symmetry-preserving cut patterns to achieve arbitrary size changes via deployment. We further prove that different symmetry changes can be achieved by controlling the shape and connectivity of the tiles and connect these results to the underlying kirigami-based lattice structures. All together, our work provides a systematic approach for creating a broad range of kirigami-based deployable structures with any prescribed size and symmetry properties.

Disrupting 3D printing of medicines with machine learning

3D printing (3DP) is a progressive technology capable of transforming pharmaceutical development. However, despite its promising advantages, its transition into clinical settings remains slow. To make the vital leap to mainstream clinical practice and improve patient care, 3DP must harness modern technologies. Machine learning (ML), an influential branch of artificial intelligence, may be a key partner for 3DP. Together, 3DP and ML can utilise intelligence based on human learning to accelerate drug product development, ensure stringent quality control (QC), and inspire innovative dosage-form design. With ML's capabilities, streamlined 3DP drug delivery could mark the next era of personalised medicine. This review details how ML can be applied to elevate the 3DP of pharmaceuticals and importantly, how it can expedite 3DP's integration into mainstream healthcare.

Artificial intelligence and machine learning in design of mechanical materials

Artificial intelligence, especially machine learning (ML) and deep learning (DL) algorithms, is becoming an important tool in the fields of materials and mechanical engineering, attributed to its power to predict materials properties, design de novo materials and discover new mechanisms beyond intuitions. As the structural complexity of novel materials soars, the material design problem to optimize mechanical behaviors can involve massive design spaces that are intractable for conventional methods. Addressing this challenge, ML models trained from large material datasets that relate structure, properties and function at multiple hierarchical levels have offered new avenues for fast exploration of the design spaces. The performance of a ML-based materials design approach relies on the collection or generation of a large dataset that is properly preprocessed using the domain knowledge of materials science underlying chemical and physical concepts, and a suitable selection of the applied ML model. Recent breakthroughs in ML techniques have created vast opportunities for not only overcoming long-standing mechanics problems but also for developing unprecedented materials design strategies. In this review, we first present a brief introduction of state-of-the-art ML models, algorithms and structures. Then, we discuss the importance of data collection, generation and preprocessing. The applications in mechanical property prediction, materials design and computational methods using ML-based approaches are summarized, followed by perspectives on opportunities and open challenges in this emerging and exciting field.

Tensegrity metamaterials for soft robotics

3D-printed flexible tensegrities with metamaterial properties enable customizable complex locomotion in soft robots.