Localized Plasmonic Structured Illumination Microscopy Using Hybrid Inverse Design.

Super-resolution fluorescence imaging has offered unprecedented insights and revolutionized our understanding of biology. In particular, localized plasmonic structured illumination microscopy (LPSIM) achieves video-rate super-resolution imaging with ∼50 nm spatial resolution by leveraging subdiffraction-limited nearfield patterns generated by plasmonic nanoantenna arrays. However, the conventional trial-and-error design process for LPSIM arrays is time-consuming and computationally intensive, limiting the exploration of optimal designs. Here, we propose a hybrid inverse design framework combining deep learning and genetic algorithms to refine LPSIM arrays. A population of designs is evaluated using a trained convolutional neural network, and a multiobjective optimization method optimizes them through iteration and evolution. Simulations demonstrate that the optimized LPSIM substrate surpasses traditional substrates, exhibiting higher reconstruction accuracy, robustness against noise, and increased tolerance for fewer measurements. This framework not only proves the efficacy of inverse design for tailoring LPSIM substrates but also opens avenues for exploring new plasmonic nanostructures in imaging applications.

Physics-Informed Inverse Design of Programmable Metasurfaces.

Emerging reconfigurable metasurfaces offer various possibilities for programmatically manipulating electromagnetic waves across spatial, spectral, and temporal domains, showcasing great potential for enhancing terahertz applications. However, they are hindered by limited tunability, particularly evident in relatively small phase tuning over 270°, due to the design constraints with time-intensive forward design methodologies. Here, a multi-bit programmable metasurface is demonstrated capable of terahertz beam steering facilitated by a developed physics-informed inverse design (PIID) approach. Through integrating a modified coupled mode theory (MCMT) into residual neural networks, the PIID algorithm not only significantly increases the design accuracy compared to conventional neural networks but also elucidates the intricate physical relations between the geometry and the modes. Without decreasing the reflection intensity, the method achieves the enhanced phase tuning as large as 300°. Additionally, the inverse-designed programmable beam steering metasurface is experimentally validated, which is adaptable across 1-bit, 2-bit, and tri-state coding schemes, yielding a deflection angle up to 68° and broadened steering coverage. The demonstration provides a promising pathway for rapidly exploring advanced metasurface devices, with potentially great impact on communication and imaging technologies.

A surrogate-assisted extended generative adversarial network for parameter optimization in free-form metasurface design.

Metasurfaces have widespread applications in fifth-generation (5G) microwave communication. Among the metasurface family, free-form metasurfaces excel in achieving intricate spectral responses compared to regular-shape counterparts. However, conventional numerical methods for free-form metasurfaces are time-consuming and demand specialized expertise. Alternatively, recent studies demonstrate that deep learning has great potential to accelerate and refine metasurface designs. Here, we present XGAN, an extended generative adversarial network (GAN) with a surrogate for high-quality free-form metasurface designs. The proposed surrogate provides a physical constraint to XGAN so that XGAN can accurately generate metasurfaces monolithically from input spectral responses. In comparative experiments involving 20000 free-form metasurface designs, XGAN achieves 0.9734 average accuracy and is 500 times faster than the conventional methodology. This method facilitates the metasurface library building for specific spectral responses and can be extended to various inverse design problems, including optical metamaterials, nanophotonic devices, and drug discovery.

Boosting-Crystal Graph Convolutional Neural Network for Predicting Highly Imbalanced Data: A Case Study for Metal-Insulator Transition Materials.

Applying machine-learning techniques for imbalanced data sets presents a significant challenge in materials science since the underrepresented characteristics of minority classes are often buried by the abundance of unrelated characteristics in majority of classes. Existing approaches to address this focus on balancing the counts of each class using oversampling or synthetic data generation techniques. However, these methods can lead to loss of valuable information or overfitting. Here, we introduce a deep learning framework to predict minority-class materials, specifically within the realm of metal-insulator transition (MIT) materials. The proposed approach, termed boosting-CGCNN, combines the crystal graph convolutional neural network (CGCNN) model with a gradient-boosting algorithm. The model effectively handled extreme class imbalances in MIT material data by sequentially building a deeper neural network. The comparative evaluations demonstrated the superior performance of the proposed model compared to other approaches. Our approach is a promising solution for handling imbalanced data sets in materials science.

Design of Ultra-Compact and Multifunctional Optical Logic Gate Based on Sb2Se3-SOI Hybrid Platform.

Optical logic devices are essential functional devices for achieving optical signal processing. In this study, we design an ultra-compact (4.92 × 2.52 µm2) reconfigurable optical logic gate by using inverse design method with DBS algorithm based on Sb2Se3-SOI integrated platform. By selecting different amorphous/crystalline distributions of Sb2Se3 via programmable electrical triggers, the designed structure can switch between OR, XOR, NOT or AND logic gate. This structure works well for all four logic functions in the wavelength range of 1540-1560 nm. Especially at the wavelength of 1550 nm, the Contrast Ratios for XOR, NOT and AND logic gate are 13.77 dB, 11.69 dB and 3.01 dB, respectively, indicating good logical judgment ability of the device. Our design is robust to a certain range of fabrication imperfections. Even if performance weakens due to deviations, improvements can be obtained by rearranging the configurations of Sb2Se3 without reproducing the whole device.

Generative models struggle with kirigami metamaterials.

Generative machine learning models have shown notable success in identifying architectures for metamaterials-materials whose behavior is determined primarily by their internal organization-that match specific target properties. By examining kirigami metamaterials, in which dependencies between cuts yield complex design restrictions, we demonstrate that this perceived success in the employment of generative models for metamaterials might be akin to survivorship bias. We assess the performance of the four most popular generative models-the Variational Autoencoder (VAE), the Generative Adversarial Network (GAN), the Wasserstein GAN (WGAN), and the Denoising Diffusion Probabilistic Model (DDPM)-in generating kirigami structures. Prohibiting cut intersections can prevent the identification of an appropriate similarity measure for kirigami metamaterials, significantly impacting the effectiveness of VAE and WGAN, which rely on the Euclidean distance-a metric shown to be unsuitable for considered geometries. This imposes significant limitations on employing modern generative models for the creation of diverse metamaterials.

Machine learning discovery of cost-efficient dry cooler designs for concentrated solar power plants.

Concentrated solar power (CSP) is one of the few sustainable energy technologies that offers day-to-night energy storage. Recent development of the supercritical carbon dioxide (sCO2) Brayton cycle has made CSP a potentially cost-competitive energy source. However, as CSP plants are most efficient in desert regions, where there is high solar irradiance and low land cost, careful design of a dry cooling system is crucial to make CSP practical. In this work, we present a machine learning system to optimize the factory design and configuration of a dry cooling system for an sCO2 Brayton cycle CSP plant. For this, we develop a physics-based simulation of the cooling properties of an air-cooled heat exchanger. The simulator is able to construct a dry cooling system satisfying a wide variety of power cycle requirements (e.g., 10-100 MW) for any surface air temperature. Using this simulator, we leverage recent results in high-dimensional Bayesian optimization to optimize dry cooler designs that minimize lifetime cost for a given location, reducing this cost by 67% compared to recently proposed designs. Our simulation and optimization framework can increase the development pace of economically-viable sustainable energy generation systems.

Machine-Learning-Based Characterization and Inverse Design of Metamaterials.

Metamaterials, characterized by unique structures, exhibit exceptional properties applicable across various domains. Traditional methods like experiments and finite-element methods (FEM) have been extensively utilized to characterize these properties. However, exploring an extensive range of structures using these methods for designing desired structures with excellent properties can be time-intensive. This paper formulates a machine-learning-based approach to expedite predicting effective metamaterial properties, leading to the discovery of microstructures with diverse and outstanding characteristics. The process involves constructing 2D and 3D microstructures, encompassing porous materials, solid-solid-based materials, and fluid-solid-based materials. Finite-element methods are then employed to determine the effective properties of metamaterials. Subsequently, the Random Forest (RF) algorithm is applied for training and predicting effective properties. Additionally, the Aquila Optimizer (AO) method is employed for a multiple optimization task in inverse design. The regression model generates accurate estimation with a coefficient of determination higher than 0.98, a mean absolute percentage error lower than 0.088, and a root mean square error lower than 0.03, indicating that the machine-learning-based method can accurately characterize the metamaterial properties. An optimized structure with a high Young's modulus and low thermal conductivity is designed by AO within the first 30 iterations. This approach accelerates simulating the effective properties of metamaterials and can design microstructures with multiple excellent performances. The work offers guidance to design microstructures in various practical applications such as vibration energy absorbers.

Agile Inverse Design of Polarization-Independent Multi-Functional Reconfiguration Metamaterials Based on Doped VO2.

Increasing attention is being paid to the application potential of multi-functional reconfigurable metamaterials in intelligent communication, sensor networks, homeland security, and other fields. A polarization-independent multi-functional reconfigurable metasurface based on doped vanadium dioxide (VO2) is proposed in this paper. It can be controlled to switch its function among three working modes: electromagnetically induced absorption (EIA), electromagnetically induced transparency (EIT), and asymmetrical absorption. In addition, deep learning tools have greatly accelerated the design of relevant devices. Such devices and the method proposed in this paper have important value in the field of intelligent reconfigurable metamaterials, communication, and sensing.

Inverse Design of Low-Resistivity Ternary Gold Alloys via Interpretable Machine Learning and Proactive Search Progress.

Ternary gold alloys (TGAs) are highly regarded for their excellent electrical properties. Electrical resistivity is a crucial indicator for evaluating the electrical performance of TGAs. To explore new promising TGAs with lower resistivity, we developed a reverse design approach integrating machine learning techniques and proactive searching progress (PSP) method. Compared with other models, the support vector regression (SVR) was determined to be the most optimal model for resistivity prediction. The training and test sets yielded R2 values of 0.73 and 0.77, respectively. The model interpretation indicated that lower electrical resistivity was associated with the following conditions: a van der Waals Radius (Vrt) of 0, a Vr (another van der Waals Radius) of less than 217, and a mass attenuation coefficient of MoKα (Macm) greater than 77.5 cm2g-1. Applying the PSP method, we successfully identified eight candidates whose resistivity was lower than that of the sample with the lowest resistivity in the dataset by more than 53-60%, e.g., Au1.000Cu4.406Pt1.833 and Au1.000Pt2.232In1.502. Finally, the candidates were validated to possess low resistivity through the pattern recognition method.

First-Principles Computational Screening of Two-Dimensional Polar Materials for Photocatalytic Water Splitting.

The band gap constraint of the photocatalyst for overall water splitting limits the utilization of solar energy. A strategy to broaden the range of light absorption is employing a two-dimensional (2D) polar material as photocatalyst, benefiting from the deflection of the energy level due to their intrinsic internal electric field. Here, by using first-principles computational screening, we search for 2D polar semiconductors for photocatalytic water splitting from both ground- and excited-state perspectives. Applying a unique electronic structure model of polar materials, there are 13 photocatalyst candidates for the hydrogen evolution reaction (HER) and 8 candidates for the oxygen evolution reaction (OER) without barrier energies from the perspective of the ground-state free energy variation calculation. In particular, Cu2As4Cl2S3 and Cu2As4Br2S3 can catalyze HER and OER simultaneously, becoming promising photocatalysts for overall water splitting. Furthermore, by combining ground-state band structure calculations with excited-state charge distribution and transfer calculated by linear-response time-dependent density functional theory (LR-TDDFT) and time-dependent ab initio nonadiabatic molecular dynamics (NAMD), respectively, the rationality of the 2D polar material model has been manifested. The intrinsic built-in electric field promotes the separation of charge carriers while suppressing their recombination. Therefore, our computational work provides a high-throughput method to design high-performance photocatalysts for water splitting.

Symmetry-Guided Inverse Design of Self-Assembling Multiscale DNA Origami Tilings.

Recent advances enable the creation of nanoscale building blocks with complex geometries and interaction specificities for self-assembly. This nearly boundless design space necessitates design principles for defining the mutual interactions between multiple particle species to target a user-specified complex structure or pattern. In this article, we develop a symmetry-based method to generate the interaction matrices that specify the assembly of two-dimensional tilings, which we illustrate using equilateral triangles. By exploiting the allowed 2D symmetries, we develop an algorithmic approach by which any periodic 2D tiling can be generated from an arbitrarily large number of subunit species, notably addressing an unmet challenge of engineering 2D crystals with periodicities that can be arbitrarily larger than the subunit size. To demonstrate the utility of our design approach, we encode specific interactions between triangular subunits synthesized by DNA origami and show that we can guide their self-assembly into tilings with a wide variety of symmetries, using up to 12 unique species of triangles. By conjugating specific triangles with gold nanoparticles, we fabricate gold-nanoparticle supracrystals whose lattice parameter spans up to 300 nm. Finally, to generate economical design rules, we compare the design economy of various tilings. In particular, we show that (1) higher symmetries allow assembly of larger unit cells with fewer subunits and (2) linear supracrystals can be designed more economically using linear primitive unit cells. This work provides a simple algorithmic approach to designing periodic assemblies, aiding in the multiscale assembly of supracrystals of nanostructured "meta-atoms" with engineered plasmonic functions.

Tailoring Phonon Dispersion of a Genetically Designed Nanophononic Metasurface.

Phonon engineering at the nanoscale holds immense promise for a myriad of applications. However, the design of phononic devices continues to rely on regular shapes chosen according to long-established simple rules. Here, we demonstrate an inverse design approach to create a two-dimensional phononic metasurface exhibiting a highly anisotropic phonon dispersion along the main axes of the Brillouin zone. A partial hypersonic bandgap of approximately 3.5 GHz is present along one axis, with gap closure along the orthogonal axis. Such a level of control is achieved through genetically optimized unit cells, with shapes exceeding conventional intuition. We experimentally validated our theoretical predictions using Brillouin light scattering, confirming the effectiveness of the inverse design method. Our approach unlocks the potential for automated engineering of phononic metasurfaces with on-demand functionalities, thus leading toward innovative phononic devices beyond the limitations of traditional design paradigms.

Harnessing the Missing Spectral Correlation for Metasurface Inverse Design.

A long-held tenet in computer science asserts that the training of deep learning is analogous to an alchemical furnace, and its "black box" signature brings forth inexplicability. For electromagnetic metasurfaces, the related intelligent applications also get stuck into such a dilemma. Although the past 5 years have witnessed a proliferation of deep learning-based works across complex photonic scenarios, they neglect the already existing but untapped physical laws. Here, the intrinsic correlation between the real and imaginary parts of the spectra are revealed using Kramers-Kronig relations, which is then mimicked by bidirectional information flow in neural network space. Such consideration harnesses the missing spectral connection to extract crucial features effectively. The bidirectional recurrent neural network is benchmarked in metasurface inverse design and compare it with a fully-connected neural network, unidirectional recurrent neural network, and attention-based transformer. Beyond the improved accuracy, the study examines the intermediate information products and physically explains why different network structures yield different performances. The work offers explicable perspectives to utilize physical information in the deep learning field and facilitates many data-intensive research endeavors.

AC-ModNet: Molecular Reverse Design Network Based on Attribute Classification.

Deep generative models are becoming a tool of choice for exploring the molecular space. One important application area of deep generative models is the reverse design of drug compounds for given attributes (solubility, ease of synthesis, etc.). Although there are many generative models, these models cannot generate specific intervals of attributes. This paper proposes a AC-ModNet model that effectively combines VAE with AC-GAN to generate molecular structures in specific attribute intervals. The AC-ModNet is trained and evaluated using the open 250K ZINC dataset. In comparison with related models, our method performs best in the FCD and Frag model evaluation indicators. Moreover, we prove the AC-ModNet created molecules have potential application value in drug design by comparing and analyzing them with medical records in the PubChem database. The results of this paper will provide a new method for machine learning drug reverse design.

Data-driven inverse design of flexible pressure sensors.

Artificial skins or flexible pressure sensors that mimic human cutaneous mechanoreceptors transduce tactile stimuli to quantitative electrical signals. Conventional trial-and-error designs for such devices follow a forward structure-to-property routine, which is usually time-consuming and determines one possible solution in one run. Data-driven inverse design can precisely target desired functions while showing far higher productivity, however, it is still absent for flexible pressure sensors because of the difficulties in acquiring a large amount of data. Here, we report a property-to-structure inverse design of flexible pressure sensors, exhibiting a significantly greater efficiency than the conventional routine. We use a reduced-order model that analytically constrains the design scope and an iterative "jumping-selection" method together with a surrogate model that enhances data screening. As an exemplary scenario, hundreds of solutions that overcome the intrinsic signal saturation have been predicted by the inverse method, validating for a variety of material systems. The success in property design on multiple indicators demonstrates that the proposed inverse design is an efficient and powerful tool to target multifarious applications of flexible pressure sensors, which can potentially advance the fields of intelligent robots, advanced healthcare, and human-machine interfaces.

Tailoring Stress-Strain Curves of Flexible Snapping Mechanical Metamaterial for On-Demand Mechanical Responses via Data-Driven Inverse Design.

By incorporating soft materials into the architecture, flexible mechanical metamaterials enable promising applications, e.g., energy modulation, and shape morphing, with a well-controllable mechanical response, but suffer from spatial and temporal programmability towards higher-level mechanical intelligence. One feasible solution is to introduce snapping structures and then tune their responses by accurately tailoring the stress-strain curves. However, owing to the strongly coupled nonlinearity of structural deformation and material constitutive model, it is difficult to deduce their stress-strain curves using conventional ways. Here, a machine learning pipeline is trained with the finite element analysis data that considers those strongly coupled nonlinearities to accurately tailor the stress-strain curves of snapping metamaterialfor on-demand mechanical response with an accuracy of 97.41%, conforming well to experiment. Utilizing the established approach, the energy absorption efficiency of the snapping-metamaterial-based device can be tuned within the accessible range to realize different rebound heights of a falling ball, and soft actuators can be spatially and temporally programmed to achieve synchronous and sequential actuation with a single energy input. Purely relying on structure designs, the accurately tailored metamaterials increase the devices' tunability/programmability. Such an approach can potentially extend to similar nonlinear scenarios towards predictable or intelligent mechanical responses.

3D Intelligent Cloaked Vehicle Equipped with Thousand-Level Reconfigurable Full-Polarization Metasurfaces.

A crucial aspect in shielding a variety of advanced electronic devices from electromagnetic detection involves controlling the flow of electromagnetic waves, akin to invisibility cloaks. Decades ago, the exploration of transformation optics heralded the dawn of modern invisibility cloaks, which has stimulated immense interest across various physical scenarios. However, most prior research is simplified to low-dimensional and stationary hidden objects, limiting their practical applicability in a dynamically changing world. This study develops a 3D large-scale intelligent cloak capable of remaining undetectable even in non-stationary conditions. By employing thousand-level reconfigurable full-polarization metasurfaces, this work has achieved an exceptionally high degree of freedom in sculpting the scattering waves as desired. Serving as the core computational unit, a hybrid inverse design enables the cloaked vehicle to respond in real-time, with a rapid reaction time of just 70 ms. These experiments integrate the cloaked vehicle with a perception-decision-control-execution system and evaluate its performance under random static positions and dynamic travelling trajectories, achieving a background scattering matching degree of up to 93.3%. These findings establish a general paradigm for the next generation of intelligent meta-devices in real-world settings, potentially paving the way for an era of "Electromagnetic Internet of Things."

Deep Learning-Based Design Method for Acoustic Metasurface Dual-Feature Fusion.

Existing research in metasurface design was based on trial-and-error high-intensity iterations and requires deep acoustic expertise from the researcher, which severely hampered the development of the metasurface field. Using deep learning enabled the fast and accurate design of hypersurfaces. Based on this, in this paper, an integrated learning approach was first utilized to construct a model of the forward mapping relationship between the hypersurface physical structure parameters and the acoustic field, which was intended to be used for data enhancement. Then a dual-feature fusion model (DFCNN) based on a convolutional neural network was proposed, in which the first feature was the high-dimensional nonlinear features extracted using a data-driven approach, and the second feature was the physical feature information of the acoustic field mined using the model. A convolutional neural network was used for feature fusion. A genetic algorithm was used for network parameter optimization. Finally, generalization ability verification was performed to prove the validity of the network model. The results showed that 90% of the integrated learning models had an error of less than 3 dB between the real and predicted sound field data, and 93% of the DFCNN models could achieve an error of less than 5 dB in the local sound field intensity.

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.