Biomimetic ultra-broadband perfect absorbers optimised with reinforcement learning

Machine Learning-Driven Design Optimization of Buckling-Induced Quasi-Zero Stiffness Metastructures for Low-Frequency Vibration Isolation

Metastructures, artificial arrangements of micro/macrostructures, possess unique properties and are of significant interest in aerospace, stealth technology, and various other applications. Recent studies have focused on quasi-zero stiffness metastructures, providing an outstanding vibration isolation capability. However, existing methods are constrained to low preloads and lack the consideration of structural analysis, despite their intended use in practical structures. This study introduces metastructures with quasi-zero stiffness characteristics under high preloads by inducing local buckling. An optimization framework combining deep reinforcement learning and finite-element analysis is employed to derive an optimal model that considers both structural safety and quasi-zero stiffness characteristics. To validate the optimization results, quasi-zero stiffness metastructures are fabricated via 3D printing, and compression and vibration experiments are conducted. The fabricated metastructures exhibit quasi-zero stiffness characteristics under a high target preload along with outstanding vibration reduction performance, even in the low-frequency range.

Hybrid supervised and reinforcement learning for the design and optimization of nanophotonic structures

From higher computational efficiency to enabling the discovery of novel and complex structures, deep learning has emerged as a powerful framework for the design and optimization of nanophotonic circuits and components. However, both data-driven and exploration-based machine learning strategies have limitations in their effectiveness for nanophotonic inverse design. Supervised machine learning approaches require large quantities of training data to produce high-performance models and have difficulty generalizing beyond training data given the complexity of the design space. Unsupervised and reinforcement learning-based approaches on the other hand can have very lengthy training or optimization times associated with them. Here we demonstrate a hybrid supervised learning and reinforcement learning approach to the inverse design of nanophotonic structures and show this approach can reduce training data dependence, improve the generalizability of model predictions, and significantly shorten exploratory training times. The presented strategy thus addresses several contemporary deep learning-based challenges, while opening the door for new design methodologies that leverage multiple classes of machine learning algorithms to produce more effective and practical solutions for photonic design.

More Than 30 000-fold Field Enhancement of Terahertz Nanoresonators Enabled by Rapid Inverse Design

The rapid development of 6G communications using terahertz (THz) electromagnetic waves has created a demand for highly sensitive THz nanoresonators capable of detecting these waves. Among the potential candidates, THz nanogap loop arrays show promising characteristics but require significant computational resources for accurate simulation. This requirement arises because their unit cells are 10 times smaller than millimeter wavelengths, with nanogap regions that are 1 000 000 times smaller. To address this challenge, we propose a rapid inverse design method using physics-informed machine learning, employing double deep Q-learning with an analytical model of the THz nanogap loop array. In ∼39 h on a middle-level personal computer, our approach identifies the optimal structure through 200 000 iterations, achieving an experimental electric field enhancement of 32 000 at 0.2 THz, 300% stronger than prior results. Our analytical model-based approach significantly reduces the amount of computational resources required, offering a practical alternative to numerical simulation-based inverse design for THz nanodevices.

Deep learning-based inverse design optimization of efficient multilayer thermal emitters in the near-infrared broad spectrum

This study proposes a deep learning architecture for automatic modeling and optimization of multilayer thin film structures to address the need for specific spectral emitters and achieve rapid design of geometric parameters for an ideal spectral response. Multilayer film structures are ideal thermal emitter structures for thermophotovoltaic application systems because they combine the advantages of large area preparation and controllable costs. However, achieving good spectral response performance requires stacking more layers, which makes it more difficult to achieve fine spectral inverse design using forward calculation of the dimensional parameters of each layer of the structure. Deep learning is the main method for solving complex data-driven problems in artificial intelligence and provides an efficient solution for the inverse design of structural parameters for a target waveband. In this study, an eight-layer thin film structure composed of SiO₂/Ti and SiO₂/W is rapidly reverse engineered using a deep learning method to achieve a structural design with an emissivity better than 0.8 in the near-infrared band. Additionally, an eight-layer thin film structure composed of 3 × 3 cm SiO₂/Ti is experimentally measured using magnetron sputtering, and the emissivity in the 1-4 µm band was better than 0.68. This research provides implications for the design and application of micro-nano structures, can be widely used in the fields of thermal imaging and thermal regulation, and will contribute to developing a new paradigm for optical nanophotonic structures with a fast target-oriented inverse design of structural parameters, such as required spectral emissivity, phase, and polarization.

Super broadband mid-infrared absorbers with ultrathin folded highly-lossy films

Super broadband optical absorbers with ultrathin films have been keenly pursued for a long time. Although highly lossy materials with sharp light attenuation have the potential to become super absorbers, a large percent of light from free space is inevitably reflected back for the distinct impedance mismatch. Here, a simple strategy, of which reducing the thickness of highly-lossy thin films to minish reflectance and simultaneously folding the ultrathin films to make light multiple pass through, is proposed to obtain super broadband mid-infrared absorbers with ultrathin films. Along this line, the absorbers were prepared by depositing Al-doped ZnO film on scaffolds consisted of alumina spherical shells, whose substrates were opaque. When the thickness of Al-doped ZnO is 43 nm and the layer number of scaffolds is three, a maximum average absorptance was achieved as 97.6% over the wavelength range from 3 to 15 μm. Applying this strategy on polished Al foil, excellent infrared camouflage performance on human-body background was demonstrated. Featured by the strong broadband optical absorption with ultrathin films, flexible access to multiple substrates and low-cost procedures, this approach has the potential in widespread applications of infrared thermal emitters and optoelectronic devices.

Intelligent design of the chiral metasurfaces for flexible targets: combining a deep neural network with a policy proximal optimization algorithm

Recently, deep reinforcement learning (DRL) for metasurface design has received increased attention for its excellent decision-making ability in complex problems. However, time-consuming numerical simulation has hindered the adoption of DRL-based design method. Here we apply the Deep learning-based virtual Environment Proximal Policy Optimization (DE-PPO) method to design the 3D chiral plasmonic metasurfaces for flexible targets and model the metasurface design process as a Markov decision process to help the training. A well trained DRL agent designs chiral metasurfaces that exhibit the optimal absolute circular dichroism value (typically, ∼ 0.4) at various target wavelengths such as 930 nm, 1000 nm, 1035 nm, and 1100 nm with great time efficiency. Besides, the training process of the PPO agent is exceptionally fast with the help of the deep neural network (DNN) auxiliary virtual environment. Also, this method changes all variable parameters of nanostructures simultaneously, reducing the size of the action vector and thus the output size of the DNN. Our proposed approach could find applications in efficient and intelligent design of nanophotonic devices.

Liquid crystal-powered Mie resonators for electrically tunable photorealistic color gradients and dark blacks

Taking inspiration from beautiful colors in nature, structural colors produced from nanostructured metasurfaces have shown great promise as a platform for bright, highly saturated, and high-resolution colors. Both plasmonic and dielectric materials have been employed to produce static colors that fulfil the required criteria for high-performance color printing, however, for practical applications in dynamic situations, a form of tunability is desirable. Combinations of the additive color palette of red, green, and blue enable the expression of further colors beyond the three primary colors, while the simultaneous intensity modulation allows access to the full color gamut. Here, we demonstrate an electrically tunable metasurface that can represent saturated red, green, and blue pixels that can be dynamically and continuously controlled between on and off states using liquid crystals. We use this to experimentally realize ultrahigh-resolution color printing, active multicolor cryptographic applications, and tunable pixels toward high-performance full-color reflective displays.

Machine-learning reinforcement for optimizing multilayered thin films: applications in designing broadband antireflection coatings

The design and fabrication of nanoscale multilayered thin films play an essential role in regulating the operation efficiency of sensitive optical sensors and filters. In this paper, we introduce a packaged tool that employs flexible electromagnetic calculation software with machine learning in order to find the optimized double-band antireflection coatings in intervals of wavelength from 3 to 5 µm and 8 to 12 µm. Instead of computing or modeling an extremely enormous set of thin film structures, this tool enhanced with machine learning can swiftly predict the optical properties of a given structure with >99.7% accuracy and a substantial reduction in computation costs. Furthermore, the tool includes two learning methods that can infer a global optimal structure or suitable local optimal ones. Specifically, these well-trained models provide the highest accurate double-band average transmission coefficient combined with the lowest number of layers or the thinnest total thickness starting from a reference multilayered structure. Finally, the more sophisticated enhancement method, called the double deep Q-learning network, exhibited the best performance in finding optimal antireflective multilayered structures with the highest double-band average transmission coefficient of about 98.95%.

Designing high efficiency asymmetric polarization converter for blue light: a deep reinforcement learning approach

Conventional polarization converters selectively preserve the required polarization state by absorbing, reflecting or refracting light with unwanted polarization state, leading to a theoretical transmittance limit of 0.5 for linearly polarized light with unpolarized light incidence. In the meanwhile, due to the high-dimensional structure parameters and time-consuming numerical simulations, designing a converter with satisfactory performance is extremely difficult and closely relies on human experts' experiences and manual intervention. To address these open issues, in this paper, we first propose an asymmetric polarization converter which shows both high transmittance for one linearly polarized light and high transmittance for the orthogonal linearly polarized light with 90° rotation in blue wavelength region. To maximize the performance of the proposed structure, a deep reinforcement learning approach is further proposed to search for the optimal set of structure parameters. To avoid overly long training time by using the numerical simulations as environment, a deep neural network is proposed to serve as the surrogate model, where a prediction accuracy of 96.6% and 95.5% in two orthogonal polarization directions is achieved with micro-second grade simulation time respectively. With the optimized structure, the average transmittance is larger than 0.5 for the wavelength range from 444 to 466 nm with a maximum of 0.605 at 455 nm, which is 21% higher than the theoretical limit of 0.5 of conventional polarization converters.

Three-dimensional artificial chirality towards low-cost and ultra-sensitive enantioselective sensing

Artificial chiral structures have potential applications in the field of enantioselective signal sensing. Advanced nanofabrication methods enable a large diversity in geometric structures and broad selectivity of materials, which can be exploited to manufacture artificial three-dimensional chiral structures. Various chiroptical phenomena exploiting spin and orbital angular momentum at the nanoscale have been continuously exploited as a way to effectively detect enantiomers. This review introduces precisely controlled bottom-up and large-area top-down metamaterial fabrication methods to solve the limitations of high manufacturing cost and low production speed. Particle synthesis, self-assembly, glanced angled vapor deposition, and three-dimensional plasmonic nanostructure printing are introduced. Furthermore, emerging sensitive chiral sensing methods such as cavity-enhanced chirality, photothermal circular dichroism, and helical dichroism of single particles are discussed. The continuous progress of nanofabrication technology presents the strong potential for developing artificial chiral structures for applications in biomedical, pharmaceutical, nanophotonic systems.

Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning

Using a model heat engine, we show that neural-network-based reinforcement learning can identify thermodynamic trajectories of maximal efficiency. We consider both gradient and gradient-free reinforcement learning. We use an evolutionary learning algorithm to evolve a population of neural networks, subject to a directive to maximize the efficiency of a trajectory composed of a set of elementary thermodynamic processes; the resulting networks learn to carry out the maximally efficient Carnot, Stirling, or Otto cycles. When given an additional irreversible process, this evolutionary scheme learns a previously unknown thermodynamic cycle. Gradient-based reinforcement learning is able to learn the Stirling cycle, whereas an evolutionary approach achieves the optimal Carnot cycle. Our results show how the reinforcement learning strategies developed for game playing can be applied to solve physical problems conditioned upon path-extensive order parameters.

Multilevel Absorbers via the Integration of Undoped and Tungsten-Doped Multilayered Vanadium Dioxide Thin Films

Reconfigurable light absorbers have attracted much attention by providing additional optical responses and expanding the number of degrees of freedom in security applications. Fabry-Pèrot absorbers based on phase change materials with tunable properties can be implemented over large scales without the need for additional steps such as lithography, while exhibiting reconfigurable optical responses. However, a fundamental limitation of widely used phase change materials such as vanadium dioxide and germanium-antimony-tellurium-based chalcogenide glasses is that they have only two distinct phases; therefore, only two different states of optical properties are available. Here, we experimentally demonstrate active multilevel absorbers that are tuned by controlling the external temperature. This is produced by creating large-scale lithography-free multilayer structures with both undoped and tungsten-doped solution-processed monoclinic-phase vanadium dioxide thin films. The doping of vanadium dioxide with tungsten allows for the modulation of the phase-transition temperature, which results in an extra degree of freedom and therefore an additional step for the tunable properties. The proposed multilevel absorber is designed and characterized both numerically and experimentally. Such large-scale multilevel tunable absorbers realized with nanoparticle-based solution fabrication techniques are expected to open the way for advanced thermo-optical cryptographic devices based on tunable reflective coloration and near-infrared absorption.

Optical meta-waveguides for integrated photonics and beyond

The growing maturity of nanofabrication has ushered massive sophisticated optical structures available on a photonic chip. The integration of subwavelength-structured metasurfaces and metamaterials on the canonical building block of optical waveguides is gradually reshaping the landscape of photonic integrated circuits, giving rise to numerous meta-waveguides with unprecedented strength in controlling guided electromagnetic waves. Here, we review recent advances in meta-structured waveguides that synergize various functional subwavelength photonic architectures with diverse waveguide platforms, such as dielectric or plasmonic waveguides and optical fibers. Foundational results and representative applications are comprehensively summarized. Brief physical models with explicit design tutorials, either physical intuition-based design methods or computer algorithms-based inverse designs, are cataloged as well. We highlight how meta-optics can infuse new degrees of freedom to waveguide-based devices and systems, by enhancing light-matter interaction strength to drastically boost device performance, or offering a versatile designer media for manipulating light in nanoscale to enable novel functionalities. We further discuss current challenges and outline emerging opportunities of this vibrant field for various applications in photonic integrated circuits, biomedical sensing, artificial intelligence and beyond.

Inverse design of the MMI power splitter by asynchronous double deep Q-learning

The asynchronous double deep Q-learning (A-DDQN) method is proposed to design the multi-mode interference (MMI) power splitters for low insertion loss and wide bandwidth from 1200 to 1650 nm wavelength range. By using A-DDQN to guide hole etchings in the interference region of MMI, the target splitting ratio (SR) can be obtained with much less CPU time (about 10 hours for one design) and more effective utilization of the computational resources in asynchronous/parallel manner. Also, this method can simplify the design by using relatively few holes to obtain the same SR with small return loss.

Reinforcement learning applied to metamaterial design

This paper presents a semi-analytical method of suppressing acoustic scattering using reinforcement learning (RL) algorithms. We give a RL agent control over design parameters of a planar configuration of cylindrical scatterers in water. These design parameters control the position and radius of the scatterers. As these cylinders encounter an incident acoustic wave, the scattering pattern is described by a function called total scattering cross section (TSCS). Through evaluating the gradients of TSCS and other information about the state of the configuration, the RL agent perturbatively adjusts design parameters, considering multiple scattering between the scatterers. As each adjustment is made, the RL agent receives a reward negatively proportional to the root mean square of the TSCS across a range of wavenumbers. Through maximizing its reward per episode, the agent discovers designs with low scattering. Specifically, the double deep Q-learning network and the deep deterministic policy gradient algorithms are employed in our models. Designs discovered by the RL algorithms performed well when compared to a state-of-the-art optimization algorithm using fmincon.

Nanoimprint lithography for high-throughput fabrication of metasurfaces

Metasurfaces are composed of periodic sub-wavelength nanostructures and exhibit optical properties that are not found in nature. They have been widely investigated for optical applications such as holograms, wavefront shaping, and structural color printing, however, electron-beam lithography is not suitable to produce large-area metasurfaces because of the high fabrication cost and low productivity. Although alternative optical technologies, such as holographic lithography and plasmonic lithography, can overcome these drawbacks, such methods are still constrained by the optical diffraction limit. To break through this fundamental problem, mechanical nanopatterning processes have been actively studied in many fields, with nanoimprint lithography (NIL) coming to the forefront. Since NIL replicates the nanopattern of the mold regardless of the diffraction limit, NIL can achieve sufficiently high productivity and patterning resolution, giving rise to an explosive development in the fabrication of metasurfaces. In this review, we focus on various NIL technologies for the manufacturing of metasurfaces. First, we briefly describe conventional NIL and then present various NIL methods for the scalable fabrication of metasurfaces. We also discuss recent applications of NIL in the realization of metasurfaces. Finally, we conclude with an outlook on each method and suggest perspectives for future research on the high-throughput fabrication of active metasurfaces.

Manipulating atomic defects in plasmonic vanadium dioxide for superior solar and thermal management

Vanadium dioxide (VO₂) is a unique active plasmonic material due to its intrinsic metal-insulator transition, remaining less explored. Herein, we pioneer a method to tailor the VO₂ surface plasmon by manipulating its atomic defects and establish a universal quantitative understanding based on seven representative defective VO₂ systems. Record high tunability is achieved for the localized surface plasmon resonance (LSPR) energy (0.66-1.16 eV) and transition temperature range (40-100 °C). The Drude model and density functional theory reveal that the charge of cations plays a dominant role in the numbers of valence electrons to determine the free electron concentration. We further demonstrate their superior performances in extensive unconventional plasmonic applications including energy-saving smart windows, wearable camouflage devices, and encryption inks.

Full and gradient structural colouration by lattice amplified gallium nitride Mie-resonators

The hybridised resonances between Mie-scatterers and lattice resonances, i.e. quasi-guided mode resonances, are investigated. The scattering of the Mie-resonators is improved by the first order of transmitted diffracted light which is coupled to the lattice formed by the Mie-resonators. The conditions of coupling are dependent on the refractive index of the substrate and the effective refractive index of the unit cell of the resonators. Based on the momentum matching conditions, the cut-off wavelength of coupling and the amount of the amplification can be controlled. As a proof-of-concept application of this framework, gallium nitride metasurfaces are designed to produce metasurfaces that display structural colour. Palettes of full spectral colour and gradients are successfully demonstrated. The hue of the colour can be controlled by changing the periodicity of the unit cell at a fixed filling ratio of Mie-scatterer radius to unit cell periodicity, since the increase in periodicity redshifts the cut-off wavelength of the lattice resonance conditions, identified as the Rayleigh anomaly. The brightness of the colour can be tuned by adjusting the filling ratio of the unit cell. Consequently, the proposed framework may provide a fundamental guideline to design spectral filters made up of low-index Mie-scatterers for various applications.

Deep Q-network to produce polarization-independent perfect solar absorbers: a statistical report

Using reinforcement learning, a deep Q-network was used to design polarization-independent, perfect solar absorbers. The deep Q-network selected the geometrical properties and materials of a symmetric three-layer metamaterial made up of circular rods on top of two films. The combination of all the possible permutations gives around 500 billion possible designs. In around 30,000 steps, the deep Q-network was able to produce 1250 structures that have an integrated absorption of higher than 90% in the visible region, with a maximum of 97.6% and an integrated absorption of less than 10% in the 8-13 µm wavelength region, with a minimum of 1.37%. A statistical analysis of the distribution of materials and geometrical parameters that make up the solar absorbers is presented.

Scalable and High-Throughput Top-Down Manufacturing of Optical Metasurfaces

Metasurfaces have shown promising potential to miniaturize existing bulk optical components thanks to their extraordinary optical properties and ultra-thin, small, and lightweight footprints. However, the absence of proper manufacturing methods has been one of the main obstacles preventing the practical application of metasurfaces and commercialization. Although a variety of fabrication techniques have been used to produce optical metasurfaces, there are still no universal scalable and high-throughput manufacturing methods that meet the criteria for large-scale metasurfaces for device/product-level applications. The fundamentals and recent progress of the large area and high-throughput manufacturing methods are discussed with practical device applications. We systematically classify various top-down scalable patterning techniques for optical metasurfaces: firstly, optical and printing methods are categorized and then their conventional and unconventional (emerging/new) techniques are discussed in detail, respectively. In the end of each section, we also introduce the recent developments of metasurfaces realized by the corresponding fabrication methods.

A Thermal Tuning Meta-Duplex-Lens (MDL): Design and Characterization

Multifunctional metasurfaces play an important role in the development of integrated optical paths. However, some of the realizations of current multifunctional metasurface devices depend on polarization selectivity, and others change the polarization state of the outgoing light. Here, based on vanadium dioxide (VO₂) phase change material, a strategy to design a meta-duplex-lens (MDL) is proposed and numerical simulation calculations demonstrate that at low temperature (about 300 K), VO₂ behaves as a dielectric so that the MDL can act as a transmission lens (transmission efficiency of 87.6%). Conversely, when VO₂ enters the metallic state (about 355 K), the MDL has the ability to reflect and polymerize electromagnetic waves and works as a reflection lens (reflection efficiency of 85.1%). The dielectric waveguide and gap-surface plasmon (GSP) theories are used in transmission and reflection directions, respectively. In order to satisfy the coverage of the phase gradient in the range of 2π in both cases, we set the antenna as a nanopillar with a high aspect ratio. It is notable that, via symmetrical antennas acting in concert with VO₂ phase change material, the polarization states of both the incident light and the outgoing light are not changed. This reversible tuning will play a significant role in the fields of imaging, optical storage devices, communication, sensors, etc.

Moth-eye shaped on-demand broadband and switchable perfect absorbers based on vanadium dioxide

Two biomimetic, moth-eye structure, perfect absorbers in the visible and near infrared regions are introduced and investigated. The moth-eye structure is made up of vanadium oxide (VO₂), which is a phase change material that changes from an insulator state to a metallic state at around 85 °C. The VO₂ structure sits on top of a sapphire (Al₂O₃) dielectric spacer layer, above a gold (Au) back reflector. Two perfect absorbers are designed, one with perfect absorption over an ultra-broadband range between 400 and 1,600 nm, for both the insulating and metallic phases, while the second can switch between being a perfect absorber or not in the range 1,000 and 1,600 nm. The absorption profiles and electric and magnetic fields are examined and discussed to provide insight into how absorbers function in the four different situations.

Topological encoding method for data-driven photonics inverse design

Data-driven approaches have been proposed as effective strategies for the inverse design and optimization of photonic structures in recent years. In order to assist data-driven methods for the design of topology of photonic devices, we propose a topological encoding method that transforms photonic structures represented by binary images to a continuous sparse representation. This sparse representation can be utilized for dimensionality reduction and dataset generation, enabling effective analysis and optimization of photonic topologies with data-driven approaches. As a proof of principle, we leverage our encoding method for the design of two dimensional non-paraxial diffractive optical elements with various diffraction intensity distributions. We proved that our encoding method is able to assist machine-learning-based inverse design approaches for accurate and global optimization.