Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials

Metasurface-Based Molecular Biosensing Aided by Artificial Intelligence

Molecular spectroscopy provides unique information on the internal structure of biological materials by detecting the characteristic vibrational signatures of their constituent chemical bonds at infrared frequencies. Nanophotonic antennas and metasurfaces have driven this concept towards few-molecule sensitivity by confining incident light into intense hot spots of the electromagnetic fields, providing strongly enhanced light-matter interaction. In this Minireview, recently developed molecular biosensing approaches based on the combination of dielectric metasurfaces and imaging detection are highlighted in comparison to traditional plasmonic geometries, and the unique potential of artificial intelligence techniques for nanophotonic sensor design and data analysis is emphasized. Because of their spectrometer-less operation principle, such imaging-based approaches hold great promise for miniaturized biosensors in practical point-of-care or field-deployable applications.

Double-deep Q-learning to increase the efficiency of metasurface holograms

We use a double deep Q-learning network (DDQN) to find the right material type and the optimal geometrical design for metasurface holograms to reach high efficiency. The DDQN acts like an intelligent sweep and could identify the optimal results in ~5.7 billion states after only 2169 steps. The optimal results were found between 23 different material types and various geometrical properties for a three-layer structure. The computed transmission efficiency was 32% for high-quality metasurface holograms; this is two times bigger than the previously reported results under the same conditions. The found structure is transmission-type and polarization-independent and works in the visible region.

Deep Learning Approach for Enhanced Detection of Surface Plasmon Scattering

A deep learning approach has been taken to improve detection characteristics of surface plasmon microscopy (SPM) of light scattering. Deep learning based on the convolutional neural network algorithm was used to estimate the effect of scattering parameters, mainly the number of scatterers. The improvement was assessed on a quantitative basis by applying the approach to SPM images formed by coherent interference of scatterers. It was found that deep learning significantly improves the accuracy over conventional detection: the enhancement in the accuracy was shown to be significantly higher by almost 6 times and useful for scattering by polydisperse mixtures. This suggests that deep learning can be used to find scattering objects effectively in the noisy environment. Furthermore, deep learning can be extended directly to label-free molecular detection assays and provide considerably improved detection in imaging and microscopy techniques.

Arbitrarily routed mode-division multiplexed photonic circuits for dense integration

On-chip integrated mode-division multiplexing (MDM) is an emerging technique for large-capacity data communications. In the past few years, while several configurations have been developed to realize on-chip MDM circuits, their practical applications are significantly hindered by the large footprint and inter-mode cross talk. Most importantly, the high-speed MDM signal transmission in an arbitrarily routed circuit is still absent. Herein, we demonstrate the MDM circuits based on digitized meta-structures which have extremely compact footprints. 112 Gbit/s signals encoded on each mode are arbitrarily routed through the circuits consisting of many sharp bends and compact crossings with a bit error rate under forward error correction limit. This will significantly improve the integration density and benefit various on-chip multimode optical systems.

On-chip mode-division multiplexing has many challenges including crosstalk, losses, and footprint.  Here the authors use a nanohole metastructure to create multiplexed bends and crossings for photonic data communications circuit routing with high density that combats these challenges.

Simultaneous Inverse Design of Materials and Structures via Deep Learning: Demonstration of Dipole Resonance Engineering Using Core-Shell Nanoparticles

Recent introduction of data-driven approaches based on deep-learning technology has revolutionized the field of nanophotonics by allowing efficient inverse design methods. In this paper, a simultaneous inverse design of materials and structure parameters of core-shell nanoparticles is achieved for the first time using deep learning of a neural network. A neural network to learn the correlation between the extinction spectra of electric and magnetic dipoles and core-shell nanoparticle designs, which include material information and shell thicknesses, is developed and trained. We demonstrate deep-learning-assisted inverse design of core-shell nanoparticles for (1) spectral tuning electric dipole resonances, (2) finding spectrally isolated pure magnetic dipole resonances, and (3) finding spectrally overlapped electric dipole and magnetic dipole resonances. Our finding paves the way for the rapid development of nanophotonics by allowing a practical utilization of deep-learning technology for nanophotonic inverse design.

Deep Learning in Chemistry

Machine learning enables computers to address problems by learning from data. Deep learning is a type of machine learning that uses a hierarchical recombination of features to extract pertinent information and then learn the patterns represented in the data. Over the last eight years, its abilities have increasingly been applied to a wide variety of chemical challenges, from improving computational chemistry to drug and materials design and even synthesis planning. This review aims to explain the concepts of deep learning to chemists from any background and follows this with an overview of the diverse applications demonstrated in the literature. We hope that this will empower the broader chemical community to engage with this burgeoning field and foster the growing movement of deep learning accelerated chemistry.

Plasmonic colours predicted by deep learning

Picosecond laser pulses have been used as a surface colouring technique for noble metals, where the colours result from plasmonic resonances in the metallic nanoparticles created and redeposited on the surface by ablation and deposition processes. This technology provides two datasets which we use to train artificial neural networks, data from the experiment itself (laser parameters vs. colours) and data from the corresponding numerical simulations (geometric parameters vs. colours). We apply deep learning to predict the colour in both cases. We also propose a method for the solution of the inverse problem – wherein the geometric parameters and the laser parameters are predicted from colour – using an iterative multivariable inverse design method.

Smart inverse design of graphene-based photonic metamaterials by an adaptive artificial neural network

The burgeoning research of graphene and other 2D materials enables many unprecedented metamaterials and metadevices for applications on nanophotonics. The design of on-demand graphene-based metamaterials often calls for the solution of a complex inverse problem within a small sampling space, which highly depends on the rich experiences from researchers of nanophotonics. Conventional optimization algorithms could be used for this inverse design, but they converge to local optimal solutions and take significant computational costs with increased nanostructure parameters. Here, we establish a deep learning method based on an adaptive batch-normalized neural network, aiming to implement smart and rapid inverse design for graphene-based metamaterials with on-demand optical responses. This method allows a quick converging speed with high precision and low computational consumption. As typical complex proof-of-concept examples, the optical metamaterials consisting of graphene/dielectric alternating multilayers are chosen to demonstrate the validity of our design paradigm. Our method demonstrates a high prediction accuracy of over 95% after very few training epochs. A universal programming package is developed to achieve the design goals of graphene-based metamaterials with low absorption and near unity absorption, respectively. Our work may find important design applications in the field of nanoscale photonics based on graphene and other 2D materials.

From Single-Dimensional to Multidimensional Manipulation of Optical Waves with Metasurfaces

Metasurfaces, 2D artificial arrays of subwavelength elements, have attracted great interest from the optical scientific community in recent years because they provide versatile possibilities for the manipulation of optical waves and promise an effective way for miniaturization and integration of optical devices. In the past decade, the main efforts were focused on the realization of single-dimensional (amplitude, frequency, polarization, or phase) manipulation of optical waves. Compared to the metasurfaces with single-dimensional manipulation, metasurfaces with multidimensional manipulation of optical waves show significant advantages in many practical application areas, such as optical holograms, sub-diffraction imaging, and the design of integrated multifunctional optical devices. Nowadays, with the rapid development of nanofabrication techniques, the research of metasurfaces has been inevitably developed from single-dimensional manipulation toward multidimensional manipulation of optical waves, which greatly boosts the application of metasurfaces and further paves the way for arbitrary design of optical devices. Herein, the recent advances in metasurfaces are briefly reviewed and classified from the viewpoint of different dimensional manipulations of optical waves. Single-dimensional manipulation and 2D manipulation of optical waves with metasurfaces are discussed systematically. In conclusion, an outlook and perspectives on the challenges and future prospects in these rapidly growing research areas are provided.

Intelligent nanophotonics: merging photonics and artificial intelligence at the nanoscale

Nanophotonics has been an active research field over the past two decades, triggered by the rising interests in exploring new physics and technologies with light at the nanoscale. As the demands of performance and integration level keep increasing, the design and optimization of nanophotonic devices become computationally expensive and time-inefficient. Advanced computational methods and artificial intelligence, especially its subfield of machine learning, have led to revolutionary development in many applications, such as web searches, computer vision, and speech/image recognition. The complex models and algorithms help to exploit the enormous parameter space in a highly efficient way. In this review, we summarize the recent advances on the emerging field where nanophotonics and machine learning blend. We provide an overview of different computational methods, with the focus on deep learning, for the nanophotonic inverse design. The implementation of deep neural networks with photonic platforms is also discussed. This review aims at sketching an illustration of the nanophotonic design with machine learning and giving a perspective on the future tasks.

Optimisation of colour generation from dielectric nanostructures using reinforcement learning

Recently, a novel machine learning model has emerged in the field of reinforcement learning known as deep Q-learning. This model is capable of finding the best possible solution in systems consisting of millions of choices, without ever experiencing it before, and has been used to beat the best human minds at complex games such as, Go and chess, which both have a huge number of possible decisions and outcomes for each move. With a human-level intelligence, it has solved the problems that no other machine learning model has done before. Here, we show the steps needed for implementing this model to an optical problem. We investigate the colour generation by dielectric nanostructures and show that this model can find geometrical properties that can generate much purer red, green and blue colours compared to previously reported results. The model found these results in 9000 steps from a possible 34.5 million solutions. This technique can easily be extended to predict and optimise the design parameters for other optical structures.

Deep Neural Network Inverse Design of Integrated Photonic Power Splitters

Predicting physical response of an artificially structured material is of particular interest for scientific and engineering applications. Here we use deep learning to predict optical response of artificially engineered nanophotonic devices. In addition to predicting forward approximation of transmission response for any given topology, this approach allows us to inversely approximate designs for a targeted optical response. Our Deep Neural Network (DNN) could design compact (2.6 × 2.6 μm²) silicon-on-insulator (SOI)-based 1 × 2 power splitters with various target splitting ratios in a fraction of a second. This model is trained to minimize the reflection (to smaller than ~ −20 dB) while achieving maximum transmission efficiency above 90% and target splitting specifications. This approach paves the way for rapid design of integrated photonic components relying on complex nanostructures.

Finding the optical properties of plasmonic structures by image processing using a combination of convolutional neural networks and recurrent neural networks

Image processing can be used to extract meaningful optical results from images. Here, from images of plasmonic structures, we combined convolutional neural networks with recurrent neural networks to extract the absorption spectra of structures. To provide the data required for the model, we performed 100,000 simulations with similar setups and random structures. In designing this deep network, we created a model that can predict the absorption response of any structure with a similar setup. We used convolutional neural networks to collect spatial information from the images, and then, we used that data and recurrent neural networks to teach the model to predict the relationship between the spatial information and the absorption spectrum. Our results show that this image processing method is accurate and can be used to replace time- and computationally-intensive numerical simulations. The trained model can predict the optical results in less than a second without the need for a strong computing system. This technique can be easily extended to cover different structures and extract any other optical properties.

Optimization of photonic crystal nanocavities based on deep learning

An approach to optimizing the Q factors of two-dimensional photonic crystal (2D-PC) nanocavities based on deep learning is hereby proposed and demonstrated. We prepare a data set consisting of 1000 nanocavities generated by randomly displacing the positions of many air holes in a base nanocavity and calculate their Q factors using a first-principles method. We train a four-layer neural network including a convolutional layer to recognize the relationship between the air holes' displacements and the Q factors using the prepared data set. After the training, the neural network is able to estimate the Q factors from the air holes' displacements with an error of 13% in standard deviation. Crucially, the trained neural network can estimate the gradient of the Q factor with respect to the air holes' displacements very quickly using back-propagation. A nanocavity structure with an extremely high Q factor of 1.58 × 10⁹ was successfully obtained by optimizing the positions of 50 holes over ~10⁶ iterations, taking advantage of the very fast evaluation of the gradient in high-dimensional parameter spaces. The obtained Q factor is more than one order of magnitude higher than that of the base cavity and more than twice that of the highest Q factors reported so far for cavities with similar modal volumes. This approach can optimize 2D-PC structures over a parameter space of a size unfeasibly large for previous optimization methods that were based solely on direct calculations. We believe that this approach is also useful for improving other optical characteristics.

Near-infrared chiral plasmonic metasurface absorbers

Chirality plays an essential role in the fields of biology, medicine and physics. However, natural materials exhibit very weak chiroptical response. In this paper, near-infrared chiral plasmonic metasurface absorbers are demonstrated to selectively absorb either the left-handed or right-handed circularly polarized light for achieving large circular dichroism (CD) across the wavelength range from 1.3 µm to 1.8 µm. It is shown that the maximum chiral absorption can reach to 0.87 and that the maximum CD in absorption is around 0.70. The current chiral metasurface design is able to achieve strong chiroptical response, which also leads to high thermal CD for the local temperature increase. The high-contrast reflective chiral images are also realized with the designed metasurface absorbers. The demonstrated chiral metasurface absorbers can be applied in many areas, such as optical filters, thermal energy harvesting, optical communication, and chiral imaging.

Five-fold plasmonic Fano resonances with giant bisignate circular dichroism

Chiral metamaterials with versatile designs can exhibit orders of magnitude enhancement in chiroptical responses compared with that of the natural chiral media. Here, we propose an ease-of-fabrication three-dimensional (3D) chiral metamaterial consisting of vertical asymmetric plate-shape resonators along a planar air hole array with extraordinary optical transmission. It is theoretically shown that such chiral metamaterials simultaneously support five-fold plasmonic Fano resonance states and exhibit significant bisignate circular dichroism (CD) with amplitude as large as 0.8 due to the distinctive local electric field distributions. More interestingly, a "bridge" in the proposed double-plate-based architectures can act as a flipped ruler that is able to continuously manipulate optical chirality including the handedness-selective enhancement and the switching of CD signals. Importantly, the proposed designs have been readily fabricated by using a focused-ion-beam irradiation-induced folding technique and they consistently exhibited five-fold Fano resonances with strong CD effects in experiments. The studies are helpful for the understanding, designing and improvement of chiral optical systems towards potential applications such as ultrasensitive biosensing, polarimetric imaging, quantum information processing, etc.