Complex nanophotonic structures hold the potential to deliver exquisitely tailored optical responses for a range of applications. Metal–insulator–metal (MIM) metasurfaces arranged in supercells, for instance, can be tailored by geometry and material choice to exhibit a variety of absorption properties and resonant wavelengths. With this flexibility, however, comes a vast space of design possibilities that classical design paradigms struggle to effectively navigate. To overcome this challenge, here, we demonstrate a tandem residual network approach to efficiently generate multiplexed supercells through inverse design. By using a training dataset with several thousand full-wave electromagnetic simulations in a design space of over three trillion possible designs, the deep learning model can accurately generate a wide range of complex supercell designs given a spectral target. Beyond inverse design, the presented approach can also be used to explore the structure–property relationships of broadband absorption and emission in such supercell configurations. Thus, this study demonstrates the feasibility of high-dimensional supercell inverse design with deep neural networks, which is applicable to complex nanophotonic structures composed of multiple subunit elements that exhibit coupling.

Understanding how nano‐ or micro‐scale structures and material properties can be optimally configured to attain specific functionalities remains a fundamental challenge. Photonic metasurfaces, for instance, can be spectrally tuned through material choice and structural geometry to achieve unique optical responses. However, existing numerical design methods require prior identification of specific material−structure combinations, or device classes, as the starting point for optimization. As such, a unified solution that simultaneously optimizes across materials and geometries has yet to be realized. To overcome these challenges, a global deep learning‐based inverse design framework is presented, where a conditional deep convolutional generative adversarial network is trained on colored images encoded with a range of material and structural parameters, including refractive index, plasma frequency, and geometric design. It is demonstrated that, in response to target absorption spectra, the network can identify an effective metasurface in terms of its class, materials properties, and overall shape. Furthermore, the model can arrive at multiple design variants with distinct materials and structures that present nearly identical absorption spectra. The proposed framework is thus an important step towards global photonics and materials design strategies that can identify combinations of device categories, material properties, and geometric parameters which algorithmically deliver a sought functionality.

Tobacco use disorder (TUD) is the most prevalent substance use disorder in the world. Genetic factors influence smoking behaviors, and although strides have been made using genome-wide association studies (GWAS) to identify risk variants, the majority of variants identified have been for nicotine consumption, rather than TUD. We leveraged five biobanks to perform a multi-ancestral meta-analysis of TUD (derived via electronic health records, EHR) in 898,680 individuals (739,895 European, 114,420 African American, 44,365 Latin American). We identified 72 independent risk loci; integration with functional genomic tools uncovered 330 potential risk genes, primarily expressed in the brain. TUD was genetically correlated with smoking and psychiatric traits from traditionally ascertained cohorts, externalizing behaviors in children, and hundreds of medical outcomes, including HIV infection, heart disease, and pain. This work furthers our biological understanding of TUD and establishes EHR as a source of phenotypic information for studying the genetics of TUD.

A fundamental challenge in the design of photonic devices, and electromagnetic structures more generally, is the optimization of their overall architecture to achieve a desired response. To this end, topology or shape optimizers based on the adjoint variable method have been widely adopted due to their high computational efficiency and ability to create complex freeform geometries. However, the functional understanding of such freeform structures remains a black box. Moreover, unless a design space of high-performance devices is known in advance, such gradient-based optimizers can get trapped in local minima valleys or saddle points, which limits performance achievable through this inverse design process. To elucidate the relationships between device performance and nanoscale structuring while mitigating the effects of local minima trapping, we present an inverse design framework that combines adjoint optimization, automated machine learning, and explainable artificial intelligence. Integrated with a numerical electromagnetic simulation method, our framework reveals structural contributions toward a figure-of-merit (FOM) of interest. Through an explanation-based reoptimization process, this information is then leveraged to minimize the FOM further than that obtained through adjoint optimization alone, thus overcoming the optimization's local minima. We demonstrate our framework in the context of waveguide splitter design and achieve between 39 and 74% increases in device performance relative to state-of-theart adjoint optimization-based inverse design across a range of telecom wavelengths. Our results highlight machine learning strategies that can substantially extend and enhance the capabilities of a conventional, optimization-based inverse design algorithm while revealing deeper insights into the algorithm's designs.

In recent years, hybrid design strategies combining machine learning (ML) with electromagnetic optimization algorithms have emerged as a new paradigm for the inverse design of photonic structures and devices. While a trained, data-driven neural network can rapidly identify solutions near the global optimum with a given dataset's design space, an iterative optimization algorithm can further refine the solution and overcome dataset limitations. Furthermore, such hybrid ML-optimization methodologies can reduce computational costs and expedite the discovery of novel electromagnetic components. However, existing hybrid ML-optimization methods have yet to optimize across both materials and geometries in a single integrated and user-friendly environment. In addition, due to the challenge of acquiring large datasets for ML, as well as the exponential growth of isolated models being trained for photonics design, there is a need to standardize the ML-optimization workflow while making the pre-trained models easily accessible. Motivated by these challenges, here we introduce DeepAdjoint, a general-purpose, open-source, and multi-objective "all-in-one" global photonics inverse design application framework which integrates pre-trained deep generative networks with state-of-the-art electromagnetic optimization algorithms such as the adjoint variables method. DeepAdjoint allows a designer to specify an arbitrary optical design target, then obtain a photonic structure that is robust to fabrication tolerances and possesses the desired optical properties -all within a single user-guided application interface. We demonstrate DeepAdjoint for the design of infrared-controlled metasurfaces, and show that a wide range of structures and absorption spectra can be achieved and optimized, including single-and multi-resonance behavior through single-and supercell-class structures, respectively. Our framework thus paves a path towards the systematic unification of ML and optimization algorithms for photonic inverse design.