An official website of the United States government
Abstract Recent remarkable progress in artificial intelligence (AI) has garnered tremendous attention from researchers, industry leaders, and the general public, who are increasingly aware of AI's growing impact on everyday life. The advancements of AI and deep learning have also significantly influenced the field of nanophotonics. On the one hand, deep learning facilitates data‐driven strategies for optimizing and solving forward and inverse problems of nanophotonic devices. On the other hand, photonic devices offer promising optical platforms for implementing deep neural networks. This review explores both AI for photonic design and photonic implementation of AI. Various deep learning models and their roles in the design of photonic devices are introduced, analyzing the strengths and challenges of these data‐driven methodologies from the perspective of computational cost. Additionally, the potential of optical hardware accelerators for neural networks is discussed by presenting a variety of photonic devices capable of performing linear and nonlinear operations, essential building blocks of neural networks. It is believed that the bidirectional interactions between nanophotonics and AI will drive the coevolution of these two research fields.
more »
« less
This content will become publicly available on January 1, 2026
Enabling Fast AI-Driven Inverse Design of a Multifunctional Nanosurface by Parallel Evolution Strategies
Multifunctional nanosurfaces receive growing attention due to their versatile properties. Capillary force lithography (CFL) has emerged as a simple and economical method for fabricating these surfaces. In recent works, the authors proposed to leverage the evolution strategies (ES) to modify nanosurface characteristics with CFL to achieve specific functionalities such as frictional, optical, and bactericidal properties. For artificial intelligence (AI)-driven inverse design, earlier research integrates basic multiphysics principles such as dynamic viscosity, air diffusivity, surface tension, and electric potential with backward deep learning (DL) on the framework of ES. As a successful alternative to reinforcement learning, ES performed well for the AI-driven inverse design. However, the computational limitations of ES pose a critical technical challenge to achieving fast and efficient design. This paper addresses the challenges by proposing a parallel-computing-based ES (named parallel ES). The parallel ES demonstrated the desired speed and scalability, accelerating the AI-driven inverse design of multifunctional nanopatterned surfaces. Detailed parallel ES algorithms and cost models are presented, showing its potential as a promising tool for advancing AI-driven nanomanufacturing.
more »
« less
- Award ID(s):
- 2129796
- PAR ID:
- 10641896
- Publisher / Repository:
- Nanomaterials, MDPI
- Date Published:
- Journal Name:
- Nanomaterials
- Volume:
- 15
- Issue:
- 1
- ISSN:
- 2079-4991
- Page Range / eLocation ID:
- 27
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The discovery of advanced thermal materials with exceptional phonon properties drives technological advancements, impacting innovations from electronics to superconductors. Understanding the intricate relationship between composition, structure, and phonon thermal transport properties is crucial for speeding up such discovery. Exploring innovative materials involves navigating vast design spaces and considering chemical and structural factors on multiple scales and modalities. Artificial intelligence (AI) is transforming science and engineering and poised to transform discovery and innovation. This era offers a unique opportunity to establish a new paradigm for the discovery of advanced materials by leveraging databases, simulations, and accumulated knowledge, venturing into experimental frontiers, and incorporating cutting-edge AI technologies. In this perspective, first, the general approach of density functional theory (DFT) coupled with phonon Boltzmann transport equation (BTE) for predicting comprehensive phonon properties will be reviewed. Then, to circumvent the extremely computationally demanding DFT + BTE approach, some early studies and progress of deploying AI/machine learning (ML) models to phonon thermal transport in the context of structure–phonon property relationship prediction will be presented, and their limitations will also be discussed. Finally, a summary of current challenges and an outlook of future trends will be given. Further development of incorporating AI/ML algorithms for phonon thermal transport could range from phonon database construction to universal machine learning potential training, to inverse design of materials with target phonon properties and to extend ML models beyond traditional phonons.more » « less
-
Abstract Lack of rigorous reproducibility and validation are significant hurdles for scientific development across many fields. Materials science, in particular, encompasses a variety of experimental and theoretical approaches that require careful benchmarking. Leaderboard efforts have been developed previously to mitigate these issues. However, a comprehensive comparison and benchmarking on an integrated platform with multiple data modalities with perfect and defect materials data is still lacking. This work introduces JARVIS-Leaderboard, an open-source and community-driven platform that facilitates benchmarking and enhances reproducibility. The platform allows users to set up benchmarks with custom tasks and enables contributions in the form of dataset, code, and meta-data submissions. We cover the following materials design categories: Artificial Intelligence (AI), Electronic Structure (ES), Force-fields (FF), Quantum Computation (QC), and Experiments (EXP). For AI, we cover several types of input data, including atomic structures, atomistic images, spectra, and text. For ES, we consider multiple ES approaches, software packages, pseudopotentials, materials, and properties, comparing results to experiment. For FF, we compare multiple approaches for material property predictions. For QC, we benchmark Hamiltonian simulations using various quantum algorithms and circuits. Finally, for experiments, we use the inter-laboratory approach to establish benchmarks. There are 1281 contributions to 274 benchmarks using 152 methods with more than 8 million data points, and the leaderboard is continuously expanding. The JARVIS-Leaderboard is available at the website:https://pages.nist.gov/jarvis_leaderboard/more » « less
-
Structural characterization of polymer materials is a major step in the process of creating materials' design-structural-property relationships. With growing interests in artificial intelligence (AI)-driven materials design and high-throughput synthesis and measurements, there is now a critical need for development of complementary data-driven approaches (e.g., machine learning models and workflows) to enable fast and automated interpretation of the characterization results. This review sets out with a description of the needs for machine learning specifically in the context of three commonly used structural characterization techniques for polymer materials: microscopy, scattering, and spectroscopy. Subsequently, a review of notable work done on development and application of machine learning models / workflows for these three types of measurements is provided. Definitions are provided for common machine learning terms to help readers who may be less familiar with the terminologies used in the context of machine learning. Finally, a perspective on the current challenges and potential opportunities to successfully integrate such data-driven methods in parallel/sequentially with the measurements is provided. The need for innovative interdisciplinary training programs for researchers regardless of their career path/employment in academia, national laboratories, or research and development in industry is highlighted as a strategy to overcome the challenge associated with the sharing and curation of data and unifying metadata.more » « less
-
null (Ed.)The ever-increasing demand for novel polymers with superior properties requires a deeper understanding and exploration of the chemical space. Recently, data-driven approaches to explore the chemical space for polymer design have emerged. Among them, inverse design strategies for designing polymers with specific properties have evolved to be a significant materials informatics platform by learning hidden knowledge from materials data as well as smartly navigating the chemical space in an optimized way. In this review, we first summarize the progress in the representation of polymers, a prerequisite step for the inverse design of polymers. Then, we systematically introduce three data-driven strategies implemented for the inverse design of polymers, i.e. , high-throughput virtual screening, global optimization, and generative models. Finally, we discuss the challenges and opportunities of the data-driven strategies as well as optimization algorithms employed in the inverse design of polymers.more » « less
