An official website of the United States government
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
Multiphysics machine learning framework for on-demand multi-functional nano pattern design by light-controlled capillary force lithography
Abstract Nature finds ways to realize multi-functional surfaces by modulating nano-scale patterns on their surfaces, enjoying transparent, bactericidal, and/or anti-fogging features. Therein height distributions of nanopatterns play a key role. Recent advancements in nanotechnologies can reach that ability via chemical, mechanical, or optical fabrications. However, they require laborious complex procedures, prohibiting fast mass manufacturing. This paper presents a computational framework to help design multi-functional nano patterns by light. The framework behaves as a surrogate model for the inverse design of nano distributions. The framework’s hybrid (i.e., human and artificial) intelligence-based approach helps learn plausible rules of multi-physics processes behind the UV-controlled nano patterning and enriches training data sets. Then the framework’s inverse machine learning (ML) model can describe the required UV doses for the target heights of liquid in nano templates. Thereby, the framework can realize multiple functionalities including the desired nano-scale color, frictions, and bactericidal properties. Feasibility test results demonstrate the promising capability of the framework to realize the desired height distributions that can potentially enable multi-functional nano-scale surface properties. This computational framework will serve as a multi-physics surrogate model to help accelerate fast fabrications of nanopatterns with light and ML.
more »
« less
- Award ID(s):
- 2129796
- PAR ID:
- 10520249
- Publisher / Repository:
- Nature Publishing Group
- Date Published:
- Journal Name:
- Communications Physics
- Volume:
- 7
- Issue:
- 1
- ISSN:
- 2399-3650
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Applications of process‐based models (PBM) for predictions are confounded by multiple uncertainties and computational burdens, resulting in appreciable errors. A novel modeling framework combining a high‐fidelity PBM with surrogate and machine learning (ML) models is developed to tackle these challenges and applied for streamflow prediction. A surrogate model permits high computational efficiency of a PBM solution at a minimum loss of its accuracy. A novel probabilistic ML model partitions the PBM‐surrogate prediction errors into reducible and irreducible types, quantifying their distributions that arise due to both explicitly perceived uncertainties (such as parametric) or those that are entirely hidden to the modeler (not included or unexpected). Using this approach, we demonstrate a substantial improvement of streamflow predictive accuracy for a case study urbanized watershed. Such a framework provides an efficient solution combining the strengths of high‐fidelity and physics‐agnostic models for a wide range of prediction problems in geosciences.more » « less
-
Abstract In the rapidly developing field of nanophotonics, machine learning (ML) methods facilitate the multi‐parameter optimization processes and serve as a valuable technique in tackling inverse design challenges by predicting nanostructure designs that satisfy specific optical property criteria. However, while considerable efforts have been devoted to applying ML for designing the overall spectral response of photonic nanostructures, often without elucidating the underlying physical mechanisms, physics‐based models remain largely unexplored. Here, physics‐empowered forward and inverse ML models to design dielectric meta‐atoms with controlled multipolar responses are introduced. By utilizing the multipole expansion theory, the forward model efficiently predicts the scattering response of meta‐atoms with diverse shapes and the inverse model designs meta‐atoms that possess the desired multipole resonances. Implementing the inverse design model, uniquely shaped meta‐atoms with enhanced higher‐order magnetic resonances and those supporting a super‐scattering regime of light‐matter interactions resulting in nearly five‐fold enhancement of scattering beyond the single‐channel limit are designed. Finally, an ML model to predict the wavelength‐dependent electric field distribution inside and near the meta‐atom is developed. The proposed ML based models will likely facilitate uncovering new regimes of linear and nonlinear light‐matter interaction at the nanoscale as well as a versatile toolkit for nanophotonic design.more » « less
-
null (Ed.)In the recent years, there is a growing interest in using quantum computers for solving combinatorial optimization problems. In this work, we developed a generic, machine learning-based framework for mapping continuous-space inverse design problems into surrogate quadratic unconstrained binary optimization (QUBO) problems by employing a binary variational autoencoder and a factorization machine. The factorization machine is trained as a low-dimensional, binary surrogate model for the continuous design space and sampled using various QUBO samplers. Using the D-Wave Advantage hybrid sampler and simulated annealing, we demonstrate that by repeated resampling and retraining of the factorization machine, our framework finds designs that exhibit figures of merit exceeding those of its training set. We showcase the framework’s performance on two inverse design problems by optimizing (i) thermal emitter topologies for thermophotovoltaic applications and (ii) diffractive meta-gratings for highly efficient beam steering. This technique can be further scaled to leverage future developments in quantum optimization to solve advanced inverse design problems for science and engineering applications.more » « less
-
Pursuit of hidden rules behind the irregularity of nano capillary lithography by hybrid intelligenceAbstract Nature finds a way to leverage nanotextures to achieve desired functions. Recent advances in nanotechnologies endow fascinating multi-functionalities to nanotextures by modulating the nanopixel’s height. But nanoscale height control is a daunting task involving chemical and/or physical processes. As a facile, cost-effective, and potentially scalable remedy, the nanoscale capillary force lithography (CFL) receives notable attention. The key enabler is optical pre-modification of photopolymer’s characteristics via ultraviolet (UV) exposure. Still, the underlying physics of the nanoscale CFL is not well understood, and unexplained phenomena such as the “forbidden gap” in the nano capillary rise (unreachable height) abound. Due to the lack of large data, small length scales, and the absence of first principles, direct adoptions of machine learning or analytical approaches have been difficult. This paper proposes a hybrid intelligence approach in which both artificial and human intelligence coherently work together to unravel the hidden rules with small data. Our results show promising performance in identifying transparent, physics-retained rules of air diffusivity, dynamic viscosity, and surface tension, which collectively appear to explain the forbidden gap in the nanoscale CFL. This paper promotes synergistic collaborations of humans and AI for advancing nanotechnology and beyond.more » « less
