Multiphysics machine learning framework for on-demand multi-functional nano pattern design by light-controlled capillary force lithography

Aug 5, 2026

Upload by Maeve

A computational multiphysics machine learning framework supports inverse design of nano-scale height distributions for light-controlled capillary force lithography. By combining human-guided and artificial intelligence learning, the approach captures plausible rules behind UV-controlled nano patterning and enriches training data for a surrogate model. The inverse ML model outputs required UV doses to achieve target liquid heights in nano templates, enabling multi-functional surfaces. Results validate the framework’s ability to realize desired height distributions for color, friction, and bactericidal properties.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Biomimetic nano-patterns and multi-functional surfaces

Challenges in conventional nanofabrication

Proposed framework

Surrogate model for inverse design

Hybrid human-AI learning for multi-physics processes

Inverse machine learning workflow

Predicting UV doses for target nano heights

Feasibility and outcomes

[https://doi.org/10.1038/s42005-024-01703-9](https://doi.org/10.1038/s42005-024-01703-9) Multiphysics machine learning framework for on-demand multi-functional nano pattern design by light-controlled capillary force lithography Check for updates In a different vein, riblet structures in shark Modifying Ashish Chapagain & In Ho Cho 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. Nature’s intricate design has increasingly inspired groundbreaking innovations-a standard example is found in the nocturnal moth, especially Spodoptera eridania, whose corneal surface has an array of nanopillars. These nanopillars minimize light reﬂectance by gradually matching the refractive index of air to that of the lens material, thereby enhancing perception1. Similarly, the longtail glasswing butterﬂy offers another blueprint for innovation. The researchers studied the nanostructures and their distribution in the wings of longtail glasswing butterﬂies (Fig. 1a, b) to improve micro-optical implants, overcoming limitations like angle-dependent sensing and biofouling. Using highresolution microscopy, the researchers found dome-shaped nanopillars with moderate aspect ratios with different densities across the wing areas. The nanopillars’ varying aspect ratio and density inﬂuenced the light scattering and anti-reﬂective properties. It also impacted the anti-wetting properties and biofouling properties. Inspired, they developed discshaped nano-structured membranes using silicon nitride by employing the polymer phase separation phenomenon, having enhanced hydrophilicity and improved angle-independence of light transmission, crucial for optical implants2. The nano-structured surfaces possess signiﬁcantly reduced adhesion of protein, bacteria, and eukaryotic cells compared toﬂat surfacesand prevent cell attachment and growth without causing cell death2. Therefore, the antimicrobial properties in dragonﬂiesand cicadae result from physical interaction between nanoscale structures and attacking pathogenic cells instead of biochemical processes3 (Fig. 1c). The distribution of nanopillars in dragonﬂy’s wings that imbue it with antibacterial property and a cross-sectional area of the arrangement is given in Fig. 1d, e. The researchers employed the nano-structured membrane in a new implantable sensor to measure eye pressure (Intraocular pressure, IOP), which offered minimal tissue growth and inﬂammation, demonstrating enhanced biocompatibility and practical utility in medical implants2. skin reduce drag, increasing swimming efﬁciency and speed. the hull

FAQs

What problem does the proposed framework solve?

It enables inverse design of multi-functional nano patterns by predicting UV doses needed to achieve target nano-scale height distributions in light-controlled capillary force lithography.

How does the framework model the multi-physics process?

It acts as a surrogate model learned through a hybrid human-and-artificial intelligence approach that captures plausible rules of UV-controlled nano patterning and supports training data enrichment.

What functionalities can the framework help realize?

It can realize multiple surface functionalities tied to the designed nano topography, including desired nano-scale color, friction, and bactericidal properties.

Aug 5, 2026

Upload by Maeve