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 nanosurf...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Nanomaterials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-4991/15/1/27 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549044713783296 |
|---|---|
| author | Ashish Chapagain Dima Abuoliem In Ho Cho |
| author_facet | Ashish Chapagain Dima Abuoliem In Ho Cho |
| author_sort | Ashish Chapagain |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-0e4aa4183e7b47f188573adcf2f75688 |
| institution | Kabale University |
| issn | 2079-4991 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Nanomaterials |
| spelling | doaj-art-0e4aa4183e7b47f188573adcf2f756882025-01-10T13:19:17ZengMDPI AGNanomaterials2079-49912024-12-011512710.3390/nano15010027Enabling Fast AI-Driven Inverse Design of a Multifunctional Nanosurface by Parallel Evolution StrategiesAshish Chapagain0Dima Abuoliem1In Ho Cho2Department of Civil, Construction, and Environmental Engineering, Iowa State University, Ames, IA 50011, USADepartment of Civil, Construction, and Environmental Engineering, Iowa State University, Ames, IA 50011, USADepartment of Civil, Construction, and Environmental Engineering, Iowa State University, Ames, IA 50011, USAMultifunctional 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.https://www.mdpi.com/2079-4991/15/1/27capillary force lithographyparallel evolution strategieslight-controlled nanopatterningAI-driven inverse designmultifunctional nanosurface |
| spellingShingle | Ashish Chapagain Dima Abuoliem In Ho Cho Enabling Fast AI-Driven Inverse Design of a Multifunctional Nanosurface by Parallel Evolution Strategies Nanomaterials capillary force lithography parallel evolution strategies light-controlled nanopatterning AI-driven inverse design multifunctional nanosurface |
| title | Enabling Fast AI-Driven Inverse Design of a Multifunctional Nanosurface by Parallel Evolution Strategies |
| title_full | Enabling Fast AI-Driven Inverse Design of a Multifunctional Nanosurface by Parallel Evolution Strategies |
| title_fullStr | Enabling Fast AI-Driven Inverse Design of a Multifunctional Nanosurface by Parallel Evolution Strategies |
| title_full_unstemmed | Enabling Fast AI-Driven Inverse Design of a Multifunctional Nanosurface by Parallel Evolution Strategies |
| title_short | Enabling Fast AI-Driven Inverse Design of a Multifunctional Nanosurface by Parallel Evolution Strategies |
| title_sort | enabling fast ai driven inverse design of a multifunctional nanosurface by parallel evolution strategies |
| topic | capillary force lithography parallel evolution strategies light-controlled nanopatterning AI-driven inverse design multifunctional nanosurface |
| url | https://www.mdpi.com/2079-4991/15/1/27 |
| work_keys_str_mv | AT ashishchapagain enablingfastaidriveninversedesignofamultifunctionalnanosurfacebyparallelevolutionstrategies AT dimaabuoliem enablingfastaidriveninversedesignofamultifunctionalnanosurfacebyparallelevolutionstrategies AT inhocho enablingfastaidriveninversedesignofamultifunctionalnanosurfacebyparallelevolutionstrategies |