Multi-fidelity high-throughput optimization of electrical conductivity in P3HT-CNT composites
Combining high-throughput experiments with machine learning accelerates materials and process optimization toward user-specified target properties. In this study, a rapid machine learning-driven automated flow mixing setup with a high-throughput drop-casting system is introduced for thin film prepar...
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/156005 |
| _version_ | 1824456351262179328 |
|---|---|
| author | Bash, Daniil Cai, Yongqiang Chellappan, Vijila Wong, Swee Liang Xu, Yang Kumar, Pawan Tan, Jin Da Abutaha, Anas Cheng, Jayce J. W. Lim, Yee‐Fun Tian, Siyu Isaac Parker Ren, Zekun Mekki‐Berrada, Flore Wong, Wai Kuan Xie, Jiaxun Kumar, Jatin Khan, Saif A. Li, Qianxiao Buonassisi, Tonio Hippalgaonkar, Kedar |
| author2 | School of Materials Science and Engineering |
| author_facet | School of Materials Science and Engineering Bash, Daniil Cai, Yongqiang Chellappan, Vijila Wong, Swee Liang Xu, Yang Kumar, Pawan Tan, Jin Da Abutaha, Anas Cheng, Jayce J. W. Lim, Yee‐Fun Tian, Siyu Isaac Parker Ren, Zekun Mekki‐Berrada, Flore Wong, Wai Kuan Xie, Jiaxun Kumar, Jatin Khan, Saif A. Li, Qianxiao Buonassisi, Tonio Hippalgaonkar, Kedar |
| author_sort | Bash, Daniil |
| collection | NTU |
| description | Combining high-throughput experiments with machine learning accelerates materials and process optimization toward user-specified target properties. In this study, a rapid machine learning-driven automated flow mixing setup with a high-throughput drop-casting system is introduced for thin film preparation, followed by fast characterization of proxy optical and target electrical properties that completes one cycle of learning with 160 unique samples in a single day, a >10× improvement relative to quantified, manual-controlled baseline. Regio-regular poly-3-hexylthiophene is combined with various types of carbon nanotubes, to identify the optimum composition and synthesis conditions to realize electrical conductivities as high as state-of-the-art 1000 S cm−1. The results are subsequently verified and explained using offline high-fidelity experiments. Graph-based model selection strategies with classical regression that optimize among multi-fidelity noisy input-output measurements are introduced. These strategies present a robust machine-learning driven high-throughput experimental scheme that can be effectively applied to understand, optimize, and design new materials and composites. |
| first_indexed | 2025-02-19T03:52:43Z |
| format | Journal Article |
| id | ntu-10356/156005 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:52:43Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1560052023-07-14T16:04:49Z Multi-fidelity high-throughput optimization of electrical conductivity in P3HT-CNT composites Bash, Daniil Cai, Yongqiang Chellappan, Vijila Wong, Swee Liang Xu, Yang Kumar, Pawan Tan, Jin Da Abutaha, Anas Cheng, Jayce J. W. Lim, Yee‐Fun Tian, Siyu Isaac Parker Ren, Zekun Mekki‐Berrada, Flore Wong, Wai Kuan Xie, Jiaxun Kumar, Jatin Khan, Saif A. Li, Qianxiao Buonassisi, Tonio Hippalgaonkar, Kedar School of Materials Science and Engineering Institute of Materials Research and Engineering, A*STAR Engineering::Materials::Composite materials Bayesian Optimization Electrical Conductivity Graphical Regression Models High-Throughput Flow Mixing Hypothesis Testing Machine Learning P3HT-CNT Composites Combining high-throughput experiments with machine learning accelerates materials and process optimization toward user-specified target properties. In this study, a rapid machine learning-driven automated flow mixing setup with a high-throughput drop-casting system is introduced for thin film preparation, followed by fast characterization of proxy optical and target electrical properties that completes one cycle of learning with 160 unique samples in a single day, a >10× improvement relative to quantified, manual-controlled baseline. Regio-regular poly-3-hexylthiophene is combined with various types of carbon nanotubes, to identify the optimum composition and synthesis conditions to realize electrical conductivities as high as state-of-the-art 1000 S cm−1. The results are subsequently verified and explained using offline high-fidelity experiments. Graph-based model selection strategies with classical regression that optimize among multi-fidelity noisy input-output measurements are introduced. These strategies present a robust machine-learning driven high-throughput experimental scheme that can be effectively applied to understand, optimize, and design new materials and composites. Agency for Science, Technology and Research (A*STAR) Submitted/Accepted version The authors acknowledge funding from the Accelerated Materials Development for Manufacturing Program at A*STAR via the AME Programmatic Fund by the Agency for Science, Technology and Research under Grant No. A1898b0043. 2022-03-30T05:32:22Z 2022-03-30T05:32:22Z 2021 Journal Article Bash, D., Cai, Y., Chellappan, V., Wong, S. L., Xu, Y., Kumar, P., Tan, J. D., Abutaha, A., Cheng, J. J. W., Lim, Y., Tian, S. I. P., Ren, Z., Mekki‐Berrada, F., Wong, W. K., Xie, J., Kumar, J., Khan, S. A., Li, Q., Buonassisi, T. & Hippalgaonkar, K. (2021). Multi-fidelity high-throughput optimization of electrical conductivity in P3HT-CNT composites. Advanced Functional Materials, 31(36), 2102606-. https://dx.doi.org/10.1002/adfm.202102606 1616-301X https://hdl.handle.net/10356/156005 10.1002/adfm.202102606 36 31 2102606 en A1898b0043 Advanced Functional Materials This is the peer reviewed version of the following article: Bash, D., Cai, Y., Chellappan, V., Wong, S. L., Xu, Y., Kumar, P., Tan, J. D., Abutaha, A., Cheng, J. J. W., Lim, Y., Tian, S. I. P., Ren, Z., Mekki‐Berrada, F., Wong, W. K., Xie, J., Kumar, J., Khan, S. A., Li, Q., Buonassisi, T. & Hippalgaonkar, K. (2021). Multi-fidelity high-throughput optimization of electrical conductivity in P3HT-CNT composites. Advanced Functional Materials, 31(36), 2102606, which has been published in final form at https://doi.org/10.1002/adfm.202102606. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions. application/pdf application/pdf |
| spellingShingle | Engineering::Materials::Composite materials Bayesian Optimization Electrical Conductivity Graphical Regression Models High-Throughput Flow Mixing Hypothesis Testing Machine Learning P3HT-CNT Composites Bash, Daniil Cai, Yongqiang Chellappan, Vijila Wong, Swee Liang Xu, Yang Kumar, Pawan Tan, Jin Da Abutaha, Anas Cheng, Jayce J. W. Lim, Yee‐Fun Tian, Siyu Isaac Parker Ren, Zekun Mekki‐Berrada, Flore Wong, Wai Kuan Xie, Jiaxun Kumar, Jatin Khan, Saif A. Li, Qianxiao Buonassisi, Tonio Hippalgaonkar, Kedar Multi-fidelity high-throughput optimization of electrical conductivity in P3HT-CNT composites |
| title | Multi-fidelity high-throughput optimization of electrical conductivity in P3HT-CNT composites |
| title_full | Multi-fidelity high-throughput optimization of electrical conductivity in P3HT-CNT composites |
| title_fullStr | Multi-fidelity high-throughput optimization of electrical conductivity in P3HT-CNT composites |
| title_full_unstemmed | Multi-fidelity high-throughput optimization of electrical conductivity in P3HT-CNT composites |
| title_short | Multi-fidelity high-throughput optimization of electrical conductivity in P3HT-CNT composites |
| title_sort | multi fidelity high throughput optimization of electrical conductivity in p3ht cnt composites |
| topic | Engineering::Materials::Composite materials Bayesian Optimization Electrical Conductivity Graphical Regression Models High-Throughput Flow Mixing Hypothesis Testing Machine Learning P3HT-CNT Composites |
| url | https://hdl.handle.net/10356/156005 |
| work_keys_str_mv | AT bashdaniil multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT caiyongqiang multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT chellappanvijila multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT wongsweeliang multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT xuyang multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT kumarpawan multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT tanjinda multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT abutahaanas multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT chengjaycejw multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT limyeefun multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT tiansiyuisaacparker multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT renzekun multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT mekkiberradaflore multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT wongwaikuan multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT xiejiaxun multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT kumarjatin multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT khansaifa multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT liqianxiao multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT buonassisitonio multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites AT hippalgaonkarkedar multifidelityhighthroughputoptimizationofelectricalconductivityinp3htcntcomposites |