Two-step machine learning enables optimized nanoparticle synthesis
<jats:title>Abstract</jats:title><jats:p>In materials science, the discovery of recipes that yield nanomaterials with defined optical properties is costly and time-consuming. In this study, we present a two-step framework for a machine learning-driven high-throughput microfluidic p...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Science and Business Media LLC
2021
|
| Online Access: | https://hdl.handle.net/1721.1/138479 |
| _version_ | 1811077605591351296 |
|---|---|
| author | Mekki-Berrada, Flore Ren, Zekun Huang, Tan Wong, Wai Kuan Zheng, Fang Xie, Jiaxun Tian, Isaac Parker Siyu Jayavelu, Senthilnath Mahfoud, Zackaria Bash, Daniil Hippalgaonkar, Kedar Khan, Saif Buonassisi, Tonio Li, Qianxiao Wang, Xiaonan |
| author2 | Singapore-MIT Alliance in Research and Technology (SMART) |
| author_facet | Singapore-MIT Alliance in Research and Technology (SMART) Mekki-Berrada, Flore Ren, Zekun Huang, Tan Wong, Wai Kuan Zheng, Fang Xie, Jiaxun Tian, Isaac Parker Siyu Jayavelu, Senthilnath Mahfoud, Zackaria Bash, Daniil Hippalgaonkar, Kedar Khan, Saif Buonassisi, Tonio Li, Qianxiao Wang, Xiaonan |
| author_sort | Mekki-Berrada, Flore |
| collection | MIT |
| description | <jats:title>Abstract</jats:title><jats:p>In materials science, the discovery of recipes that yield nanomaterials with defined optical properties is costly and time-consuming. In this study, we present a two-step framework for a machine learning-driven high-throughput microfluidic platform to rapidly produce silver nanoparticles with the desired absorbance spectrum. Combining a Gaussian process-based Bayesian optimization (BO) with a deep neural network (DNN), the algorithmic framework is able to converge towards the target spectrum after sampling 120 conditions. Once the dataset is large enough to train the DNN with sufficient accuracy in the region of the target spectrum, the DNN is used to predict the colour palette accessible with the reaction synthesis. While remaining interpretable by humans, the proposed framework efficiently optimizes the nanomaterial synthesis and can extract fundamental knowledge of the relationship between chemical composition and optical properties, such as the role of each reactant on the shape and amplitude of the absorbance spectrum.</jats:p> |
| first_indexed | 2024-09-23T10:45:40Z |
| format | Article |
| id | mit-1721.1/138479 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T10:45:40Z |
| publishDate | 2021 |
| publisher | Springer Science and Business Media LLC |
| record_format | dspace |
| spelling | mit-1721.1/1384792023-04-14T15:26:07Z Two-step machine learning enables optimized nanoparticle synthesis Mekki-Berrada, Flore Ren, Zekun Huang, Tan Wong, Wai Kuan Zheng, Fang Xie, Jiaxun Tian, Isaac Parker Siyu Jayavelu, Senthilnath Mahfoud, Zackaria Bash, Daniil Hippalgaonkar, Kedar Khan, Saif Buonassisi, Tonio Li, Qianxiao Wang, Xiaonan Singapore-MIT Alliance in Research and Technology (SMART) Massachusetts Institute of Technology. Department of Mechanical Engineering <jats:title>Abstract</jats:title><jats:p>In materials science, the discovery of recipes that yield nanomaterials with defined optical properties is costly and time-consuming. In this study, we present a two-step framework for a machine learning-driven high-throughput microfluidic platform to rapidly produce silver nanoparticles with the desired absorbance spectrum. Combining a Gaussian process-based Bayesian optimization (BO) with a deep neural network (DNN), the algorithmic framework is able to converge towards the target spectrum after sampling 120 conditions. Once the dataset is large enough to train the DNN with sufficient accuracy in the region of the target spectrum, the DNN is used to predict the colour palette accessible with the reaction synthesis. While remaining interpretable by humans, the proposed framework efficiently optimizes the nanomaterial synthesis and can extract fundamental knowledge of the relationship between chemical composition and optical properties, such as the role of each reactant on the shape and amplitude of the absorbance spectrum.</jats:p> 2021-12-14T19:21:47Z 2021-12-14T19:21:47Z 2021 2021-12-14T19:17:58Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/138479 Mekki-Berrada, Flore, Ren, Zekun, Huang, Tan, Wong, Wai Kuan, Zheng, Fang et al. 2021. "Two-step machine learning enables optimized nanoparticle synthesis." npj Computational Materials, 7 (1). en 10.1038/S41524-021-00520-W npj Computational Materials Creative Commons Attribution 4.0 International license https://creativecommons.org/licenses/by/4.0/ application/pdf Springer Science and Business Media LLC Nature |
| spellingShingle | Mekki-Berrada, Flore Ren, Zekun Huang, Tan Wong, Wai Kuan Zheng, Fang Xie, Jiaxun Tian, Isaac Parker Siyu Jayavelu, Senthilnath Mahfoud, Zackaria Bash, Daniil Hippalgaonkar, Kedar Khan, Saif Buonassisi, Tonio Li, Qianxiao Wang, Xiaonan Two-step machine learning enables optimized nanoparticle synthesis |
| title | Two-step machine learning enables optimized nanoparticle synthesis |
| title_full | Two-step machine learning enables optimized nanoparticle synthesis |
| title_fullStr | Two-step machine learning enables optimized nanoparticle synthesis |
| title_full_unstemmed | Two-step machine learning enables optimized nanoparticle synthesis |
| title_short | Two-step machine learning enables optimized nanoparticle synthesis |
| title_sort | two step machine learning enables optimized nanoparticle synthesis |
| url | https://hdl.handle.net/1721.1/138479 |
| work_keys_str_mv | AT mekkiberradaflore twostepmachinelearningenablesoptimizednanoparticlesynthesis AT renzekun twostepmachinelearningenablesoptimizednanoparticlesynthesis AT huangtan twostepmachinelearningenablesoptimizednanoparticlesynthesis AT wongwaikuan twostepmachinelearningenablesoptimizednanoparticlesynthesis AT zhengfang twostepmachinelearningenablesoptimizednanoparticlesynthesis AT xiejiaxun twostepmachinelearningenablesoptimizednanoparticlesynthesis AT tianisaacparkersiyu twostepmachinelearningenablesoptimizednanoparticlesynthesis AT jayavelusenthilnath twostepmachinelearningenablesoptimizednanoparticlesynthesis AT mahfoudzackaria twostepmachinelearningenablesoptimizednanoparticlesynthesis AT bashdaniil twostepmachinelearningenablesoptimizednanoparticlesynthesis AT hippalgaonkarkedar twostepmachinelearningenablesoptimizednanoparticlesynthesis AT khansaif twostepmachinelearningenablesoptimizednanoparticlesynthesis AT buonassisitonio twostepmachinelearningenablesoptimizednanoparticlesynthesis AT liqianxiao twostepmachinelearningenablesoptimizednanoparticlesynthesis AT wangxiaonan twostepmachinelearningenablesoptimizednanoparticlesynthesis |