Neural networks determination of material elastic constants and structures in nematic complex fluids
Abstract Supervised machine learning and artificial neural network approaches can allow for the determination of selected material parameters or structures from a measurable signal without knowing the exact mathematical relationship between them. Here, we demonstrate that material nematic elastic co...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-04-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-33134-x |
| _version_ | 1827966364788195328 |
|---|---|
| author | Jaka Zaplotnik Jaka Pišljar Miha Škarabot Miha Ravnik |
| author_facet | Jaka Zaplotnik Jaka Pišljar Miha Škarabot Miha Ravnik |
| author_sort | Jaka Zaplotnik |
| collection | DOAJ |
| description | Abstract Supervised machine learning and artificial neural network approaches can allow for the determination of selected material parameters or structures from a measurable signal without knowing the exact mathematical relationship between them. Here, we demonstrate that material nematic elastic constants and the initial structural material configuration can be found using sequential neural networks applied to the transmmited time-dependent light intensity through the nematic liquid crystal (NLC) sample under crossed polarizers. Specifically, we simulate multiple times the relaxation of the NLC from a random (qeunched) initial state to the equilibirum for random values of elastic constants and, simultaneously, the transmittance of the sample for monochromatic polarized light. The obtained time-dependent light transmittances and the corresponding elastic constants form a training data set on which the neural network is trained, which allows for the determination of the elastic constants, as well as the initial state of the director. Finally, we demonstrate that the neural network trained on numerically generated examples can also be used to determine elastic constants from experimentally measured data, finding good agreement between experiments and neural network predictions. |
| first_indexed | 2024-04-09T17:48:49Z |
| format | Article |
| id | doaj.art-fb13cc16eb6748259defe60f14e60f06 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T17:48:49Z |
| publishDate | 2023-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-fb13cc16eb6748259defe60f14e60f062023-04-16T11:13:59ZengNature PortfolioScientific Reports2045-23222023-04-0113111210.1038/s41598-023-33134-xNeural networks determination of material elastic constants and structures in nematic complex fluidsJaka Zaplotnik0Jaka Pišljar1Miha Škarabot2Miha Ravnik3Faculty of Mathematics and Physics, University of LjubljanaJožef Stefan InstituteJožef Stefan InstituteFaculty of Mathematics and Physics, University of LjubljanaAbstract Supervised machine learning and artificial neural network approaches can allow for the determination of selected material parameters or structures from a measurable signal without knowing the exact mathematical relationship between them. Here, we demonstrate that material nematic elastic constants and the initial structural material configuration can be found using sequential neural networks applied to the transmmited time-dependent light intensity through the nematic liquid crystal (NLC) sample under crossed polarizers. Specifically, we simulate multiple times the relaxation of the NLC from a random (qeunched) initial state to the equilibirum for random values of elastic constants and, simultaneously, the transmittance of the sample for monochromatic polarized light. The obtained time-dependent light transmittances and the corresponding elastic constants form a training data set on which the neural network is trained, which allows for the determination of the elastic constants, as well as the initial state of the director. Finally, we demonstrate that the neural network trained on numerically generated examples can also be used to determine elastic constants from experimentally measured data, finding good agreement between experiments and neural network predictions.https://doi.org/10.1038/s41598-023-33134-x |
| spellingShingle | Jaka Zaplotnik Jaka Pišljar Miha Škarabot Miha Ravnik Neural networks determination of material elastic constants and structures in nematic complex fluids Scientific Reports |
| title | Neural networks determination of material elastic constants and structures in nematic complex fluids |
| title_full | Neural networks determination of material elastic constants and structures in nematic complex fluids |
| title_fullStr | Neural networks determination of material elastic constants and structures in nematic complex fluids |
| title_full_unstemmed | Neural networks determination of material elastic constants and structures in nematic complex fluids |
| title_short | Neural networks determination of material elastic constants and structures in nematic complex fluids |
| title_sort | neural networks determination of material elastic constants and structures in nematic complex fluids |
| url | https://doi.org/10.1038/s41598-023-33134-x |
| work_keys_str_mv | AT jakazaplotnik neuralnetworksdeterminationofmaterialelasticconstantsandstructuresinnematiccomplexfluids AT jakapisljar neuralnetworksdeterminationofmaterialelasticconstantsandstructuresinnematiccomplexfluids AT mihaskarabot neuralnetworksdeterminationofmaterialelasticconstantsandstructuresinnematiccomplexfluids AT miharavnik neuralnetworksdeterminationofmaterialelasticconstantsandstructuresinnematiccomplexfluids |