Transfer learning for multi-material classification of transition metal dichalcogenides with atomic force microscopy
Deep learning models based on atomic force microscopy enhance efficiency in inverse design and characterization of materials. However, the limited and imbalanced data of experimental materials that are typically available is a major challenge. Also important is the need to interpret trained models,...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ada2da |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556603219738624 |
|---|---|
| author | Isaiah A Moses Wesley F Reinhart |
| author_facet | Isaiah A Moses Wesley F Reinhart |
| author_sort | Isaiah A Moses |
| collection | DOAJ |
| description | Deep learning models based on atomic force microscopy enhance efficiency in inverse design and characterization of materials. However, the limited and imbalanced data of experimental materials that are typically available is a major challenge. Also important is the need to interpret trained models, which are normally complex enough to be uninterpretable by humans. Here, we present a systemic evaluation of transfer learning strategies to accommodate low-data scenarios in materials synthesis and a model latent feature analysis to draw connections to the human-interpretable characteristics of the samples. While we imagine this framework can be used in downstream analysis tasks such as quantitative characterization, we demonstrate the strategies on a multi-material classification task for which the ground truth labels are readily available. Our models show accurate predictions in five classes of transition metal dichalcogenides (TMDs) (MoS _2 , WS _2 , WSe _2 , MoSe _2 , and Mo-WSe _2 ) with up to 89% accuracy on held-out test samples. Analysis of the latent features reveals a correlation with physical characteristics such as grain density, Difference of Gaussian blob, and local variation. The transfer learning optimization modality and the exploration of the correlation between the latent and physical features provide important frameworks that can be applied to other classes of materials beyond TMDs to enhance the models’ performance and explainability which can accelerate the inverse design of materials for technological applications. |
| format | Article |
| id | doaj-art-d2046274b736480e98777c19eca9ba62 |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-d2046274b736480e98777c19eca9ba622025-01-07T06:59:29ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-015404508110.1088/2632-2153/ada2daTransfer learning for multi-material classification of transition metal dichalcogenides with atomic force microscopyIsaiah A Moses0https://orcid.org/0000-0002-8920-2180Wesley F Reinhart1https://orcid.org/0000-0001-7256-2123Materials Research Institute, The Pennsylvania State University , University Park, PA 16802, United States of AmericaDepartment of Materials Science and Engineering, The Pennsylvania State University , University Park, PA 16802, United States of America; Institute for Computational and Data Sciences, The Pennsylvania State University , University Park, PA 16802, United States of AmericaDeep learning models based on atomic force microscopy enhance efficiency in inverse design and characterization of materials. However, the limited and imbalanced data of experimental materials that are typically available is a major challenge. Also important is the need to interpret trained models, which are normally complex enough to be uninterpretable by humans. Here, we present a systemic evaluation of transfer learning strategies to accommodate low-data scenarios in materials synthesis and a model latent feature analysis to draw connections to the human-interpretable characteristics of the samples. While we imagine this framework can be used in downstream analysis tasks such as quantitative characterization, we demonstrate the strategies on a multi-material classification task for which the ground truth labels are readily available. Our models show accurate predictions in five classes of transition metal dichalcogenides (TMDs) (MoS _2 , WS _2 , WSe _2 , MoSe _2 , and Mo-WSe _2 ) with up to 89% accuracy on held-out test samples. Analysis of the latent features reveals a correlation with physical characteristics such as grain density, Difference of Gaussian blob, and local variation. The transfer learning optimization modality and the exploration of the correlation between the latent and physical features provide important frameworks that can be applied to other classes of materials beyond TMDs to enhance the models’ performance and explainability which can accelerate the inverse design of materials for technological applications.https://doi.org/10.1088/2632-2153/ada2datransition metal dichalcogenidesatomic force microscopycomputer visionmodel interpretationtransfer learning |
| spellingShingle | Isaiah A Moses Wesley F Reinhart Transfer learning for multi-material classification of transition metal dichalcogenides with atomic force microscopy Machine Learning: Science and Technology transition metal dichalcogenides atomic force microscopy computer vision model interpretation transfer learning |
| title | Transfer learning for multi-material classification of transition metal dichalcogenides with atomic force microscopy |
| title_full | Transfer learning for multi-material classification of transition metal dichalcogenides with atomic force microscopy |
| title_fullStr | Transfer learning for multi-material classification of transition metal dichalcogenides with atomic force microscopy |
| title_full_unstemmed | Transfer learning for multi-material classification of transition metal dichalcogenides with atomic force microscopy |
| title_short | Transfer learning for multi-material classification of transition metal dichalcogenides with atomic force microscopy |
| title_sort | transfer learning for multi material classification of transition metal dichalcogenides with atomic force microscopy |
| topic | transition metal dichalcogenides atomic force microscopy computer vision model interpretation transfer learning |
| url | https://doi.org/10.1088/2632-2153/ada2da |
| work_keys_str_mv | AT isaiahamoses transferlearningformultimaterialclassificationoftransitionmetaldichalcogenideswithatomicforcemicroscopy AT wesleyfreinhart transferlearningformultimaterialclassificationoftransitionmetaldichalcogenideswithatomicforcemicroscopy |