Deep learning strategies for addressing issues with small datasets in 2D materials research: Microbial Corrosion
Protective coatings based on two dimensional materials such as graphene have gained traction for diverse applications. Their impermeability, inertness, excellent bonding with metals, and amenability to functionalization renders them as promising coatings for both abiotic and microbiologically influe...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-12-01
|
| Series: | Frontiers in Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmicb.2022.1059123/full |
| _version_ | 1797979286948282368 |
|---|---|
| author | Cody Allen Cody Allen Cody Allen Shiva Aryal Tuyen Do Rishav Gautum Md Mahmudul Hasan Md Mahmudul Hasan Md Mahmudul Hasan Bharat K. Jasthi Bharat K. Jasthi Bharat K. Jasthi Etienne Gnimpieba Etienne Gnimpieba Venkataramana Gadhamshetty Venkataramana Gadhamshetty Venkataramana Gadhamshetty |
| author_facet | Cody Allen Cody Allen Cody Allen Shiva Aryal Tuyen Do Rishav Gautum Md Mahmudul Hasan Md Mahmudul Hasan Md Mahmudul Hasan Bharat K. Jasthi Bharat K. Jasthi Bharat K. Jasthi Etienne Gnimpieba Etienne Gnimpieba Venkataramana Gadhamshetty Venkataramana Gadhamshetty Venkataramana Gadhamshetty |
| author_sort | Cody Allen |
| collection | DOAJ |
| description | Protective coatings based on two dimensional materials such as graphene have gained traction for diverse applications. Their impermeability, inertness, excellent bonding with metals, and amenability to functionalization renders them as promising coatings for both abiotic and microbiologically influenced corrosion (MIC). Owing to the success of graphene coatings, the whole family of 2D materials, including hexagonal boron nitride and molybdenum disulphide are being screened to obtain other promising coatings. AI-based data-driven models can accelerate virtual screening of 2D coatings with desirable physical and chemical properties. However, lack of large experimental datasets renders training of classifiers difficult and often results in over-fitting. Generate large datasets for MIC resistance of 2D coatings is both complex and laborious. Deep learning data augmentation methods can alleviate this issue by generating synthetic electrochemical data that resembles the training data classes. Here, we investigated two different deep generative models, namely variation autoencoder (VAE) and generative adversarial network (GAN) for generating synthetic data for expanding small experimental datasets. Our model experimental system included few layered graphene over copper surfaces. The synthetic data generated using GAN displayed a greater neural network system performance (83-85% accuracy) than VAE generated synthetic data (78-80% accuracy). However, VAE data performed better (90% accuracy) than GAN data (84%-85% accuracy) when using XGBoost. Finally, we show that synthetic data based on VAE and GAN models can drive machine learning models for developing MIC resistant 2D coatings. |
| first_indexed | 2024-04-11T05:36:36Z |
| format | Article |
| id | doaj.art-161ef166068a4610a2f8546bc5eeb331 |
| institution | Directory Open Access Journal |
| issn | 1664-302X |
| language | English |
| last_indexed | 2024-04-11T05:36:36Z |
| publishDate | 2022-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Microbiology |
| spelling | doaj.art-161ef166068a4610a2f8546bc5eeb3312022-12-22T11:59:04ZengFrontiers Media S.A.Frontiers in Microbiology1664-302X2022-12-011310.3389/fmicb.2022.10591231059123Deep learning strategies for addressing issues with small datasets in 2D materials research: Microbial CorrosionCody Allen0Cody Allen1Cody Allen2Shiva Aryal3Tuyen Do4Rishav Gautum5Md Mahmudul Hasan6Md Mahmudul Hasan7Md Mahmudul Hasan8Bharat K. Jasthi9Bharat K. Jasthi10Bharat K. Jasthi11Etienne Gnimpieba12Etienne Gnimpieba13Venkataramana Gadhamshetty14Venkataramana Gadhamshetty15Venkataramana Gadhamshetty16Department of Civil and Environmental Engineering, South Dakota Mines, Rapid City, SD, United StatesTwo-Dimensional Materials for Biofilm Engineering Science and Technology (2DBEST) Center, South Dakota Mines, Rapid City, SD, United StatesData-Driven Materials Discovery Center, South Dakota Mines, Rapid City, SD, United StatesDepartment of Biomedical Engineering, University of South Dakota, Sioux Falls, SD, United StatesDepartment of Biomedical Engineering, University of South Dakota, Sioux Falls, SD, United StatesDepartment of Biomedical Engineering, University of South Dakota, Sioux Falls, SD, United StatesDepartment of Civil and Environmental Engineering, South Dakota Mines, Rapid City, SD, United StatesTwo-Dimensional Materials for Biofilm Engineering Science and Technology (2DBEST) Center, South Dakota Mines, Rapid City, SD, United StatesData-Driven Materials Discovery Center, South Dakota Mines, Rapid City, SD, United StatesTwo-Dimensional Materials for Biofilm Engineering Science and Technology (2DBEST) Center, South Dakota Mines, Rapid City, SD, United StatesData-Driven Materials Discovery Center, South Dakota Mines, Rapid City, SD, United StatesDepartment of Materials and Metallurgical Engineering, South Dakota Mines, Rapid City, SD, United StatesData-Driven Materials Discovery Center, South Dakota Mines, Rapid City, SD, United StatesDepartment of Biomedical Engineering, University of South Dakota, Sioux Falls, SD, United StatesDepartment of Civil and Environmental Engineering, South Dakota Mines, Rapid City, SD, United StatesTwo-Dimensional Materials for Biofilm Engineering Science and Technology (2DBEST) Center, South Dakota Mines, Rapid City, SD, United StatesData-Driven Materials Discovery Center, South Dakota Mines, Rapid City, SD, United StatesProtective coatings based on two dimensional materials such as graphene have gained traction for diverse applications. Their impermeability, inertness, excellent bonding with metals, and amenability to functionalization renders them as promising coatings for both abiotic and microbiologically influenced corrosion (MIC). Owing to the success of graphene coatings, the whole family of 2D materials, including hexagonal boron nitride and molybdenum disulphide are being screened to obtain other promising coatings. AI-based data-driven models can accelerate virtual screening of 2D coatings with desirable physical and chemical properties. However, lack of large experimental datasets renders training of classifiers difficult and often results in over-fitting. Generate large datasets for MIC resistance of 2D coatings is both complex and laborious. Deep learning data augmentation methods can alleviate this issue by generating synthetic electrochemical data that resembles the training data classes. Here, we investigated two different deep generative models, namely variation autoencoder (VAE) and generative adversarial network (GAN) for generating synthetic data for expanding small experimental datasets. Our model experimental system included few layered graphene over copper surfaces. The synthetic data generated using GAN displayed a greater neural network system performance (83-85% accuracy) than VAE generated synthetic data (78-80% accuracy). However, VAE data performed better (90% accuracy) than GAN data (84%-85% accuracy) when using XGBoost. Finally, we show that synthetic data based on VAE and GAN models can drive machine learning models for developing MIC resistant 2D coatings.https://www.frontiersin.org/articles/10.3389/fmicb.2022.1059123/full2D materialscoatingsgraphenehexagonal boron nitrideelectrochemical impedance spectroscopymachine learning |
| spellingShingle | Cody Allen Cody Allen Cody Allen Shiva Aryal Tuyen Do Rishav Gautum Md Mahmudul Hasan Md Mahmudul Hasan Md Mahmudul Hasan Bharat K. Jasthi Bharat K. Jasthi Bharat K. Jasthi Etienne Gnimpieba Etienne Gnimpieba Venkataramana Gadhamshetty Venkataramana Gadhamshetty Venkataramana Gadhamshetty Deep learning strategies for addressing issues with small datasets in 2D materials research: Microbial Corrosion Frontiers in Microbiology 2D materials coatings graphene hexagonal boron nitride electrochemical impedance spectroscopy machine learning |
| title | Deep learning strategies for addressing issues with small datasets in 2D materials research: Microbial Corrosion |
| title_full | Deep learning strategies for addressing issues with small datasets in 2D materials research: Microbial Corrosion |
| title_fullStr | Deep learning strategies for addressing issues with small datasets in 2D materials research: Microbial Corrosion |
| title_full_unstemmed | Deep learning strategies for addressing issues with small datasets in 2D materials research: Microbial Corrosion |
| title_short | Deep learning strategies for addressing issues with small datasets in 2D materials research: Microbial Corrosion |
| title_sort | deep learning strategies for addressing issues with small datasets in 2d materials research microbial corrosion |
| topic | 2D materials coatings graphene hexagonal boron nitride electrochemical impedance spectroscopy machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fmicb.2022.1059123/full |
| work_keys_str_mv | AT codyallen deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT codyallen deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT codyallen deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT shivaaryal deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT tuyendo deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT rishavgautum deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT mdmahmudulhasan deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT mdmahmudulhasan deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT mdmahmudulhasan deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT bharatkjasthi deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT bharatkjasthi deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT bharatkjasthi deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT etiennegnimpieba deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT etiennegnimpieba deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT venkataramanagadhamshetty deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT venkataramanagadhamshetty deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion AT venkataramanagadhamshetty deeplearningstrategiesforaddressingissueswithsmalldatasetsin2dmaterialsresearchmicrobialcorrosion |