Deep Learning to Automate Parameter Extraction and Model Fitting of Two-Dimensional Transistors Article Swipe
YOU?
·
· 2025
· Open Access
·
We present a deep learning approach to extract physical parameters (e.g., mobility, Schottky contact barrier height, defect profiles) of two-dimensional (2D) transistors from electrical measurements, enabling automated parameter extraction and technology computer-aided design (TCAD) fitting. To facilitate this task, we implement a simple data augmentation and pre-training approach by training a secondary neural network to approximate a physics-based device simulator. This method enables high-quality fits after training the neural network on electrical data generated from physics-based simulations of ~500 devices, a factor >40$\times$ fewer than other recent efforts. Consequently, fitting can be achieved by training on physically rigorous TCAD models, including complex geometry, self-consistent transport, and electrostatic effects, and is not limited to computationally inexpensive compact models. We apply our approach to reverse-engineer key parameters from experimental monolayer WS$_2$ transistors, achieving a median coefficient of determination ($R^2$) = 0.99 when fitting measured electrical data. We also demonstrate that this approach generalizes and scales well by reverse-engineering electrical data on high-electron-mobility transistors while fitting 35 parameters simultaneously. To facilitate future research on deep learning approaches for inverse transistor design, we have published our code and sample data sets online.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2507.05134
- https://arxiv.org/pdf/2507.05134
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4415163570
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415163570Canonical identifier for this work in OpenAlex
- Title
-
Deep Learning to Automate Parameter Extraction and Model Fitting of Two-Dimensional TransistorsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-07-07Full publication date if available
- Authors
-
Robert K. A. Bennett, Jan-Lucas Uslu, Harmon F. Gault, Asir Intisar Khan, Lauren Hoang, Tara Peña, Kathryn M. Neilson, Young Suh Song, Zhepeng Zhang, Andrew J. Mannix, Eric PopList of authors in order
- Landing page
-
https://arxiv.org/abs/2507.05134Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2507.05134Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2507.05134Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4415163570 |
|---|---|
| doi | |
| ids.openalex | https://openalex.org/W4415163570 |
| fwci | 0.0 |
| type | preprint |
| title | Deep Learning to Automate Parameter Extraction and Model Fitting of Two-Dimensional Transistors |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10558 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9865999817848206 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2208 |
| topics[0].subfield.display_name | Electrical and Electronic Engineering |
| topics[0].display_name | Advancements in Semiconductor Devices and Circuit Design |
| topics[1].id | https://openalex.org/T14117 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9542999863624573 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2208 |
| topics[1].subfield.display_name | Electrical and Electronic Engineering |
| topics[1].display_name | Integrated Circuits and Semiconductor Failure Analysis |
| topics[2].id | https://openalex.org/T10623 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9444000124931335 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2208 |
| topics[2].subfield.display_name | Electrical and Electronic Engineering |
| topics[2].display_name | Thin-Film Transistor Technologies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2507.05134 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2507.05134 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2507.05134 |
| indexed_in | arxiv |
| authorships[0].author.id | https://openalex.org/A5084302737 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7427-8724 |
| authorships[0].author.display_name | Robert K. A. Bennett |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Bennett, Robert K. A. |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5092346602 |
| authorships[1].author.orcid | https://orcid.org/0009-0009-1069-5778 |
| authorships[1].author.display_name | Jan-Lucas Uslu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Uslu, Jan-Lucas |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5119140916 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Harmon F. Gault |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Gault, Harmon F. |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5016699271 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-4635-4667 |
| authorships[3].author.display_name | Asir Intisar Khan |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Khan, Asir Intisar |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5018354165 |
| authorships[4].author.orcid | https://orcid.org/0009-0001-7556-8560 |
| authorships[4].author.display_name | Lauren Hoang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Hoang, Lauren |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5081755517 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-8404-9543 |
| authorships[5].author.display_name | Tara Peña |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Peña, Tara |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5014327459 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-1061-2919 |
| authorships[6].author.display_name | Kathryn M. Neilson |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Neilson, Kathryn |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5068692393 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-5229-1693 |
| authorships[7].author.display_name | Young Suh Song |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Song, Young Suh |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5057609385 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-9870-0720 |
| authorships[8].author.display_name | Zhepeng Zhang |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Zhang, Zhepeng |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5055435906 |
| authorships[9].author.orcid | https://orcid.org/0000-0003-4788-1506 |
| authorships[9].author.display_name | Andrew J. Mannix |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Mannix, Andrew J. |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5051662579 |
| authorships[10].author.orcid | https://orcid.org/0000-0003-0436-8534 |
| authorships[10].author.display_name | Eric Pop |
| authorships[10].author_position | last |
| authorships[10].raw_author_name | Pop, Eric |
| authorships[10].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2507.05134 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-14T00:00:00 |
| display_name | Deep Learning to Automate Parameter Extraction and Model Fitting of Two-Dimensional Transistors |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T04:12:42.849631 |
| primary_topic.id | https://openalex.org/T10558 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9865999817848206 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2208 |
| primary_topic.subfield.display_name | Electrical and Electronic Engineering |
| primary_topic.display_name | Advancements in Semiconductor Devices and Circuit Design |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:2507.05134 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2507.05134 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2507.05134 |
| primary_location.id | pmh:oai:arXiv.org:2507.05134 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2507.05134 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2507.05134 |
| publication_date | 2025-07-07 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.= | 137 |
| abstract_inverted_index.a | 2, 41, 50, 56, 80, 131 |
| abstract_inverted_index.35 | 163 |
| abstract_inverted_index.To | 35, 166 |
| abstract_inverted_index.We | 0, 117, 144 |
| abstract_inverted_index.be | 91 |
| abstract_inverted_index.by | 48, 93, 154 |
| abstract_inverted_index.is | 109 |
| abstract_inverted_index.of | 18, 77, 134 |
| abstract_inverted_index.on | 70, 95, 158, 170 |
| abstract_inverted_index.to | 6, 54, 112, 121 |
| abstract_inverted_index.we | 39, 178 |
| abstract_inverted_index.and | 29, 45, 105, 108, 151, 183 |
| abstract_inverted_index.can | 90 |
| abstract_inverted_index.for | 174 |
| abstract_inverted_index.key | 123 |
| abstract_inverted_index.not | 110 |
| abstract_inverted_index.our | 119, 181 |
| abstract_inverted_index.the | 67 |
| abstract_inverted_index.(2D) | 20 |
| abstract_inverted_index.0.99 | 138 |
| abstract_inverted_index.TCAD | 98 |
| abstract_inverted_index.This | 60 |
| abstract_inverted_index.also | 145 |
| abstract_inverted_index.code | 182 |
| abstract_inverted_index.data | 43, 72, 157, 185 |
| abstract_inverted_index.deep | 3, 171 |
| abstract_inverted_index.fits | 64 |
| abstract_inverted_index.from | 22, 74, 125 |
| abstract_inverted_index.have | 179 |
| abstract_inverted_index.sets | 186 |
| abstract_inverted_index.than | 84 |
| abstract_inverted_index.that | 147 |
| abstract_inverted_index.this | 37, 148 |
| abstract_inverted_index.well | 153 |
| abstract_inverted_index.when | 139 |
| abstract_inverted_index.~500 | 78 |
| abstract_inverted_index.after | 65 |
| abstract_inverted_index.apply | 118 |
| abstract_inverted_index.data. | 143 |
| abstract_inverted_index.fewer | 83 |
| abstract_inverted_index.other | 85 |
| abstract_inverted_index.task, | 38 |
| abstract_inverted_index.while | 161 |
| abstract_inverted_index.(TCAD) | 33 |
| abstract_inverted_index.(e.g., | 10 |
| abstract_inverted_index.WS$_2$ | 128 |
| abstract_inverted_index.defect | 16 |
| abstract_inverted_index.design | 32 |
| abstract_inverted_index.device | 58 |
| abstract_inverted_index.factor | 81 |
| abstract_inverted_index.future | 168 |
| abstract_inverted_index.median | 132 |
| abstract_inverted_index.method | 61 |
| abstract_inverted_index.neural | 52, 68 |
| abstract_inverted_index.recent | 86 |
| abstract_inverted_index.sample | 184 |
| abstract_inverted_index.scales | 152 |
| abstract_inverted_index.simple | 42 |
| abstract_inverted_index.($R^2$) | 136 |
| abstract_inverted_index.barrier | 14 |
| abstract_inverted_index.compact | 115 |
| abstract_inverted_index.complex | 101 |
| abstract_inverted_index.contact | 13 |
| abstract_inverted_index.design, | 177 |
| abstract_inverted_index.enables | 62 |
| abstract_inverted_index.extract | 7 |
| abstract_inverted_index.fitting | 89, 140, 162 |
| abstract_inverted_index.height, | 15 |
| abstract_inverted_index.inverse | 175 |
| abstract_inverted_index.limited | 111 |
| abstract_inverted_index.models, | 99 |
| abstract_inverted_index.models. | 116 |
| abstract_inverted_index.network | 53, 69 |
| abstract_inverted_index.online. | 187 |
| abstract_inverted_index.present | 1 |
| abstract_inverted_index.Schottky | 12 |
| abstract_inverted_index.achieved | 92 |
| abstract_inverted_index.approach | 5, 47, 120, 149 |
| abstract_inverted_index.devices, | 79 |
| abstract_inverted_index.effects, | 107 |
| abstract_inverted_index.efforts. | 87 |
| abstract_inverted_index.enabling | 25 |
| abstract_inverted_index.fitting. | 34 |
| abstract_inverted_index.learning | 4, 172 |
| abstract_inverted_index.measured | 141 |
| abstract_inverted_index.physical | 8 |
| abstract_inverted_index.research | 169 |
| abstract_inverted_index.rigorous | 97 |
| abstract_inverted_index.training | 49, 66, 94 |
| abstract_inverted_index.achieving | 130 |
| abstract_inverted_index.automated | 26 |
| abstract_inverted_index.generated | 73 |
| abstract_inverted_index.geometry, | 102 |
| abstract_inverted_index.implement | 40 |
| abstract_inverted_index.including | 100 |
| abstract_inverted_index.mobility, | 11 |
| abstract_inverted_index.monolayer | 127 |
| abstract_inverted_index.parameter | 27 |
| abstract_inverted_index.profiles) | 17 |
| abstract_inverted_index.published | 180 |
| abstract_inverted_index.secondary | 51 |
| abstract_inverted_index.approaches | 173 |
| abstract_inverted_index.electrical | 23, 71, 142, 156 |
| abstract_inverted_index.extraction | 28 |
| abstract_inverted_index.facilitate | 36, 167 |
| abstract_inverted_index.parameters | 9, 124, 164 |
| abstract_inverted_index.physically | 96 |
| abstract_inverted_index.simulator. | 59 |
| abstract_inverted_index.technology | 30 |
| abstract_inverted_index.transistor | 176 |
| abstract_inverted_index.transport, | 104 |
| abstract_inverted_index.>40$\times$ | 82 |
| abstract_inverted_index.approximate | 55 |
| abstract_inverted_index.coefficient | 133 |
| abstract_inverted_index.demonstrate | 146 |
| abstract_inverted_index.generalizes | 150 |
| abstract_inverted_index.inexpensive | 114 |
| abstract_inverted_index.simulations | 76 |
| abstract_inverted_index.transistors | 21, 160 |
| abstract_inverted_index.augmentation | 44 |
| abstract_inverted_index.experimental | 126 |
| abstract_inverted_index.high-quality | 63 |
| abstract_inverted_index.pre-training | 46 |
| abstract_inverted_index.transistors, | 129 |
| abstract_inverted_index.Consequently, | 88 |
| abstract_inverted_index.determination | 135 |
| abstract_inverted_index.electrostatic | 106 |
| abstract_inverted_index.measurements, | 24 |
| abstract_inverted_index.physics-based | 57, 75 |
| abstract_inverted_index.computer-aided | 31 |
| abstract_inverted_index.computationally | 113 |
| abstract_inverted_index.self-consistent | 103 |
| abstract_inverted_index.simultaneously. | 165 |
| abstract_inverted_index.two-dimensional | 19 |
| abstract_inverted_index.reverse-engineer | 122 |
| abstract_inverted_index.reverse-engineering | 155 |
| abstract_inverted_index.high-electron-mobility | 159 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 11 |
| citation_normalized_percentile.value | 0.5479976 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |