Physics-aware graph neural networks for automated tight-binding model construction in quantum transport simulations Article Swipe
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-7831376/v1
Tight-binding (TB) model is crucial for quantum transport simulations of semiconductor devices, critically determining the electrical characteristics of channel materials. Here, we propose a graph neural network (GNN)-based framework for automated TB model construction. By integrating atomic sites (nodes) and chemical bonds (edges) into atomistic graph representations, our method efficiently extracts orbital onsite energies and inter-orbital hopping parameters through supervised learning of density functional theory-derived band structures. The physics-aware architecture of GNNs, which inherently mirrors the atomic and bonding configurations of materials, ensures that the predicted TB models retain intrinsic physical interpretability, including the sparse matrix form, tunable orbital localization, exponentially decaying hopping strength, and defect-resolved local density of states, significantly broadening their applicability. As a result, it allows co-training on defective and defect-free systems, so that structural perturbations are naturally encoded as parameter changes, overcoming the lack of hopping parameters between distinct configurations and enabling the construction of Hamiltonians for non-periodic, defect-containing device channels, a longstanding challenge in ab initio quantum transport modeling. Furthermore, we develop the model size scaling and band structure editing functionalities, enabling flexible manipulation of electronic properties and cutting computational costs. We apply this framework to amorphous In-Ga-Zn-O and 4H-silicon carbide, two technologically critical channel materials whose performance-limiting defects cause unresolved reliability issues such as current degradation and threshold voltage drift, arising from quantum effects that cannot be captured by conventional drift-diffusion models. This work bridges the gap between ab initio calculations and device-level modeling, offering a transformative tool for semiconductor device design and beyond.
Related Topics
- Type
- preprint
- Landing Page
- https://doi.org/10.21203/rs.3.rs-7831376/v1
- https://www.researchsquare.com/article/rs-7831376/latest.pdf
- OA Status
- gold
- OpenAlex ID
- https://openalex.org/W4415981563
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415981563Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.21203/rs.3.rs-7831376/v1Digital Object Identifier
- Title
-
Physics-aware graph neural networks for automated tight-binding model construction in quantum transport simulationsWork title
- Type
-
preprintOpenAlex work type
- Publication year
-
2025Year of publication
- Publication date
-
2025-11-07Full publication date if available
- Authors
-
Lei Liao, Yawei Lv, Shihong Yu, Tang Weimin, Haipeng Lan, Hui‐Xiong Deng, Kenli Li, Changzhong JiangList of authors in order
- Landing page
-
https://doi.org/10.21203/rs.3.rs-7831376/v1Publisher landing page
- PDF URL
-
https://www.researchsquare.com/article/rs-7831376/latest.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://www.researchsquare.com/article/rs-7831376/latest.pdfDirect OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4415981563 |
|---|---|
| doi | https://doi.org/10.21203/rs.3.rs-7831376/v1 |
| ids.doi | https://doi.org/10.21203/rs.3.rs-7831376/v1 |
| ids.openalex | https://openalex.org/W4415981563 |
| fwci | |
| type | preprint |
| title | Physics-aware graph neural networks for automated tight-binding model construction in quantum transport simulations |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | |
| locations[0].id | doi:10.21203/rs.3.rs-7831376/v1 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.researchsquare.com/article/rs-7831376/latest.pdf |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.21203/rs.3.rs-7831376/v1 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5036022527 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-1325-2410 |
| authorships[0].author.display_name | Lei Liao |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I16609230 |
| authorships[0].affiliations[0].raw_affiliation_string | Hunan University |
| authorships[0].institutions[0].id | https://openalex.org/I16609230 |
| authorships[0].institutions[0].ror | https://ror.org/05htk5m33 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I16609230 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Hunan University |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Lei Liao |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Hunan University |
| authorships[1].author.id | https://openalex.org/A5032875274 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4217-8830 |
| authorships[1].author.display_name | Yawei Lv |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I16609230 |
| authorships[1].affiliations[0].raw_affiliation_string | Hunan University |
| authorships[1].institutions[0].id | https://openalex.org/I16609230 |
| authorships[1].institutions[0].ror | https://ror.org/05htk5m33 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I16609230 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Hunan University |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Yawei Lv |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Hunan University |
| authorships[2].author.id | https://openalex.org/A5045670893 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Shihong Yu |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I16609230 |
| authorships[2].affiliations[0].raw_affiliation_string | Hunan University |
| authorships[2].institutions[0].id | https://openalex.org/I16609230 |
| authorships[2].institutions[0].ror | https://ror.org/05htk5m33 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I16609230 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Hunan University |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Shihong Yu |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Hunan University |
| authorships[3].author.id | https://openalex.org/A5052646821 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Tang Weimin |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I16609230 |
| authorships[3].affiliations[0].raw_affiliation_string | Hunan University |
| authorships[3].institutions[0].id | https://openalex.org/I16609230 |
| authorships[3].institutions[0].ror | https://ror.org/05htk5m33 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I16609230 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | Hunan University |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Weimin Tang |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Hunan University |
| authorships[4].author.id | https://openalex.org/A5108955334 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Haipeng Lan |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I16609230 |
| authorships[4].affiliations[0].raw_affiliation_string | Hunan University |
| authorships[4].institutions[0].id | https://openalex.org/I16609230 |
| authorships[4].institutions[0].ror | https://ror.org/05htk5m33 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I16609230 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | Hunan University |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Haipeng Lan |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Hunan University |
| authorships[5].author.id | https://openalex.org/A5086581441 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-2155-8727 |
| authorships[5].author.display_name | Hui‐Xiong Deng |
| authorships[5].countries | CN |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I19820366, https://openalex.org/I4210149211 |
| authorships[5].affiliations[0].raw_affiliation_string | Institute of Semiconductors, Chinese Academy of Sciences |
| authorships[5].institutions[0].id | https://openalex.org/I19820366 |
| authorships[5].institutions[0].ror | https://ror.org/034t30j35 |
| authorships[5].institutions[0].type | government |
| authorships[5].institutions[0].lineage | https://openalex.org/I19820366 |
| authorships[5].institutions[0].country_code | CN |
| authorships[5].institutions[0].display_name | Chinese Academy of Sciences |
| authorships[5].institutions[1].id | https://openalex.org/I4210149211 |
| authorships[5].institutions[1].ror | https://ror.org/048dd0611 |
| authorships[5].institutions[1].type | facility |
| authorships[5].institutions[1].lineage | https://openalex.org/I19820366, https://openalex.org/I4210149211 |
| authorships[5].institutions[1].country_code | CN |
| authorships[5].institutions[1].display_name | Institute of Semiconductors |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Hui-Xiong Deng |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Institute of Semiconductors, Chinese Academy of Sciences |
| authorships[6].author.id | https://openalex.org/A5078793726 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-2635-7716 |
| authorships[6].author.display_name | Kenli Li |
| authorships[6].countries | CN |
| authorships[6].affiliations[0].institution_ids | https://openalex.org/I16609230 |
| authorships[6].affiliations[0].raw_affiliation_string | Hunan University |
| authorships[6].institutions[0].id | https://openalex.org/I16609230 |
| authorships[6].institutions[0].ror | https://ror.org/05htk5m33 |
| authorships[6].institutions[0].type | education |
| authorships[6].institutions[0].lineage | https://openalex.org/I16609230 |
| authorships[6].institutions[0].country_code | CN |
| authorships[6].institutions[0].display_name | Hunan University |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Kenli Li |
| authorships[6].is_corresponding | False |
| authorships[6].raw_affiliation_strings | Hunan University |
| authorships[7].author.id | https://openalex.org/A5028412020 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-6599-8850 |
| authorships[7].author.display_name | Changzhong Jiang |
| authorships[7].countries | CN |
| authorships[7].affiliations[0].institution_ids | https://openalex.org/I16609230 |
| authorships[7].affiliations[0].raw_affiliation_string | Hunan University |
| authorships[7].institutions[0].id | https://openalex.org/I16609230 |
| authorships[7].institutions[0].ror | https://ror.org/05htk5m33 |
| authorships[7].institutions[0].type | education |
| authorships[7].institutions[0].lineage | https://openalex.org/I16609230 |
| authorships[7].institutions[0].country_code | CN |
| authorships[7].institutions[0].display_name | Hunan University |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Changzhong Jiang |
| authorships[7].is_corresponding | False |
| authorships[7].raw_affiliation_strings | Hunan University |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.researchsquare.com/article/rs-7831376/latest.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-11-07T00:00:00 |
| display_name | Physics-aware graph neural networks for automated tight-binding model construction in quantum transport simulations |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-07T23:23:33.682996 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.21203/rs.3.rs-7831376/v1 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.researchsquare.com/article/rs-7831376/latest.pdf |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-7831376/v1 |
| primary_location.id | doi:10.21203/rs.3.rs-7831376/v1 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.researchsquare.com/article/rs-7831376/latest.pdf |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-7831376/v1 |
| publication_date | 2025-11-07 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 24, 116, 156, 242 |
| abstract_inverted_index.As | 115 |
| abstract_inverted_index.By | 35 |
| abstract_inverted_index.TB | 32, 87 |
| abstract_inverted_index.We | 187 |
| abstract_inverted_index.ab | 160, 235 |
| abstract_inverted_index.as | 133, 210 |
| abstract_inverted_index.be | 223 |
| abstract_inverted_index.by | 225 |
| abstract_inverted_index.in | 159 |
| abstract_inverted_index.is | 4 |
| abstract_inverted_index.it | 118 |
| abstract_inverted_index.of | 10, 18, 62, 71, 81, 109, 139, 149, 180 |
| abstract_inverted_index.on | 121 |
| abstract_inverted_index.so | 126 |
| abstract_inverted_index.to | 191 |
| abstract_inverted_index.we | 22, 166 |
| abstract_inverted_index.The | 68 |
| abstract_inverted_index.and | 40, 55, 78, 105, 123, 145, 172, 183, 194, 213, 238, 249 |
| abstract_inverted_index.are | 130 |
| abstract_inverted_index.for | 6, 30, 151, 245 |
| abstract_inverted_index.gap | 233 |
| abstract_inverted_index.our | 48 |
| abstract_inverted_index.the | 15, 76, 85, 94, 137, 147, 168, 232 |
| abstract_inverted_index.two | 197 |
| abstract_inverted_index.(TB) | 2 |
| abstract_inverted_index.This | 229 |
| abstract_inverted_index.band | 66, 173 |
| abstract_inverted_index.from | 218 |
| abstract_inverted_index.into | 44 |
| abstract_inverted_index.lack | 138 |
| abstract_inverted_index.size | 170 |
| abstract_inverted_index.such | 209 |
| abstract_inverted_index.that | 84, 127, 221 |
| abstract_inverted_index.this | 189 |
| abstract_inverted_index.tool | 244 |
| abstract_inverted_index.work | 230 |
| abstract_inverted_index.GNNs, | 72 |
| abstract_inverted_index.Here, | 21 |
| abstract_inverted_index.apply | 188 |
| abstract_inverted_index.bonds | 42 |
| abstract_inverted_index.cause | 205 |
| abstract_inverted_index.form, | 97 |
| abstract_inverted_index.graph | 25, 46 |
| abstract_inverted_index.local | 107 |
| abstract_inverted_index.model | 3, 33, 169 |
| abstract_inverted_index.sites | 38 |
| abstract_inverted_index.their | 113 |
| abstract_inverted_index.which | 73 |
| abstract_inverted_index.whose | 202 |
| abstract_inverted_index.allows | 119 |
| abstract_inverted_index.atomic | 37, 77 |
| abstract_inverted_index.cannot | 222 |
| abstract_inverted_index.costs. | 186 |
| abstract_inverted_index.design | 248 |
| abstract_inverted_index.device | 154, 247 |
| abstract_inverted_index.drift, | 216 |
| abstract_inverted_index.initio | 161, 236 |
| abstract_inverted_index.issues | 208 |
| abstract_inverted_index.matrix | 96 |
| abstract_inverted_index.method | 49 |
| abstract_inverted_index.models | 88 |
| abstract_inverted_index.neural | 26 |
| abstract_inverted_index.onsite | 53 |
| abstract_inverted_index.retain | 89 |
| abstract_inverted_index.sparse | 95 |
| abstract_inverted_index.(edges) | 43 |
| abstract_inverted_index.(nodes) | 39 |
| abstract_inverted_index.arising | 217 |
| abstract_inverted_index.between | 142, 234 |
| abstract_inverted_index.beyond. | 250 |
| abstract_inverted_index.bonding | 79 |
| abstract_inverted_index.bridges | 231 |
| abstract_inverted_index.channel | 19, 200 |
| abstract_inverted_index.crucial | 5 |
| abstract_inverted_index.current | 211 |
| abstract_inverted_index.cutting | 184 |
| abstract_inverted_index.defects | 204 |
| abstract_inverted_index.density | 63, 108 |
| abstract_inverted_index.develop | 167 |
| abstract_inverted_index.editing | 175 |
| abstract_inverted_index.effects | 220 |
| abstract_inverted_index.encoded | 132 |
| abstract_inverted_index.ensures | 83 |
| abstract_inverted_index.hopping | 57, 103, 140 |
| abstract_inverted_index.mirrors | 75 |
| abstract_inverted_index.models. | 228 |
| abstract_inverted_index.network | 27 |
| abstract_inverted_index.orbital | 52, 99 |
| abstract_inverted_index.propose | 23 |
| abstract_inverted_index.quantum | 7, 162, 219 |
| abstract_inverted_index.result, | 117 |
| abstract_inverted_index.scaling | 171 |
| abstract_inverted_index.states, | 110 |
| abstract_inverted_index.through | 59 |
| abstract_inverted_index.tunable | 98 |
| abstract_inverted_index.voltage | 215 |
| abstract_inverted_index.captured | 224 |
| abstract_inverted_index.carbide, | 196 |
| abstract_inverted_index.changes, | 135 |
| abstract_inverted_index.chemical | 41 |
| abstract_inverted_index.critical | 199 |
| abstract_inverted_index.decaying | 102 |
| abstract_inverted_index.devices, | 12 |
| abstract_inverted_index.distinct | 143 |
| abstract_inverted_index.enabling | 146, 177 |
| abstract_inverted_index.energies | 54 |
| abstract_inverted_index.extracts | 51 |
| abstract_inverted_index.flexible | 178 |
| abstract_inverted_index.learning | 61 |
| abstract_inverted_index.offering | 241 |
| abstract_inverted_index.physical | 91 |
| abstract_inverted_index.systems, | 125 |
| abstract_inverted_index.amorphous | 192 |
| abstract_inverted_index.atomistic | 45 |
| abstract_inverted_index.automated | 31 |
| abstract_inverted_index.challenge | 158 |
| abstract_inverted_index.channels, | 155 |
| abstract_inverted_index.defective | 122 |
| abstract_inverted_index.framework | 29, 190 |
| abstract_inverted_index.including | 93 |
| abstract_inverted_index.intrinsic | 90 |
| abstract_inverted_index.materials | 201 |
| abstract_inverted_index.modeling, | 240 |
| abstract_inverted_index.modeling. | 164 |
| abstract_inverted_index.naturally | 131 |
| abstract_inverted_index.parameter | 134 |
| abstract_inverted_index.predicted | 86 |
| abstract_inverted_index.strength, | 104 |
| abstract_inverted_index.structure | 174 |
| abstract_inverted_index.threshold | 214 |
| abstract_inverted_index.transport | 8, 163 |
| abstract_inverted_index.4H-silicon | 195 |
| abstract_inverted_index.In-Ga-Zn-O | 193 |
| abstract_inverted_index.broadening | 112 |
| abstract_inverted_index.critically | 13 |
| abstract_inverted_index.electrical | 16 |
| abstract_inverted_index.electronic | 181 |
| abstract_inverted_index.functional | 64 |
| abstract_inverted_index.inherently | 74 |
| abstract_inverted_index.materials, | 82 |
| abstract_inverted_index.materials. | 20 |
| abstract_inverted_index.overcoming | 136 |
| abstract_inverted_index.parameters | 58, 141 |
| abstract_inverted_index.properties | 182 |
| abstract_inverted_index.structural | 128 |
| abstract_inverted_index.supervised | 60 |
| abstract_inverted_index.unresolved | 206 |
| abstract_inverted_index.(GNN)-based | 28 |
| abstract_inverted_index.co-training | 120 |
| abstract_inverted_index.defect-free | 124 |
| abstract_inverted_index.degradation | 212 |
| abstract_inverted_index.determining | 14 |
| abstract_inverted_index.efficiently | 50 |
| abstract_inverted_index.integrating | 36 |
| abstract_inverted_index.reliability | 207 |
| abstract_inverted_index.simulations | 9 |
| abstract_inverted_index.structures. | 67 |
| abstract_inverted_index.Furthermore, | 165 |
| abstract_inverted_index.Hamiltonians | 150 |
| abstract_inverted_index.architecture | 70 |
| abstract_inverted_index.calculations | 237 |
| abstract_inverted_index.construction | 148 |
| abstract_inverted_index.conventional | 226 |
| abstract_inverted_index.device-level | 239 |
| abstract_inverted_index.longstanding | 157 |
| abstract_inverted_index.manipulation | 179 |
| abstract_inverted_index.Tight-binding | 1 |
| abstract_inverted_index.computational | 185 |
| abstract_inverted_index.construction. | 34 |
| abstract_inverted_index.exponentially | 101 |
| abstract_inverted_index.inter-orbital | 56 |
| abstract_inverted_index.localization, | 100 |
| abstract_inverted_index.non-periodic, | 152 |
| abstract_inverted_index.perturbations | 129 |
| abstract_inverted_index.physics-aware | 69 |
| abstract_inverted_index.semiconductor | 11, 246 |
| abstract_inverted_index.significantly | 111 |
| abstract_inverted_index.applicability. | 114 |
| abstract_inverted_index.configurations | 80, 144 |
| abstract_inverted_index.theory-derived | 65 |
| abstract_inverted_index.transformative | 243 |
| abstract_inverted_index.characteristics | 17 |
| abstract_inverted_index.defect-resolved | 106 |
| abstract_inverted_index.drift-diffusion | 227 |
| abstract_inverted_index.technologically | 198 |
| abstract_inverted_index.functionalities, | 176 |
| abstract_inverted_index.representations, | 47 |
| abstract_inverted_index.defect-containing | 153 |
| abstract_inverted_index.interpretability, | 92 |
| abstract_inverted_index.performance-limiting | 203 |
| abstract_inverted_index.<title>Abstract</title> | 0 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile |