Deep learning-driven inverse design of all-dielectric silicon metasurfaces with targeted spectral response Article Swipe
Zhao Zhang
,
Yuzhang Liang
,
Haonan Wei
,
Wei Peng
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1063/5.0288038
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1063/5.0288038
The inverse design of all-dielectric metasurfaces faces challenges, including the reliance on full-spectrum input and the limitation of structure design to predefined geometries. This paper constructs a deep-learning-driven inverse-design framework that combines a fitness function with multi-strategy optimization algorithms to achieve the on-demand design of all-silicon metasurfaces. Here, the fitness function enables the quantification of convex-shaped spectral peaks (based on their wavelength and intensity) by combining a weight mechanism and avoiding interference from irrelevant wavelength bands. Meanwhile, the target error is monitored in real time through the fitness function value, enabling precise control over single-peak, dual-peak, and three-peak spectral responses. Moreover, three complementary optimization algorithms are considered: discrete optimization to explore full-degree-of-freedom structures, linear optimization to generate block-shaped and processable structures through parameterized row scanning, and shape optimization to simplify the process by restricting structures to regular geometries. The effective optimization of single-peak, dual-peak, and three-peak from the numerical simulation confirms that our proposed framework possesses distinct advantages, including a minimal target wavelength error, an order-of-magnitude higher efficiency, and excellent consistency between the fitness function value and the actual spectral deviation. This work enables, for the first time, the transformation of the silicon metasurface design from a “full-spectrum trial-and-error” approach to a “key-feature-driven reverse engineering” paradigm.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1063/5.0288038
- OA Status
- hybrid
- References
- 38
- OpenAlex ID
- https://openalex.org/W4415613016
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415613016Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1063/5.0288038Digital Object Identifier
- Title
-
Deep learning-driven inverse design of all-dielectric silicon metasurfaces with targeted spectral responseWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-10-28Full publication date if available
- Authors
-
Zhao Zhang, Yuzhang Liang, Haonan Wei, Wei PengList of authors in order
- Landing page
-
https://doi.org/10.1063/5.0288038Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1063/5.0288038Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
38Number of works referenced by this work
Full payload
| id | https://openalex.org/W4415613016 |
|---|---|
| doi | https://doi.org/10.1063/5.0288038 |
| ids.doi | https://doi.org/10.1063/5.0288038 |
| ids.openalex | https://openalex.org/W4415613016 |
| fwci | |
| type | article |
| title | Deep learning-driven inverse design of all-dielectric silicon metasurfaces with targeted spectral response |
| biblio.issue | 16 |
| biblio.volume | 138 |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list.value | 3500 |
| apc_list.currency | USD |
| apc_list.value_usd | 3500 |
| apc_paid.value | 3500 |
| apc_paid.currency | USD |
| apc_paid.value_usd | 3500 |
| language | en |
| locations[0].id | doi:10.1063/5.0288038 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S187991544 |
| locations[0].source.issn | 0021-8979, 1089-7550, 1520-8850 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 0021-8979 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Journal of Applied Physics |
| locations[0].source.host_organization | https://openalex.org/P4310320257 |
| locations[0].source.host_organization_name | American Institute of Physics |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310320257 |
| locations[0].source.host_organization_lineage_names | American Institute of Physics |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Journal of Applied Physics |
| locations[0].landing_page_url | https://doi.org/10.1063/5.0288038 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5101229664 |
| authorships[0].author.orcid | https://orcid.org/0009-0003-8058-9133 |
| authorships[0].author.display_name | Zhao Zhang |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I27357992 |
| authorships[0].affiliations[0].raw_affiliation_string | School of Physics, Dalian University of Technology, Dalian 116024, China |
| authorships[0].institutions[0].id | https://openalex.org/I27357992 |
| authorships[0].institutions[0].ror | https://ror.org/023hj5876 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I27357992 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Dalian University of Technology |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhao Zhang |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | School of Physics, Dalian University of Technology, Dalian 116024, China |
| authorships[1].author.id | https://openalex.org/A5036683345 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-6257-3547 |
| authorships[1].author.display_name | Yuzhang Liang |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I27357992 |
| authorships[1].affiliations[0].raw_affiliation_string | School of Physics, Dalian University of Technology, Dalian 116024, China |
| authorships[1].institutions[0].id | https://openalex.org/I27357992 |
| authorships[1].institutions[0].ror | https://ror.org/023hj5876 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I27357992 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Dalian University of Technology |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Yuzhang Liang |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | School of Physics, Dalian University of Technology, Dalian 116024, China |
| authorships[2].author.id | https://openalex.org/A5070266378 |
| authorships[2].author.orcid | https://orcid.org/0009-0006-7772-7840 |
| authorships[2].author.display_name | Haonan Wei |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I27357992 |
| authorships[2].affiliations[0].raw_affiliation_string | School of Physics, Dalian University of Technology, Dalian 116024, China |
| authorships[2].institutions[0].id | https://openalex.org/I27357992 |
| authorships[2].institutions[0].ror | https://ror.org/023hj5876 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I27357992 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Dalian University of Technology |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Haonan Wei |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | School of Physics, Dalian University of Technology, Dalian 116024, China |
| authorships[3].author.id | https://openalex.org/A5070853442 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-0246-0698 |
| authorships[3].author.display_name | Wei Peng |
| authorships[3].countries | CN |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I27357992 |
| authorships[3].affiliations[0].raw_affiliation_string | School of Physics, Dalian University of Technology, Dalian 116024, China |
| authorships[3].institutions[0].id | https://openalex.org/I27357992 |
| authorships[3].institutions[0].ror | https://ror.org/023hj5876 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I27357992 |
| authorships[3].institutions[0].country_code | CN |
| authorships[3].institutions[0].display_name | Dalian University of Technology |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Wei Peng |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | School of Physics, Dalian University of Technology, Dalian 116024, China |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1063/5.0288038 |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-28T00:00:00 |
| display_name | Deep learning-driven inverse design of all-dielectric silicon metasurfaces with targeted spectral response |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1063/5.0288038 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S187991544 |
| best_oa_location.source.issn | 0021-8979, 1089-7550, 1520-8850 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 0021-8979 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Journal of Applied Physics |
| best_oa_location.source.host_organization | https://openalex.org/P4310320257 |
| best_oa_location.source.host_organization_name | American Institute of Physics |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310320257 |
| best_oa_location.source.host_organization_lineage_names | American Institute of Physics |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Journal of Applied Physics |
| best_oa_location.landing_page_url | https://doi.org/10.1063/5.0288038 |
| primary_location.id | doi:10.1063/5.0288038 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S187991544 |
| primary_location.source.issn | 0021-8979, 1089-7550, 1520-8850 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 0021-8979 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Journal of Applied Physics |
| primary_location.source.host_organization | https://openalex.org/P4310320257 |
| primary_location.source.host_organization_name | American Institute of Physics |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310320257 |
| primary_location.source.host_organization_lineage_names | American Institute of Physics |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Journal of Applied Physics |
| primary_location.landing_page_url | https://doi.org/10.1063/5.0288038 |
| publication_date | 2025-10-28 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W2955280314, https://openalex.org/W3117413265, https://openalex.org/W4394961339, https://openalex.org/W4396935641, https://openalex.org/W2806536390, https://openalex.org/W2962914006, https://openalex.org/W2974878544, https://openalex.org/W2949257317, https://openalex.org/W2996691366, https://openalex.org/W3081636821, https://openalex.org/W3123218896, https://openalex.org/W4392620603, https://openalex.org/W2972869543, https://openalex.org/W4220688644, https://openalex.org/W2775280502, https://openalex.org/W2891797827, https://openalex.org/W2937816906, https://openalex.org/W3031385593, https://openalex.org/W4304206722, https://openalex.org/W4409122258, https://openalex.org/W4408538634, https://openalex.org/W4408905362, https://openalex.org/W2803281408, https://openalex.org/W4281828204, https://openalex.org/W4323341897, https://openalex.org/W4391899108, https://openalex.org/W4409356811, https://openalex.org/W2991464628, https://openalex.org/W4296231863, https://openalex.org/W4297499176, https://openalex.org/W2989293933, https://openalex.org/W4229066872, https://openalex.org/W2949960465, https://openalex.org/W3127785322, https://openalex.org/W2900701156, https://openalex.org/W3118655897, https://openalex.org/W3195343891, https://openalex.org/W4306405725 |
| referenced_works_count | 38 |
| abstract_inverted_index.a | 26, 32, 66, 159, 196, 201 |
| abstract_inverted_index.an | 164 |
| abstract_inverted_index.by | 64, 132 |
| abstract_inverted_index.in | 82 |
| abstract_inverted_index.is | 80 |
| abstract_inverted_index.of | 3, 17, 44, 54, 141, 190 |
| abstract_inverted_index.on | 11, 59 |
| abstract_inverted_index.to | 20, 39, 109, 115, 128, 135, 200 |
| abstract_inverted_index.The | 0, 138 |
| abstract_inverted_index.and | 14, 62, 69, 96, 118, 125, 144, 168, 176 |
| abstract_inverted_index.are | 105 |
| abstract_inverted_index.for | 184 |
| abstract_inverted_index.our | 152 |
| abstract_inverted_index.row | 123 |
| abstract_inverted_index.the | 9, 15, 41, 48, 52, 77, 86, 130, 147, 172, 177, 185, 188, 191 |
| abstract_inverted_index.This | 23, 181 |
| abstract_inverted_index.from | 72, 146, 195 |
| abstract_inverted_index.over | 93 |
| abstract_inverted_index.real | 83 |
| abstract_inverted_index.that | 30, 151 |
| abstract_inverted_index.time | 84 |
| abstract_inverted_index.with | 35 |
| abstract_inverted_index.work | 182 |
| abstract_inverted_index.Here, | 47 |
| abstract_inverted_index.error | 79 |
| abstract_inverted_index.faces | 6 |
| abstract_inverted_index.first | 186 |
| abstract_inverted_index.input | 13 |
| abstract_inverted_index.paper | 24 |
| abstract_inverted_index.peaks | 57 |
| abstract_inverted_index.shape | 126 |
| abstract_inverted_index.their | 60 |
| abstract_inverted_index.three | 101 |
| abstract_inverted_index.time, | 187 |
| abstract_inverted_index.value | 175 |
| abstract_inverted_index.(based | 58 |
| abstract_inverted_index.actual | 178 |
| abstract_inverted_index.bands. | 75 |
| abstract_inverted_index.design | 2, 19, 43, 194 |
| abstract_inverted_index.error, | 163 |
| abstract_inverted_index.higher | 166 |
| abstract_inverted_index.linear | 113 |
| abstract_inverted_index.target | 78, 161 |
| abstract_inverted_index.value, | 89 |
| abstract_inverted_index.weight | 67 |
| abstract_inverted_index.achieve | 40 |
| abstract_inverted_index.between | 171 |
| abstract_inverted_index.control | 92 |
| abstract_inverted_index.enables | 51 |
| abstract_inverted_index.explore | 110 |
| abstract_inverted_index.fitness | 33, 49, 87, 173 |
| abstract_inverted_index.inverse | 1 |
| abstract_inverted_index.minimal | 160 |
| abstract_inverted_index.precise | 91 |
| abstract_inverted_index.process | 131 |
| abstract_inverted_index.regular | 136 |
| abstract_inverted_index.reverse | 203 |
| abstract_inverted_index.silicon | 192 |
| abstract_inverted_index.through | 85, 121 |
| abstract_inverted_index.approach | 199 |
| abstract_inverted_index.avoiding | 70 |
| abstract_inverted_index.combines | 31 |
| abstract_inverted_index.confirms | 150 |
| abstract_inverted_index.discrete | 107 |
| abstract_inverted_index.distinct | 156 |
| abstract_inverted_index.enables, | 183 |
| abstract_inverted_index.enabling | 90 |
| abstract_inverted_index.function | 34, 50, 88, 174 |
| abstract_inverted_index.generate | 116 |
| abstract_inverted_index.proposed | 153 |
| abstract_inverted_index.reliance | 10 |
| abstract_inverted_index.simplify | 129 |
| abstract_inverted_index.spectral | 56, 98, 179 |
| abstract_inverted_index.Moreover, | 100 |
| abstract_inverted_index.combining | 65 |
| abstract_inverted_index.effective | 139 |
| abstract_inverted_index.excellent | 169 |
| abstract_inverted_index.framework | 29, 154 |
| abstract_inverted_index.including | 8, 158 |
| abstract_inverted_index.mechanism | 68 |
| abstract_inverted_index.monitored | 81 |
| abstract_inverted_index.numerical | 148 |
| abstract_inverted_index.on-demand | 42 |
| abstract_inverted_index.paradigm. | 205 |
| abstract_inverted_index.possesses | 155 |
| abstract_inverted_index.scanning, | 124 |
| abstract_inverted_index.structure | 18 |
| abstract_inverted_index.Meanwhile, | 76 |
| abstract_inverted_index.algorithms | 38, 104 |
| abstract_inverted_index.constructs | 25 |
| abstract_inverted_index.deviation. | 180 |
| abstract_inverted_index.dual-peak, | 95, 143 |
| abstract_inverted_index.intensity) | 63 |
| abstract_inverted_index.irrelevant | 73 |
| abstract_inverted_index.limitation | 16 |
| abstract_inverted_index.predefined | 21 |
| abstract_inverted_index.responses. | 99 |
| abstract_inverted_index.simulation | 149 |
| abstract_inverted_index.structures | 120, 134 |
| abstract_inverted_index.three-peak | 97, 145 |
| abstract_inverted_index.wavelength | 61, 74, 162 |
| abstract_inverted_index.advantages, | 157 |
| abstract_inverted_index.all-silicon | 45 |
| abstract_inverted_index.challenges, | 7 |
| abstract_inverted_index.considered: | 106 |
| abstract_inverted_index.consistency | 170 |
| abstract_inverted_index.efficiency, | 167 |
| abstract_inverted_index.geometries. | 22, 137 |
| abstract_inverted_index.metasurface | 193 |
| abstract_inverted_index.processable | 119 |
| abstract_inverted_index.restricting | 133 |
| abstract_inverted_index.structures, | 112 |
| abstract_inverted_index.block-shaped | 117 |
| abstract_inverted_index.interference | 71 |
| abstract_inverted_index.metasurfaces | 5 |
| abstract_inverted_index.optimization | 37, 103, 108, 114, 127, 140 |
| abstract_inverted_index.single-peak, | 94, 142 |
| abstract_inverted_index.complementary | 102 |
| abstract_inverted_index.convex-shaped | 55 |
| abstract_inverted_index.full-spectrum | 12 |
| abstract_inverted_index.metasurfaces. | 46 |
| abstract_inverted_index.parameterized | 122 |
| abstract_inverted_index.all-dielectric | 4 |
| abstract_inverted_index.engineering” | 204 |
| abstract_inverted_index.inverse-design | 28 |
| abstract_inverted_index.multi-strategy | 36 |
| abstract_inverted_index.quantification | 53 |
| abstract_inverted_index.transformation | 189 |
| abstract_inverted_index.“full-spectrum | 197 |
| abstract_inverted_index.order-of-magnitude | 165 |
| abstract_inverted_index.trial-and-error” | 198 |
| abstract_inverted_index.deep-learning-driven | 27 |
| abstract_inverted_index.“key-feature-driven | 202 |
| abstract_inverted_index.full-degree-of-freedom | 111 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |