{"id":"https://openalex.org/W7223207481","doi":"https://doi.org/10.1364/oe.612531","title":"Green-preconditioned dynamic graph neural operator for electromagnetic field prediction in heterogeneous media","display_name":"Green-preconditioned dynamic graph neural operator for electromagnetic field prediction in heterogeneous media","publication_year":2026,"publication_date":"2026-10-22","ids":{"openalex":"https://openalex.org/W7223207481","doi":"https://doi.org/10.1364/oe.612531","pmid":"https://pubmed.ncbi.nlm.nih.gov/42972829"},"language":"en","primary_location":{"id":"doi:10.1364/oe.612531","doi":"https://doi.org/10.1364/oe.612531","is_oa":true,"landing_page_url":"https://doi.org/10.1364/oe.612531","pdf_url":null,"source":{"id":"https://openalex.org/S178776955","display_name":"Optics Express","issn_l":"1094-4087","issn":["1094-4087"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-b","jufo-1","ki-jl-1","medline","norway-2","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315679","host_organization_name":"Optica Publishing Group","host_organization_lineage":["https://openalex.org/P4310315679"],"host_organization_lineage_names":["Optica Publishing Group"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Optics Express","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1364/oe.612531","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159286172","display_name":"Gao zhiwei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I90090648","display_name":"Shijiazhuang Tiedao University","ror":"https://ror.org/022e9e065","country_code":"CN","type":"education","lineage":["https://openalex.org/I90090648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Gao","raw_affiliation_strings":["Shijiazhuang Tiedao University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shijiazhuang Tiedao University","institution_ids":["https://openalex.org/I90090648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159270019","display_name":"Zhijie Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I90090648","display_name":"Shijiazhuang Tiedao University","ror":"https://ror.org/022e9e065","country_code":"CN","type":"education","lineage":["https://openalex.org/I90090648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Liu","raw_affiliation_strings":["Shijiazhuang Tiedao University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shijiazhuang Tiedao University","institution_ids":["https://openalex.org/I90090648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159276739","display_name":"chengan sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I90090648","display_name":"Shijiazhuang Tiedao University","ror":"https://ror.org/022e9e065","country_code":"CN","type":"education","lineage":["https://openalex.org/I90090648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengan Sun","raw_affiliation_strings":["Shijiazhuang Tiedao University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shijiazhuang Tiedao University","institution_ids":["https://openalex.org/I90090648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159288706","display_name":"Li Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I90090648","display_name":"Shijiazhuang Tiedao University","ror":"https://ror.org/022e9e065","country_code":"CN","type":"education","lineage":["https://openalex.org/I90090648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["Shijiazhuang Tiedao University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shijiazhuang Tiedao University","institution_ids":["https://openalex.org/I90090648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159275645","display_name":"Zheng Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I90090648","display_name":"Shijiazhuang Tiedao University","ror":"https://ror.org/022e9e065","country_code":"CN","type":"education","lineage":["https://openalex.org/I90090648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Li","raw_affiliation_strings":["Shijiazhuang Tiedao University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shijiazhuang Tiedao University","institution_ids":["https://openalex.org/I90090648"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90090648"],"apc_list":{"value":2270,"currency":"USD","value_usd":2270},"apc_paid":{"value":2270,"currency":"USD","value_usd":2270},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74874432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"22","first_page":"42859","last_page":"42859"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9526000022888184,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9526000022888184,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11263","display_name":"Electromagnetic Simulation and Numerical Methods","score":0.019600000232458115,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.013500000350177288,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/electromagnetic-field-prediction","display_name":"electromagnetic field prediction","score":0.8360000252723694},{"id":"https://openalex.org/keywords/heterogeneous-media","display_name":"heterogeneous media","score":0.9769999980926514},{"id":"https://openalex.org/keywords/graph-neural-operators","display_name":"graph neural operators","score":0.8479999899864197},{"id":"https://openalex.org/keywords/green-s-function","display_name":"Green's function","score":0.5120000243186951},{"id":"https://openalex.org/keywords/u-net-comparison","display_name":"U-Net comparison","score":0.6819999814033508},{"id":"https://openalex.org/keywords/computational-cost-reduction","display_name":"computational complexity reduction","score":0.4440000057220459},{"id":"https://openalex.org/keywords/electromagnetic-scattering","display_name":"electromagnetic scattering","score":0.3109999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6247000098228455},{"id":"https://openalex.org/C28843909","wikidata":"https://www.wikidata.org/wiki/Q177625","display_name":"Electromagnetic field","level":2,"score":0.5629000067710876},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4966999888420105},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.4578999876976013},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39890000224113464},{"id":"https://openalex.org/C149773537","wikidata":"https://www.wikidata.org/wiki/Q12969754","display_name":"Electromagnetic radiation","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.35120001435279846},{"id":"https://openalex.org/C44886760","wikidata":"https://www.wikidata.org/wiki/Q1758425","display_name":"Wave propagation","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C134765980","wikidata":"https://www.wikidata.org/wiki/Q879126","display_name":"Bitwise operation","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C42067758","wikidata":"https://www.wikidata.org/wiki/Q174102","display_name":"Refractive index","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C154236941","wikidata":"https://www.wikidata.org/wiki/Q942347","display_name":"Physical optics","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C206844423","wikidata":"https://www.wikidata.org/wiki/Q5157313","display_name":"Computational electromagnetics","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C2984039729","wikidata":"https://www.wikidata.org/wiki/Q11406","display_name":"Electromagnetic theory","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C25227671","wikidata":"https://www.wikidata.org/wiki/Q13405516","display_name":"Near and far field","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1364/oe.612531","doi":"https://doi.org/10.1364/oe.612531","is_oa":true,"landing_page_url":"https://doi.org/10.1364/oe.612531","pdf_url":null,"source":{"id":"https://openalex.org/S178776955","display_name":"Optics Express","issn_l":"1094-4087","issn":["1094-4087"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-b","jufo-1","ki-jl-1","medline","norway-2","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315679","host_organization_name":"Optica Publishing Group","host_organization_lineage":["https://openalex.org/P4310315679"],"host_organization_lineage_names":["Optica Publishing Group"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Optics Express","raw_type":"journal-article"},{"id":"pmid:42972829","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42972829","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Optics express","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1364/oe.612531","doi":"https://doi.org/10.1364/oe.612531","is_oa":true,"landing_page_url":"https://doi.org/10.1364/oe.612531","pdf_url":null,"source":{"id":"https://openalex.org/S178776955","display_name":"Optics Express","issn_l":"1094-4087","issn":["1094-4087"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-b","jufo-1","ki-jl-1","medline","norway-2","oarl","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315679","host_organization_name":"Optica Publishing Group","host_organization_lineage":["https://openalex.org/P4310315679"],"host_organization_lineage_names":["Optica Publishing Group"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Optics Express","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321536","display_name":"China Academy of Engineering Physics","ror":"https://ror.org/039vqpp67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2003017040","https://openalex.org/W2044684119","https://openalex.org/W2133865602","https://openalex.org/W2194775991","https://openalex.org/W2266290075","https://openalex.org/W2586727320","https://openalex.org/W2613358869","https://openalex.org/W2899663614","https://openalex.org/W2910298034","https://openalex.org/W2979786244","https://openalex.org/W2998004632","https://openalex.org/W3008967825","https://openalex.org/W3010501116","https://openalex.org/W3028129150","https://openalex.org/W3035649237","https://openalex.org/W3037932933","https://openalex.org/W3045503779","https://openalex.org/W3092323705","https://openalex.org/W3109834426","https://openalex.org/W3129005144","https://openalex.org/W3181040444","https://openalex.org/W4292664320","https://openalex.org/W4320718470","https://openalex.org/W4399601245","https://openalex.org/W4400028688","https://openalex.org/W4403693397","https://openalex.org/W4410737363","https://openalex.org/W7117313143"],"related_works":["https://openalex.org/W7202243386","https://openalex.org/W7158035789","https://openalex.org/W7074548023","https://openalex.org/W7202288755","https://openalex.org/W2286971197","https://openalex.org/W940057790","https://openalex.org/W3044864599","https://openalex.org/W3146647792","https://openalex.org/W2186528300","https://openalex.org/W3128865289"],"abstract_inverted_index":{"Neural-network":[0],"prediction":[1,278],"of":[2,13,65,120,137,146,154,225,232,240,276,292],"electromagnetic":[3],"fields":[4],"in":[5,152,187,279],"heterogeneous":[6,280],"media":[7,281],"can":[8],"reduce":[9],"the":[10,18,66,80,86,108,113,175,197,207,248,273,289],"computational":[11],"cost":[12],"repeated":[14],"numerical":[15],"simulations.":[16],"However,":[17],"commonly":[19],"used":[20,237],"U-shaped":[21],"convolutional":[22],"neural":[23,53,96],"network":[24,97],"(U-Net)":[25],"has":[26],"difficulty":[27],"reconciling":[28],"fixed":[29],"local":[30,99],"convolutions":[31],"with":[32,181,228],"full-field":[33,58,135],"propagation,":[34,294],"abrupt":[35],"material-interface":[36,61],"changes,":[37],"and":[38,40,63,92,102,128,148,167,177,206,236,262,287,297,302],"reflected":[39],"transmitted":[41],"responses.":[42],"To":[43],"address":[44],"this":[45],"issue,":[46],"we":[47],"develop":[48],"a":[49,71,116,134,143,222,229,283],"green-preconditioned":[50],"dynamic":[51,94],"graph":[52,95],"operator":[54],"(GP-DGNO)":[55],"that":[56,270],"integrates":[57],"scattering-baseline":[59],"prediction,":[60],"correction,":[62,296],"propagation":[64],"corrected":[67],"interface":[68,100,295],"response":[69],"within":[70],"single":[72],"end-to-end":[73],"model.":[74],"A":[75,90],"bilateral":[76],"spectral":[77,293],"green-FNO":[78],"learns":[79],"global":[81],"scattering":[82,202],"residual":[83],"relative":[84],"to":[85,110],"paired":[87,182],"incident":[88],"field.":[89],"material-":[91],"geometry-conditioned":[93],"corrects":[98],"responses,":[101],"an":[103],"explicit":[104,298],"green-propagation":[105],"head":[106],"transfers":[107],"correction":[109],"regions":[111],"outside":[112],"interface.":[114],"On":[115],"locked":[117],"test":[118,285],"set":[119],"336":[121,155],"cases":[122],"comprising":[123],"48":[124],"unseen":[125],"geometry":[126],"families":[127],"seven":[129],"physical":[130],"conditions,":[131,158,180],"GP-DGNO":[132,159,261,271],"achieved":[133],"NRMSE":[136],"0.1982":[138],"versus":[139,204,211,244],"0.2098":[140],"for":[141,234,260,265],"U-Net,":[142,235],"mean":[144,223,230],"reduction":[145],"5.54%,":[147],"produced":[149],"lower":[150,161,172],"error":[151,162,173,195],"214":[153],"cases.":[156],"Across":[157],"had":[160,171,193],"under":[163,174,200,282],"weak-scattering,":[164],"ID,":[165],"low-frequency,":[166],"high-frequency":[168],"conditions.":[169,189,304],"U-Net":[170],"MHz":[176],"combined":[178,208],"frequency-material":[179],"confidence":[183],"intervals":[184],"excluding":[185],"zero":[186],"both":[188],"The":[190,213],"full":[191,214],"model":[192,215],"higher":[194],"than":[196],"incident-field":[198],"prior":[199],"weak":[201],"(0.0462":[203],"0.0284)":[205],"condition":[209],"(0.5069":[210],"0.5002).":[212],"reached":[216],"its":[217],"best":[218],"validation":[219],"result":[220],"at":[221],"epoch":[224,231],"117.0,":[226],"compared":[227],"164.7":[233],"375.1":[238],"MiB":[239],"peak":[241],"training":[242],"memory":[243],"696.8":[245],"MiB.":[246],"Under":[247],"unified":[249,284],"GPU-resident":[250],"steady-state":[251],"timing":[252],"protocol,":[253],"inference":[254],"took":[255],"12.28":[256],"ms":[257,264],"per":[258],"case":[259],"7.18":[263],"U-Net.":[266],"These":[267],"results":[268],"show":[269],"improves":[272],"overall":[274],"accuracy":[275],"electromagnetic-field":[277],"protocol":[286],"clarify":[288],"operating":[290],"limits":[291],"re-propagation":[299],"across":[300],"frequency":[301],"material":[303]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-23T00:00:00"}