{"id":"https://openalex.org/W7204535352","doi":"https://doi.org/10.31223/x5qv3p","title":"Systematic Evaluation of a Transformer-Based Surrogate for Distributed Groundwater Dynamics: Long-Horizon Prediction, Dynamic\u2013Static Fusion, and Data Augmentation","display_name":"Systematic Evaluation of a Transformer-Based Surrogate for Distributed Groundwater Dynamics: Long-Horizon Prediction, Dynamic\u2013Static Fusion, and Data Augmentation","publication_year":2026,"publication_date":"2026-09-05","ids":{"openalex":"https://openalex.org/W7204535352","doi":"https://doi.org/10.31223/x5qv3p"},"language":"en","primary_location":{"id":"doi:10.31223/x5qv3p","doi":"https://doi.org/10.31223/x5qv3p","is_oa":true,"landing_page_url":"https://doi.org/10.31223/x5qv3p","pdf_url":"https://eartharxiv.org/repository/object/14828/download/25777/","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eartharxiv.org/repository/object/14828/download/25777/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148519112","display_name":"hui huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Huang","raw_affiliation_strings":["School of Atmospheric Sciences , Sun Yat-sen University , Zhuhai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Atmospheric Sciences , Sun Yat-sen University , Zhuhai , China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125025320","display_name":"Aoqi Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aoqi Sun","raw_affiliation_strings":["School of Atmospheric Sciences , Sun Yat-sen University , Zhuhai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Atmospheric Sciences , Sun Yat-sen University , Zhuhai , China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150383542","display_name":"Hoang Tran","orcid":"https://orcid.org/0009-0000-0302-1841","observed_orcids":["https://orcid.org/0009-0000-0302-1841"]},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hoang Tran","raw_affiliation_strings":["Atmospheric Science & Global Change Division , Pacific Northwest National Laboratory , Richland , WA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Atmospheric Science & Global Change Division , Pacific Northwest National Laboratory , Richland , WA , USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014994279","display_name":"YONGJIU DAI","orcid":"https://orcid.org/0000-0002-3588-6644","observed_orcids":["https://orcid.org/0000-0002-3588-6644"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjiu Dai","raw_affiliation_strings":["School of Atmospheric Sciences , Sun Yat-sen University , Zhuhai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Atmospheric Sciences , Sun Yat-sen University , Zhuhai , China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5150399813","display_name":"Chen Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Yang","raw_affiliation_strings":["School of Atmospheric Sciences , Sun Yat-sen University , Zhuhai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Atmospheric Sciences , Sun Yat-sen University , Zhuhai , China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11490","display_name":"Hydrological Forecasting Using AI","score":0.9369999766349792,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11490","display_name":"Hydrological Forecasting Using AI","score":0.9369999766349792,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.02930000051856041,"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/T10894","display_name":"Groundwater flow and contamination studies","score":0.017500000074505806,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/long-horizon-prediction","display_name":"long-horizon prediction","score":0.7200000286102295},{"id":"https://openalex.org/keywords/water-table-depth","display_name":"water table depth","score":0.7329999804496765},{"id":"https://openalex.org/keywords/parflow-clm","display_name":"ParFlow-CLM","score":0.753000020980835},{"id":"https://openalex.org/keywords/precipitation-forcing","display_name":"precipitation forcing","score":0.367000013589859},{"id":"https://openalex.org/keywords/cross-attention","display_name":"cross-attention","score":0.8730000257492065},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.8289999961853027},{"id":"https://openalex.org/keywords/precipitation-regime","display_name":"precipitation regime","score":0.4309999942779541},{"id":"https://openalex.org/keywords/spatiotemporal-dependencies","display_name":"spatiotemporal dependencies","score":0.6309999823570251},{"id":"https://openalex.org/keywords/hydrogeological-heterogeneity","display_name":"hydrogeological heterogeneity","score":0.6320000290870667}],"concepts":[{"id":"https://openalex.org/C76177295","wikidata":"https://www.wikidata.org/wiki/Q161598","display_name":"Groundwater","level":2,"score":0.7096999883651733},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.5636000037193298},{"id":"https://openalex.org/C76886044","wikidata":"https://www.wikidata.org/wiki/Q2883300","display_name":"Hydrology (agriculture)","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C524765639","wikidata":"https://www.wikidata.org/wiki/Q1501619","display_name":"Water resource management","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.30709999799728394},{"id":"https://openalex.org/C153823671","wikidata":"https://www.wikidata.org/wiki/Q1049799","display_name":"Water resources","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C8625798","wikidata":"https://www.wikidata.org/wiki/Q752112","display_name":"Surface water","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C75622301","wikidata":"https://www.wikidata.org/wiki/Q208791","display_name":"Aquifer","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C2993807900","wikidata":"https://www.wikidata.org/wiki/Q1049799","display_name":"Groundwater resources","level":4,"score":0.2676999866962433},{"id":"https://openalex.org/C176650113","wikidata":"https://www.wikidata.org/wiki/Q370689","display_name":"Groundwater model","level":5,"score":0.2660999894142151},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.25040000677108765},{"id":"https://openalex.org/C2778192778","wikidata":"https://www.wikidata.org/wiki/Q20113712","display_name":"Groundwater pollution","level":4,"score":0.25040000677108765}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.31223/x5qv3p","doi":"https://doi.org/10.31223/x5qv3p","is_oa":true,"landing_page_url":"https://doi.org/10.31223/x5qv3p","pdf_url":"https://eartharxiv.org/repository/object/14828/download/25777/","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:EA:id:14828","doi":null,"is_oa":true,"landing_page_url":"https://eartharxiv.org/repository/object/14828/download/25777/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402614","display_name":"EarthArXiv (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EarthArXiv","raw_type":"PREPRINTS"},{"id":"doi:10.5281/zenodo.22145194","doi":"https://doi.org/10.5281/zenodo.22145194","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22145194","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.31223/x5qv3p","doi":"https://doi.org/10.31223/x5qv3p","is_oa":true,"landing_page_url":"https://doi.org/10.31223/x5qv3p","pdf_url":"https://eartharxiv.org/repository/object/14828/download/25777/","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Clean water and sanitation","id":"https://metadata.un.org/sdg/6","score":0.7778000235557556},{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.46149998903274536}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204535352.pdf","grobid_xml":"https://content.openalex.org/works/W7204535352.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7162643014","https://openalex.org/W6891715003","https://openalex.org/W7165355304","https://openalex.org/W4362636249","https://openalex.org/W4415815763","https://openalex.org/W4281766922","https://openalex.org/W7135400639","https://openalex.org/W4412846748","https://openalex.org/W4220897176","https://openalex.org/W7222775696"],"abstract_inverted_index":{"Transformers":[0],"are":[1],"increasingly":[2],"reshaping":[3],"artificial-intelligence-based":[4],"Earth":[5,300],"system":[6,301],"prediction,":[7],"yet":[8],"their":[9,289],"suitability":[10],"for":[11,69,274,280],"distributed":[12],"groundwater":[13,48,249,260,278,297],"surrogate":[14,68],"modeling":[15],"remains":[16],"poorly":[17],"understood.":[18],"Groundwater":[19],"dynamics":[20,298],"combine":[21],"strong":[22],"temporal":[23,156],"persistence":[24],"with":[25,80,150,166,193],"spatial":[26,146],"interactions":[27],"governed":[28],"by":[29,119],"heterogeneous":[30],"hydrogeological":[31],"conditions.":[32],"These":[33,241],"characteristics":[34],"make":[35],"attention-based":[36],"architectures":[37],"potentially":[38],"well":[39],"suited":[40],"to":[41,56,112,292],"representing":[42],"the":[43,96,124,126,159,174,184,200,231,235,245],"long-range":[44],"spatiotemporal":[45],"dependencies":[46],"of":[47,98,186,247,296],"systems,":[49],"rather":[50],"than":[51],"merely":[52],"providing":[53],"an":[54],"alternative":[55,106],"recurrent":[57],"models.":[58,302],"Here,":[59],"we":[60],"systematically":[61,192],"evaluated":[62],"a":[63,67],"groundwater-adapted":[64],"PredFormer":[65,128,209],"as":[66],"regional":[70,281],"ParFlow-CLM":[71],"simulations.":[72],"The":[73,269],"adapted":[74,127],"model":[75],"combined":[76],"temporal-first":[77],"factorized":[78],"attention":[79],"pressure-residual":[81],"prediction":[82,91,181,282],"and":[83,103,114,153,176,188,216,257,266,283],"blockwise":[84],"autoregressive":[85,255],"rollout.":[86],"We":[87],"assessed":[88],"its":[89,109],"long-horizon":[90],"behavior":[92],"over":[93,253],"720":[94],"h,":[95],"contributions":[97],"prescribed":[99,171],"P\u2212ET":[100],"(PME)":[101],"forcing":[102],"static":[104,189],"attributes,":[105],"static-fusion":[107,201],"strategies,":[108],"performance":[110],"relative":[111],"PredRNN,":[113],"precipitation-regime-specific":[115],"data":[116],"augmentation":[117,221],"generated":[118],"perturbing":[120],"precipitation":[121,151,236],"forcing.":[122],"Over":[123],"horizon,":[125],"maintained":[129],"decimeter-scale":[130],"median":[131],"water":[132],"table":[133],"depth":[134],"(WTD)":[135],"errors,":[136],"although":[137,183],"error":[138,160],"magnitude":[139],"varied":[140,191],"among":[141,199],"WTD":[142],"regimes.":[143],"Larger":[144],"upper-tail":[145],"errors":[147],"were":[148,162],"associated":[149,165],"amount":[152],"variability,":[154],"whereas":[155],"fluctuations":[157],"in":[158,180,217],"trajectories":[161],"more":[163,205],"closely":[164],"abrupt":[167],"wet\u2013dry":[168],"transitions.":[169],"Adding":[170],"PME":[172],"produced":[173,222],"largest":[175],"most":[177,218],"consistent":[178],"reduction":[179],"error,":[182],"benefits":[185,229],"dynamic":[187],"inputs":[190],"WTD.":[194],"Post-temporal\u2013spatial":[195],"cross-attention":[196],"performed":[197,210],"best":[198],"strategies.":[202],"PredRNN":[203],"was":[204],"accurate":[206],"initially,":[207],"but":[208,226],"better":[211],"at":[212],"longer":[213],"lead":[214],"times":[215],"segments.":[219],"Data":[220],"modest":[223],"overall":[224],"changes":[225],"clear":[227],"regime-dependent":[228],"when":[230],"added":[232],"samples":[233],"matched":[234],"conditions":[237],"encountered":[238],"during":[239],"prediction.":[240],"findings":[242],"show":[243],"that":[244],"advantages":[246],"Transformer-based":[248],"surrogates":[250,279],"emerge":[251],"primarily":[252],"extended":[254],"horizons":[256],"depend":[258],"on":[259],"state,":[261],"input":[262],"composition,":[263],"information-fusion":[264],"strategy,":[265],"training-sample":[267],"coverage.":[268],"results":[270],"provide":[271,293],"process-informed":[272],"guidance":[273],"developing":[275],"computationally":[276],"efficient":[277],"water-resources":[284],"management,":[285],"while":[286],"also":[287],"highlighting":[288],"longer-term":[290],"potential":[291],"AI-enabled":[294],"representations":[295],"within":[299]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-29T00:00:00"}