{"id":"https://openalex.org/W3194073685","doi":"https://doi.org/10.1145/3469096.3474929","title":"Rescuing historical climate observations to support hydrological research","display_name":"Rescuing historical climate observations to support hydrological research","publication_year":2021,"publication_date":"2021-08-16","ids":{"openalex":"https://openalex.org/W3194073685","doi":"https://doi.org/10.1145/3469096.3474929","mag":"3194073685"},"language":"en","primary_location":{"id":"doi:10.1145/3469096.3474929","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469096.3474929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM Symposium on Document Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084090570","display_name":"Ogundepo Odunayo","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Ogundepo Odunayo","raw_affiliation_strings":["University of Waterloo, Ontario, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Ontario, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036174984","display_name":"Naveela N. Sookoo","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Naveela N. Sookoo","raw_affiliation_strings":["University of Waterloo, Ontario, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Ontario, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028774371","display_name":"Gautam Bathla","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gautam Bathla","raw_affiliation_strings":["University of Waterloo, Ontario, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Ontario, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077016822","display_name":"Anthony Cavallin","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Anthony Cavallin","raw_affiliation_strings":["University of Waterloo, Ontario, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Ontario, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042302774","display_name":"Bhaleka Persaud","orcid":"https://orcid.org/0000-0003-2785-3954"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bhaleka D. Persaud","raw_affiliation_strings":["University of Waterloo, Ontario, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Ontario, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000063079","display_name":"Kathy Szigeti","orcid":"https://orcid.org/0000-0003-1790-9790"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kathy Szigeti","raw_affiliation_strings":["University of Waterloo, Ontario, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Ontario, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037707164","display_name":"Philippe Van Cappellen","orcid":"https://orcid.org/0000-0001-5476-0820"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Philippe Van Cappellen","raw_affiliation_strings":["University of Waterloo, Ontario, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Ontario, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Waterloo, Ontario, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Ontario, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5084090570"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.09830778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9635000228881836,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9635000228881836,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14427","display_name":"Environmental Monitoring and Data Management","score":0.9606000185012817,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.9397000074386597,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8015397191047668},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7735093832015991},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.7701490521430969},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7648425698280334},{"id":"https://openalex.org/keywords/hydrometeorology","display_name":"Hydrometeorology","score":0.5769346952438354},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5701221227645874},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.485139936208725},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4738072454929352},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36377114057540894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3395264744758606},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25930657982826233},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13517886400222778},{"id":"https://openalex.org/keywords/precipitation","display_name":"Precipitation","score":0.12158006429672241},{"id":"https://openalex.org/keywords/meteorology","display_name":"Meteorology","score":0.1124584972858429},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10390156507492065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015397191047668},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7735093832015991},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.7701490521430969},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7648425698280334},{"id":"https://openalex.org/C100725284","wikidata":"https://www.wikidata.org/wiki/Q1045317","display_name":"Hydrometeorology","level":3,"score":0.5769346952438354},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5701221227645874},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.485139936208725},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4738072454929352},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36377114057540894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3395264744758606},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25930657982826233},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13517886400222778},{"id":"https://openalex.org/C107054158","wikidata":"https://www.wikidata.org/wiki/Q25257","display_name":"Precipitation","level":2,"score":0.12158006429672241},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.1124584972858429},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10390156507492065},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3469096.3474929","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3469096.3474929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM Symposium on Document Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/17344","is_oa":false,"landing_page_url":"http://hdl.handle.net/10012/17344","pdf_url":null,"source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Preprint"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.8199999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326644","display_name":"Canada First Research Excellence Fund","ror":null},{"id":"https://openalex.org/F4320336032","display_name":"Global Water Futures","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2001642682","https://openalex.org/W2772955562","https://openalex.org/W2899266989","https://openalex.org/W2969825080","https://openalex.org/W2996791521","https://openalex.org/W3020116341","https://openalex.org/W3148809405","https://openalex.org/W3210232381","https://openalex.org/W6639102338"],"related_works":["https://openalex.org/W2131938703","https://openalex.org/W1968333292","https://openalex.org/W3006264628","https://openalex.org/W2898980309","https://openalex.org/W3107931054","https://openalex.org/W3198741782","https://openalex.org/W2908205146","https://openalex.org/W4210985622","https://openalex.org/W4376611844","https://openalex.org/W4402532657"],"abstract_inverted_index":{"The":[0,82,172],"acceleration":[1],"of":[2,63,85,113,161,230,235,243],"climate":[3,14,34,95,170,237],"change":[4],"and":[5,142,150,166,181,194,209,221,228,246,273,279],"its":[6],"impact":[7],"highlight":[8],"the":[9,31,43,46,60,73,111,154,169,186,206,241,262],"need":[10],"for":[11,126,147,201,281],"long-term":[12],"reliable":[13],"data":[15,50,74,149],"at":[16],"high":[17],"spatiotemporal":[18],"resolution":[19],"to":[20,30,45,89,92,101,178,182,191,224],"answer":[21],"key":[22],"science":[23],"questions":[24],"in":[25,57,105,153],"cold":[26,106],"regions":[27],"hydrology.":[28],"Prior":[29],"digital":[32],"age,":[33],"records":[35,96],"were":[36,55],"archived":[37],"on":[38,211,249,261],"paper.":[39],"For":[40],"example,":[41],"from":[42,51,233],"1950s":[44],"1990s,":[47],"solar":[48],"radiation":[49],"recording":[52],"stations":[53],"worldwide":[54],"published":[56],"booklets":[58],"by":[59,79],"former":[61],"Union":[62],"Soviet":[64],"Socialist":[65],"Republics":[66],"(USSR)":[67],"Hydrometeorological":[68],"Service.":[69],"As":[70],"a":[71,98,114,132],"result,":[72],"are":[75],"not":[76],"easily":[77],"accessible":[78],"most":[80],"researchers.":[81],"overarching":[83],"aim":[84],"this":[86],"research":[87,104],"is":[88,189,271,277],"develop":[90],"techniques":[91,223],"convert":[93],"paper-based":[94],"into":[97],"machine-readable":[99],"format":[100],"support":[102],"environmental":[103],"regions.":[107],"This":[108],"study":[109],"compares":[110],"performance":[112,242],"proprietary":[115],"optical":[116],"character":[117],"recognition":[118],"(OCR)":[119],"service":[120],"with":[121,163,175],"an":[122,143,198],"open-source":[123,144],"OCR":[124,145,199,222,245],"tool":[125],"digitizing":[127],"hydrometeorological":[128],"data.":[129,171],"We":[130,204,239,252],"built":[131],"digitization":[133,207],"pipeline":[134,268],"combining":[135],"different":[136,215],"image":[137,176,219],"preprocessing":[138,177,218],"techniques,":[139],"semantic":[140],"segmentation,":[141],"engine":[146,200],"extracting":[148],"metadata":[151,232],"recorded":[152],"scanned":[155,236],"documents.":[156],"Each":[157],"page":[158,187],"contains":[159],"blocks":[160],"text":[162,202,250],"station":[164],"names":[165],"tables":[167,193],"containing":[168],"process":[173,208],"begins":[174],"reduce":[179],"noise":[180],"improve":[183],"quality":[184],"before":[185],"content":[188],"segmented":[190],"detect":[192],"finally":[195],"run":[196],"through":[197],"extraction.":[203,251],"outline":[205],"report":[210],"initial":[212],"results,":[213],"including":[214],"segmentation":[216],"approaches,":[217],"algorithms,":[220],"ensure":[225],"accurate":[226],"extraction":[227,267],"organization":[229],"relevant":[231],"thousands":[234],"records.":[238],"evaluated":[240],"Tesseract":[244,270],"ABBYY":[247],"FineReader":[248,257],"find":[253],"that":[254],"although":[255],"ABBY":[256],"has":[258],"better":[259],"accuracy":[260],"sample":[263],"data,":[264],"our":[265],"custom":[266],"using":[269],"efficient":[272],"scalable":[274],"because":[275],"it":[276],"flexible":[278],"allows":[280],"more":[282],"customization.":[283]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-08-30T00:00:00"}