{"id":"https://openalex.org/W4406459085","doi":"https://doi.org/10.1109/bigdata62323.2024.10825214","title":"Natural Language Processing for Extracting Rich Disease Data Aligned To Satellite Meteorological Data","display_name":"Natural Language Processing for Extracting Rich Disease Data Aligned To Satellite Meteorological Data","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406459085","doi":"https://doi.org/10.1109/bigdata62323.2024.10825214"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5115904625","display_name":"Mahi Pasarkar","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mahi Pasarkar","raw_affiliation_strings":["Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011517497","display_name":"Junseob Kim","orcid":"https://orcid.org/0000-0002-6959-5271"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junseob Kim","raw_affiliation_strings":["Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115904626","display_name":"Eoin O\u2019Gara","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eoin O\u2019Gara","raw_affiliation_strings":["Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101511637","display_name":"Alan Zhang","orcid":"https://orcid.org/0000-0003-4025-1720"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Zhang","raw_affiliation_strings":["Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051863472","display_name":"Malik Magdon\u2010Ismail","orcid":"https://orcid.org/0000-0001-7327-7770"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Malik Magdon-Ismail","raw_affiliation_strings":["Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055253153","display_name":"Thilanka Munasinghe","orcid":"https://orcid.org/0000-0002-0911-750X"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thilanka Munasinghe","raw_affiliation_strings":["Rensselaer Polytechnic Institute,Troy,NY,USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute,Troy,NY,USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108318734","display_name":"Jiaqi Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Weng","raw_affiliation_strings":["Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079902855","display_name":"David Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Qiu","raw_affiliation_strings":["Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044601656","display_name":"Ethan Cruz","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ethan Cruz","raw_affiliation_strings":["Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute,School of Science,Troy,NY,USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064582405","display_name":"Jennifer Wei","orcid":"https://orcid.org/0000-0002-1539-2137"},"institutions":[{"id":"https://openalex.org/I4210124779","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80","country_code":"US","type":"funder","lineage":["https://openalex.org/I4210124779"]},{"id":"https://openalex.org/I1306266525","display_name":"Goddard Space Flight Center","ror":"https://ror.org/0171mag52","country_code":"US","type":"facility","lineage":["https://openalex.org/I1306266525","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jennifer C. Wei","raw_affiliation_strings":["National Aeronautics and Space Administration,Goddard Space Flight Center,Greenbelt,MD,USA"],"affiliations":[{"raw_affiliation_string":"National Aeronautics and Space Administration,Goddard Space Flight Center,Greenbelt,MD,USA","institution_ids":["https://openalex.org/I1306266525","https://openalex.org/I4210124779"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110601434","display_name":"Ashan Pathirana","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156914","display_name":"Ministry of Health, Nutrition and Indigenous Medicine","ror":"https://ror.org/054pkye94","country_code":"LK","type":"government","lineage":["https://openalex.org/I4210156914"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Ashan Pathirana","raw_affiliation_strings":["Ministry of Health,Health Promotion Bureau,Colombo,Sri Lanka"],"affiliations":[{"raw_affiliation_string":"Ministry of Health,Health Promotion Bureau,Colombo,Sri Lanka","institution_ids":["https://openalex.org/I4210156914"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5115904625"],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":0.8111,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82944054,"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":"4394","last_page":"4401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14042","display_name":"Technology and Security Systems","score":0.8799999952316284,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14042","display_name":"Technology and Security Systems","score":0.8799999952316284,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8769000172615051,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10616","display_name":"Smart Agriculture and AI","score":0.852400004863739,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7143977284431458},{"id":"https://openalex.org/keywords/satellite","display_name":"Satellite","score":0.615566611289978},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.43959909677505493},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4317346215248108},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.42516815662384033},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3968766927719116},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.35562801361083984},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.14635774493217468},{"id":"https://openalex.org/keywords/astronomy","display_name":"Astronomy","score":0.08760768175125122}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7143977284431458},{"id":"https://openalex.org/C19269812","wikidata":"https://www.wikidata.org/wiki/Q26540","display_name":"Satellite","level":2,"score":0.615566611289978},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43959909677505493},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4317346215248108},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.42516815662384033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3968766927719116},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.35562801361083984},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.14635774493217468},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.08760768175125122},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1598140581","https://openalex.org/W1987822482","https://openalex.org/W1991383860","https://openalex.org/W2032756564","https://openalex.org/W2057353349","https://openalex.org/W2137998699","https://openalex.org/W2149527488","https://openalex.org/W2184543991","https://openalex.org/W2618743573","https://openalex.org/W2889497954","https://openalex.org/W2963419157","https://openalex.org/W2966351171","https://openalex.org/W2999368109","https://openalex.org/W3079483106","https://openalex.org/W3102251128","https://openalex.org/W4323076031","https://openalex.org/W4392002118","https://openalex.org/W6630199436","https://openalex.org/W6686456631","https://openalex.org/W6713534179"],"related_works":["https://openalex.org/W2121524756","https://openalex.org/W782553550","https://openalex.org/W1987967678","https://openalex.org/W4283262748","https://openalex.org/W2013329914","https://openalex.org/W2392383081","https://openalex.org/W1618102658","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"Global":[0],"climate":[1],"change":[2],"is":[3,67,90,112],"redefining":[4],"our":[5,71,163],"understanding":[6],"of":[7,87],"how":[8],"diseases":[9,15,75],"spread.":[10],"In":[11,81],"Sri":[12,199],"Lanka,":[13],"vector-borne":[14],"such":[16,101],"as":[17,102],"dengue":[18],"fever":[19],"historically":[20],"surged":[21],"during":[22],"the":[23,82,217],"monsoon":[24],"seasons":[25],"when":[26],"temperatures":[27,40],"were":[28],"high":[29],"enough":[30],"for":[31,114,124,173,198,203,216,225],"mosquito":[32,46],"eggs":[33,47],"to":[34,38,57,69,73,97,140,149,161,194],"hatch.":[35],"Unfortunately,":[36],"due":[37,96],"rising":[39],"and":[41,63,129,157,177,201,207],"more":[42,185],"erratic":[43],"rainfall":[44],"patterns,":[45],"can":[48,145,169],"now":[49],"hatch":[50],"year-round":[51],"making":[52],"outbreaks":[53],"increasingly":[54,78],"unpredictable,":[55],"leading":[56],"an":[58,77],"alarming":[59],"rise":[60],"in":[61,76,188],"hospitalizations":[62],"deaths.":[64],"More":[65],"data":[66,99,142,168,197,210],"needed":[68],"adapt":[70],"response":[72],"these":[74,209],"warmer":[79],"world.":[80],"contemporary":[83],"landscape,":[84],"a":[85,121,220],"wealth":[86],"disease":[88,107,127,226],"information":[89],"available,":[91],"yet":[92],"accessibility":[93,156],"remains":[94],"limited":[95],"unstructured":[98,106,126],"formats":[100,111],"PDFs.":[103],"Therefore,":[104],"converting":[105],"reports":[108,128],"into":[109,132],"structured":[110,167],"necessary":[113],"effectively":[115],"leveraging":[116],"data.":[117],"This":[118],"paper":[119],"introduces":[120],"comprehensive":[122],"framework":[123,193],"collecting":[125],"transforming":[130],"them":[131],"analyzable":[133],"formats.":[134],"By":[135],"creating":[136],"separate":[137],"models":[138,154],"tailored":[139],"each":[141],"format,":[143],"we":[144],"ensure":[146],"accuracy":[147],"compared":[148],"general":[150],"models.":[151],"These":[152],"straightforward":[153],"enhance":[155],"empower":[158],"other":[159],"researchers":[160],"use":[162],"tools.":[164],"The":[165],"returned":[166],"then":[170],"be":[171],"harnessed":[172],"analysis,":[174],"statistical":[175],"purposes,":[176],"informing":[178],"evidence-based":[179],"public":[180],"health":[181],"interventions,":[182],"thus":[183],"facilitating":[184],"informed":[186],"decision-making":[187],"healthcare.":[189],"We":[190],"deploy":[191],"this":[192],"produce":[195],"geospatial":[196],"Lanka":[200],"Brazil":[202],"many":[204],"different":[205],"conditions":[206],"align":[208],"with":[211],"satellite":[212],"environmental":[213],"data,":[214],"providing":[215],"first":[218],"time":[219],"structured,":[221],"aligned":[222],"powerful":[223],"dataset":[224],"modeling.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}