{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T22:28:38Z","timestamp":1784759318983,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2126253, 2322308, 2331908"],"award-info":[{"award-number":["2126253, 2322308, 2331908"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3708035.3736017","type":"proceedings-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T12:10:41Z","timestamp":1752840641000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A Scalable Framework for Heterogeneous Environmental Data Management Using Smart Data Pipeline"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7469-922X","authenticated-orcid":false,"given":"Pratik","family":"Poudel","sequence":"first","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4244-5011","authenticated-orcid":false,"given":"Boyuan","family":"Guan","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3991-0856","authenticated-orcid":false,"given":"Nicole","family":"Sanchez","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9016-9894","authenticated-orcid":false,"given":"Kiavash","family":"Bahreini","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6579-3724","authenticated-orcid":false,"given":"Wencong","family":"Cui","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7628-3398","authenticated-orcid":false,"given":"Andres","family":"Lopez","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6528-8671","authenticated-orcid":false,"given":"Hamed","family":"Najafi","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5768-4760","authenticated-orcid":false,"given":"Zhaohui","family":"Fu","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2097-2432","authenticated-orcid":false,"given":"Leonardo","family":"Bobadilla","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8222-4013","authenticated-orcid":false,"given":"Jason","family":"Liu","sequence":"additional","affiliation":[{"name":"Florida International University, Miami, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,18]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Mohammad\u00a0Shahmeer Ahmad Zan\u00a0Ahmad Naeem Mohamed Eltabakh Mourad Ouzzani and Nan Tang. 2023. RetClean: Retrieval-based data cleaning using foundation models and data lakes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.16909 (2023)."},{"key":"e_1_3_3_1_3_2","unstructured":"Amazon Web Services. 2025. AWS CodeCommit. https:\/\/aws.amazon.com\/codecommit\/"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","unstructured":"Jim Basney Terry Fleury and Jim Gaynor. 2013. CILogon: A federated X.509 certification authority for cyberinfrastructure logon. XSEDE \u201913: Proceedings of the Conference on Extreme Science and Engineering Discovery Environment (2013). 10.1145\/2484762.2484791","DOI":"10.1145\/2484762.2484791"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Rebekka Benfer and Jochen M\u00fcller. 2024. Semantic digital twin creation of building systems through time series based metadata inference\u2013A review. Energy and Buildings (2024) 114637.","DOI":"10.1016\/j.enbuild.2024.114637"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Laura D\u00edaz Carlos Granell Michael Gould and Joaqu\u00edn Huerta. 2011. Managing user-generated information in geospatial cyberinfrastructures. Future Generation Computer Systems 27 3 (2011) 304\u2013314.","DOI":"10.1016\/j.future.2010.09.002"},{"key":"e_1_3_3_1_7_2","volume-title":"ArcGIS API for Python","author":"(ESRI) Environmental Systems Research Institute","year":"2025","unstructured":"Environmental Systems Research Institute (ESRI). 2025. ArcGIS API for Python. https:\/\/developers.arcgis.com\/python\/latest\/"},{"key":"e_1_3_3_1_8_2","unstructured":"Environmental Systems Research Institute (ESRI). 2025. ArcGIS Online. https:\/\/www.esri.com\/en-us\/arcgis\/products\/arcgis-online"},{"key":"e_1_3_3_1_9_2","unstructured":"Environmental Systems Research Institute (ESRI). 2025. ArcGIS Pro. https:\/\/www.esri.com\/en-us\/arcgis\/products\/arcgis-pro\/overview"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"V. Eyring S. Bony G.\u00a0A. Meehl C.\u00a0A. Senior B. Stevens R.\u00a0J. Stouffer and K.\u00a0E. Taylor. 2016. Overview of the Coupled Model Intercomparison Project Phase 6 (CMIP6) experimental design and organization. Geoscientific Model Development 9 5 (2016) 1937\u20131958. 10.5194\/gmd-9-1937-2016","DOI":"10.5194\/gmd-9-1937-2016"},{"key":"e_1_3_3_1_11_2","unstructured":"Florida International University. 2025. FIU Dataverse. https:\/\/dataverse.fiu.edu\/"},{"key":"e_1_3_3_1_12_2","unstructured":"Florida International University. 2025. Raptor-Reconfigurable Advanced Platform for Transdisciplinary Open Research. https:\/\/raptor.fiu.edu."},{"key":"e_1_3_3_1_13_2","unstructured":"University of\u00a0Florida GeoPlan\u00a0Center. 2022. Florida Geographic Data Library (FGDL). https:\/\/fgdl.org."},{"key":"e_1_3_3_1_14_2","unstructured":"Harvard University. 2025. Harvard Dataverse. https:\/\/dataverse.harvard.edu\/"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Jeffery\u00a0S Horsburgh David\u00a0G Tarboton Michael Piasecki David\u00a0R Maidment Ilya Zaslavsky David Valentine and Thomas Whitenack. 2009. An integrated system for publishing environmental observations data. Environmental Modelling & Software 24 8 (2009) 879\u2013888.","DOI":"10.1016\/j.envsoft.2009.01.002"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Fei Hu Mengchao Xu Jingchao Yang Yanshou Liang Kejin Cui Michael\u00a0M Little Christopher\u00a0S Lynnes Daniel\u00a0Q Duffy and Chaowei Yang. 2018. Evaluating the open source data containers for handling big geospatial raster data. ISPRS International Journal of Geo-Information 7 4 (2018) 144.","DOI":"10.3390\/ijgi7040144"},{"key":"e_1_3_3_1_17_2","volume-title":"Global Spatial Data Infrastructures 12 World Conference: Realising Spatially Enabled Societies","author":"Kalantari Mohsen","year":"2010","unstructured":"Mohsen Kalantari, Hamed Olfat, and Abbas Rajabifard. 2010. Automatic spatial metadata enrichment: reducing metadata creation burden through spatial folksonomies. In Global Spatial Data Infrastructures 12 World Conference: Realising Spatially Enabled Societies. Citeseer."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3355738.3355750"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Gary King. 2007. An introduction to the dataverse network as an infrastructure for data sharing. Sociological Methods & Research 36 2 (2007) 173\u2013199.","DOI":"10.1177\/0049124107306660"},{"key":"e_1_3_3_1_20_2","unstructured":"LangChain Contributors. 2023. LangChain. https:\/\/github.com\/hwchase17\/langchain."},{"key":"e_1_3_3_1_21_2","volume-title":"aws.s3: AWS S3 Client Package","author":"Leeper Thomas\u00a0J.","year":"2020","unstructured":"Thomas\u00a0J. Leeper. 2020. aws.s3: AWS S3 Client Package. R package version 0.3.21."},{"key":"e_1_3_3_1_22_2","unstructured":"Lan Li Liri Fang and Vetle\u00a0I Torvik. 2024. AutoDCWorkflow: LLM-based data cleaning workflow auto-generation and benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.06724 (2024)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","unstructured":"Bertram Ludascher Ilkay Altintas Chad Berkley Daniel Higgins Efrat Jaeger Matthew\u00a0B. Jones Edward\u00a0A. Lee Jing Tao and Yang Zhao. 2006. Scientific workflow management and the Kepler system. Concurrency and Computation: Practice and Experience 18 10 (2006) 1039\u20131065. 10.1002\/cpe.994","DOI":"10.1002\/cpe.994"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"D-Lib Magazine. 2011. The dataverse network: an open-source application for sharing discovering and preserving data. D-lib Magazine 17 1\/2 (2011).","DOI":"10.1045\/january2011-crosas"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Gerald\u00a0A Meehl Richard Moss Karl\u00a0E Taylor Veronika Eyring Ronald\u00a0J Stouffer Sandrine Bony and Bjorn Stevens. 2014. Climate model intercomparisons: Preparing for the next phase. Eos Transactions American Geophysical Union 95 9 (2014) 77\u201378.","DOI":"10.1002\/2014EO090001"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Mike Mesnier Gregory\u00a0R Ganger and Erik Riedel. 2003. Object-based storage. IEEE Communications Magazine 41 8 (2003) 84\u201390.","DOI":"10.1109\/MCOM.2003.1222722"},{"key":"e_1_3_3_1_27_2","unstructured":"Morgridge Institute for Research. 2025. Pelican Platform. https:\/\/pelicanplatform.org\/"},{"key":"e_1_3_3_1_28_2","unstructured":"R Naveenkumar Shantanu Bhadra L Haldurai S Visalakshi and Nitin Kumar. 2024. Environmental Artificial Intelligence paving the way for a greener and more resilient planet using machine learning. Journal of Computational Analysis and Applications 33 7 (2024)."},{"key":"e_1_3_3_1_29_2","unstructured":"NVIDIA Omniverse Development Team. 2025. NVIDIA Omniverse. https:\/\/www.nvidia.com\/en-us\/omniverse\/"},{"key":"e_1_3_3_1_30_2","unstructured":"OASIS. 2005. SAML 2.0. https:\/\/www.oasis-open.org\/committees\/tc_home.php?wg_abbrev=security."},{"key":"e_1_3_3_1_31_2","unstructured":"University of South Florida Water\u00a0Institute. 2025. Water Atlas. https:\/\/wateratlas.usf.edu."},{"key":"e_1_3_3_1_32_2","unstructured":"OpenAI. 2023. OpenAI API. https:\/\/openai.com\/api\/."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","unstructured":"OSG. 2006. OSPool. 10.21231\/906P-4D78","DOI":"10.21231\/906P-4D78"},{"key":"e_1_3_3_1_34_2","unstructured":"Project Jupyter. 2023. JupyterHub. https:\/\/jupyterhub.readthedocs.io\/en\/stable\/."},{"key":"e_1_3_3_1_35_2","unstructured":"Theodoros Rekatsinas Xu Chu Ihab\u00a0F Ilyas and Christopher R\u00e9. 2017. Holoclean: Holistic data repairs with probabilistic inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1702.00820 (2017)."},{"key":"e_1_3_3_1_36_2","unstructured":"SchedMD. 2002. SLURM: Simple Linux Utility for Resource Management. https:\/\/slurm.schedmd.com. Accessed: 2025-02-02."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"John\u00a0L Schnase Daniel\u00a0Q Duffy Glenn\u00a0S Tamkin Denis Nadeau John\u00a0H Thompson Cristina\u00a0M Grieg Mark\u00a0A McInerney and William\u00a0P Webster. 2017. MERRA analytic services: Meeting the big data challenges of climate science through cloud-enabled climate analytics-as-a-service. Computers Environment and Urban Systems 61 (2017) 198\u2013211.","DOI":"10.1016\/j.compenvurbsys.2013.12.003"},{"key":"e_1_3_3_1_38_2","first-page":"17","volume-title":"Proceedings of the iRODS user group meeting 2011: Sustainable policy-based data management, sharing, and preservation","author":"Schnase John\u00a0L","year":"2011","unstructured":"John\u00a0L Schnase, Glenn Tamkin, David Fladung, Scott Sinno, and Roger Gill. 2011. Federated observational and simulation data in the NASA Center for Climate Simulation data management system project. In Proceedings of the iRODS user group meeting 2011: Sustainable policy-based data management, sharing, and preservation. 17\u201318."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI49370.2019.00245"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","unstructured":"Joan Starr Eleni Castro Merc Crosas Michel Dumontier Robert Downs Ruth Duerr Laurel Haak Melissa Haendel Ivan Herman Simon Hodson Joe Hourcl\u00e9 John Kratz Jennifer Lin Lars Nielsen Amy Nurnberger Stefan Pr\u00f6ll Andreas Rauber Simone Sacchi Arthur Smith and Tim Clark. 2015. Achieving human and machine accessibility of cited data in scholarly publications. PeerJ Computer Science 1 (05 2015). 10.7717\/peerj-cs.1","DOI":"10.7717\/peerj-cs.1"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3557915.3560953"},{"key":"e_1_3_3_1_42_2","unstructured":"Trino Software Foundation. 2025. Trino a query engine that runs at ludicrous speed. https:\/\/trino.io\/"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Kassidy Troxell Bradley Schonhoff Mark Kershaw Milena Ceccopieri Todd Crowl and Piero Gardinali. 2024. Near real-time monitoring of the Biscayne Bay Watershed (South Florida USA) and major tributaries by water quality research buoys. Science of The Total Environment 955 (2024) 177203.","DOI":"10.1016\/j.scitotenv.2024.177203"},{"key":"e_1_3_3_1_44_2","first-page":"307","volume-title":"Proceedings of the 7th Conference on Operating Systems Design and Implementation (OSDI\u201906)","author":"Weil Sage","year":"2006","unstructured":"Sage Weil, Scott\u00a0A Brandt, Ethan\u00a0L Miller, Darrell\u00a0DE Long, and Carlos Maltzahn. 2006. Ceph: A scalable, high-performance distributed file system. In Proceedings of the 7th Conference on Operating Systems Design and Implementation (OSDI\u201906). 307\u2013320."},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","unstructured":"Mark\u00a0D. Wilkinson Michel Dumontier IJsbrand\u00a0J. Aalbersberg Gabrielle Appleton Myles Axton Arie Baak Niklas Blomberg Jan-Willem Boiten Luiz\u00a0Bosco da Silva\u00a0Santos Philip\u00a0E. Bourne et\u00a0al. 2016. The FAIR Guiding Principles for scientific data management and stewardship. Scientific Data 3 (2016) 160018. 10.1038\/sdata.2016.18","DOI":"10.1038\/sdata.2016.18"},{"key":"e_1_3_3_1_46_2","unstructured":"Shuo Zhang Zezhou Huang and Eugene Wu. 2024. Data cleaning using large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.15547 (2024)."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-51819-5"}],"event":{"name":"PEARC '25: Practice and Experience in Advanced Research Computing","location":"Columbus Ohio USA","acronym":"PEARC '25","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Practice and Experience in Advanced Research Computing 2025: The Power of Collaboration"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708035.3736017","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708035.3736017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T12:31:14Z","timestamp":1752841874000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708035.3736017"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":46,"alternative-id":["10.1145\/3708035.3736017","10.1145\/3708035"],"URL":"https:\/\/doi.org\/10.1145\/3708035.3736017","relation":{},"subject":[],"published":{"date-parts":[[2025,7,18]]},"assertion":[{"value":"2025-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}