Academic Journal
Προβολή σε EDS

Wave-driven resuspension as the dominant environmental predictor of enterococci at Chicago beaches.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Wave-driven resuspension as the dominant environmental predictor of enterococci at Chicago beaches.
Συγγραφείς: Ferron L; Illinois Mathematics and Science Academy (IMSA), Aurora, IL, USA., Shrestha A; School of Public Health, University of Illinois Chicago (UIC), Chicago, IL, USA., Silva MR; AIHealth4All, College of Medicine, University of Illinois Chicago, Chicago, IL, USA. mqcft@umkc.edu.; Office of Research and Innovation, University of Missouri - Kansas City, Kansas City, MO, USA. mqcft@umkc.edu.
Πηγή: Environmental monitoring and assessment [Environ Monit Assess] 2026 Aug 27; Vol. 198 (9). Date of Electronic Publication: 2026 Aug 27.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Springer Country of Publication: Netherlands NLM ID: 8508350 Publication Model: Electronic Cited Medium: Internet ISSN: 1573-2959 (Electronic) Linking ISSN: 01676369 NLM ISO Abbreviation: Environ Monit Assess Subsets: MEDLINE
Imprint Name(s): Publication: 1998- : Dordrecht : Springer
Original Publication: Dordrecht, Holland ; Boston : D. Reidel Pub. Co., c1981-
Ιατρικοί όροι (MeSH): Bathing Beaches*/statistics & numerical data , Enterococcus*/growth & development , Enterococcus*/isolation & purification , Environmental Monitoring*/methods , Water Microbiology*, Chicago ; Random Forest ; Water Movements
Περίληψη: Predicting fecal indicator bacteria (FIB) to protect public health at Chicago beaches remains a significant challenge due to complex, site-specific environmental dynamics. This study presents a machine learning pipeline utilizing site-specific random forest regressor models to predict log-transformed enterococci concentrations. The models integrate meteorological, hydrodynamic, and temporal-lag features. A hybrid evaluation framework is implemented; models are trained for regression but evaluated on their ability to classify bacterial exceedances at a 320 CCE/100 mL threshold, chosen as a conservative value given data sparsity at the Chicago Park District's Beach Action Value of 1000 CCE/100 mL, which is used to issue swim advisories at these recreational beaches. This is achieved by dynamically identifying an optimal F1 score threshold for each model's raw count predictions, linking regression performance to classification utility. Model interpretability was a primary focus, employing SHAP (SHapley Additive exPlanations) for each beach and in aggregate. This analysis provided critical insights into the distinct drivers at each location. For the Chicago beaches, the models identified hydrodynamic factors, specifically maximum wave height and maximum dominant wave period, as the most significant hydrometeorological predictors of enterococci concentrations, highlighting the importance of nearshore physical processes in this region. The resulting pipeline provides an interpretable, validated, and site-specific forecasting system capable of identifying high-risk contamination events with moderate accuracy but struggling with sensitivity.
(© 2026. The Author(s).)
Competing Interests: Declarations. Competing interests: The authors have no relevant financial or non-financial interests to disclose. Ethical responsibilities of authors: All authors have read, understood, and have complied as applicable with the statement on “Ethical responsibilities of Authors” as found in the Instructions for Authors.
References: Environ Sci Technol. 2025 Oct 28;59(42):22386-22396. (PMID: 41091646)
Water Res. 2020 Sep 1;182:116014. (PMID: 32622131)
Appl Environ Microbiol. 2003 Sep;69(9):5555-62. (PMID: 12957945)
J Microbiol Methods. 2020 Jul;174:105947. (PMID: 32442655)
Lett Appl Microbiol. 1999 Mar;28(3):184-8. (PMID: 10196765)
Water Sci Technol. 2003;47(3):205-10. (PMID: 12639030)
Water Res X. 2018 Dec 27;2:100016. (PMID: 31194054)
Int J Epidemiol. 2010 Oct;39(5):1291-8. (PMID: 20522483)
J Water Health. 2003 Jun;1(2):85-9. (PMID: 15382737)
Environ Sci Technol. 2012 Feb 21;46(4):2204-11. (PMID: 22257076)
Epidemiology. 2012 Jan;23(1):95-106. (PMID: 22157306)
J Water Health. 2006 Sep;4(3):389-93. (PMID: 17036846)
Environ Sci Technol. 2023 Nov 21;57(46):17671-17689. (PMID: 37384597)
Environ Sci Technol. 2007 Dec 15;41(24):8227-32. (PMID: 18200844)
Environ Sci Technol. 2008 Dec 15;42(24):9217-24. (PMID: 19174895)
Water Res. 2011 Feb;45(4):1659-68. (PMID: 21195447)
J Environ Manage. 2016 Jan 15;166:285-93. (PMID: 26517277)
Mar Pollut Bull. 2014 Feb 15;79(1-2):114-22. (PMID: 24393380)
Environ Monit Assess. 2013 Mar;185(3):2355-66. (PMID: 22736208)
Contributed Indexing: Keywords: Beach monitoring; Fecal indicator bacteria; Hydrodynamics; Lake Michigan; Random forest; SHAP
Entry Date(s): Date Created: 20260827 Date Completed: 20260827 Latest Revision: 20260923
Update Code: 20260923
PubMed Central ID: PMC13522073
DOI: 10.1007/s10661-026-15791-3
PMID: 42658341
Βάση Δεδομένων: MEDLINE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://dx.doi.org/doi:10.1007/s10661-026-15791-3
    Name: EDS - Springer Nature Journals (s7799221)
    Category: fullText
    Text: View record at Springer
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=15732959&ISBN=&volume=198&issue=9&date=20260827&spage=&pages=&title=Environmental monitoring and assessment&atitle=Wave-driven%20resuspension%20as%20the%20dominant%20environmental%20predictor%20of%20enterococci%20at%20Chicago%20beaches.&aulast=Ferron%20L&id=DOI:10.1007/s10661-026-15791-3
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42658341
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Wave-driven resuspension as the dominant environmental predictor of enterococci at Chicago beaches.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Ferron+L%22">Ferron L</searchLink>; Illinois Mathematics and Science Academy (IMSA), Aurora, IL, USA.<br /><searchLink fieldCode="AU" term="%22Shrestha+A%22">Shrestha A</searchLink>; School of Public Health, University of Illinois Chicago (UIC), Chicago, IL, USA.<br /><searchLink fieldCode="AU" term="%22Silva+MR%22">Silva MR</searchLink>; AIHealth4All, College of Medicine, University of Illinois Chicago, Chicago, IL, USA. mqcft@umkc.edu.; Office of Research and Innovation, University of Missouri - Kansas City, Kansas City, MO, USA. mqcft@umkc.edu.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%228508350%22">Environmental monitoring and assessment</searchLink> [Environ Monit Assess] 2026 Aug 27; Vol. 198 (9). <i>Date of Electronic Publication: </i>2026 Aug 27.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Springer%22">Springer </searchLink><i>Country of Publication: </i>Netherlands <i>NLM ID: </i>8508350 <i>Publication Model: </i>Electronic <i>Cited Medium: </i>Internet <i>ISSN: </i>1573-2959 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2201676369%22">01676369 </searchLink><i>NLM ISO Abbreviation: </i>Environ Monit Assess <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Publication</i>: 1998- : Dordrecht : Springer<br /><i>Original Publication</i>: Dordrecht, Holland ; Boston : D. Reidel Pub. Co., c1981-
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Bathing+Beaches%22">Bathing Beaches*</searchLink>/<searchLink fieldCode="MM" term="%22Bathing+Beaches+statistics+%26+numerical+data%22">statistics & numerical data</searchLink> <br /><searchLink fieldCode="MM" term="%22Enterococcus%22">Enterococcus*</searchLink>/<searchLink fieldCode="MM" term="%22Enterococcus+growth+%26+development%22">growth & development</searchLink> <br /><searchLink fieldCode="MM" term="%22Enterococcus%22">Enterococcus*</searchLink>/<searchLink fieldCode="MM" term="%22Enterococcus+isolation+%26+purification%22">isolation & purification</searchLink> <br /><searchLink fieldCode="MM" term="%22Environmental+Monitoring%22">Environmental Monitoring*</searchLink>/<searchLink fieldCode="MM" term="%22Environmental+Monitoring+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Water+Microbiology%22">Water Microbiology*</searchLink><br /><searchLink fieldCode="MH" term="%22Chicago%22">Chicago</searchLink> ; <searchLink fieldCode="MH" term="%22Random+Forest%22">Random Forest</searchLink> ; <searchLink fieldCode="MH" term="%22Water+Movements%22">Water Movements</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Predicting fecal indicator bacteria (FIB) to protect public health at Chicago beaches remains a significant challenge due to complex, site-specific environmental dynamics. This study presents a machine learning pipeline utilizing site-specific random forest regressor models to predict log-transformed enterococci concentrations. The models integrate meteorological, hydrodynamic, and temporal-lag features. A hybrid evaluation framework is implemented; models are trained for regression but evaluated on their ability to classify bacterial exceedances at a 320 CCE/100 mL threshold, chosen as a conservative value given data sparsity at the Chicago Park District's Beach Action Value of 1000 CCE/100 mL, which is used to issue swim advisories at these recreational beaches. This is achieved by dynamically identifying an optimal F1 score threshold for each model's raw count predictions, linking regression performance to classification utility. Model interpretability was a primary focus, employing SHAP (SHapley Additive exPlanations) for each beach and in aggregate. This analysis provided critical insights into the distinct drivers at each location. For the Chicago beaches, the models identified hydrodynamic factors, specifically maximum wave height and maximum dominant wave period, as the most significant hydrometeorological predictors of enterococci concentrations, highlighting the importance of nearshore physical processes in this region. The resulting pipeline provides an interpretable, validated, and site-specific forecasting system capable of identifying high-risk contamination events with moderate accuracy but struggling with sensitivity.<br /> (© 2026. The Author(s).)
– Name: Abstract
  Label: Competing Interests
  Group: Ab
  Data: Declarations. Competing interests: The authors have no relevant financial or non-financial interests to disclose. Ethical responsibilities of authors: All authors have read, understood, and have complied as applicable with the statement on “Ethical responsibilities of Authors” as found in the Instructions for Authors.
– Name: Ref
  Label: References
  Group: RefInfo
  Data: Environ Sci Technol. 2025 Oct 28;59(42):22386-22396. (PMID: <searchLink fieldCode="PM" term="%2241091646%22">41091646)</searchLink><br />Water Res. 2020 Sep 1;182:116014. (PMID: <searchLink fieldCode="PM" term="%2232622131%22">32622131)</searchLink><br />Appl Environ Microbiol. 2003 Sep;69(9):5555-62. (PMID: <searchLink fieldCode="PM" term="%2212957945%22">12957945)</searchLink><br />J Microbiol Methods. 2020 Jul;174:105947. (PMID: <searchLink fieldCode="PM" term="%2232442655%22">32442655)</searchLink><br />Lett Appl Microbiol. 1999 Mar;28(3):184-8. (PMID: <searchLink fieldCode="PM" term="%2210196765%22">10196765)</searchLink><br />Water Sci Technol. 2003;47(3):205-10. (PMID: <searchLink fieldCode="PM" term="%2212639030%22">12639030)</searchLink><br />Water Res X. 2018 Dec 27;2:100016. (PMID: <searchLink fieldCode="PM" term="%2231194054%22">31194054)</searchLink><br />Int J Epidemiol. 2010 Oct;39(5):1291-8. (PMID: <searchLink fieldCode="PM" term="%2220522483%22">20522483)</searchLink><br />J Water Health. 2003 Jun;1(2):85-9. (PMID: <searchLink fieldCode="PM" term="%2215382737%22">15382737)</searchLink><br />Environ Sci Technol. 2012 Feb 21;46(4):2204-11. (PMID: <searchLink fieldCode="PM" term="%2222257076%22">22257076)</searchLink><br />Epidemiology. 2012 Jan;23(1):95-106. (PMID: <searchLink fieldCode="PM" term="%2222157306%22">22157306)</searchLink><br />J Water Health. 2006 Sep;4(3):389-93. (PMID: <searchLink fieldCode="PM" term="%2217036846%22">17036846)</searchLink><br />Environ Sci Technol. 2023 Nov 21;57(46):17671-17689. (PMID: <searchLink fieldCode="PM" term="%2237384597%22">37384597)</searchLink><br />Environ Sci Technol. 2007 Dec 15;41(24):8227-32. (PMID: <searchLink fieldCode="PM" term="%2218200844%22">18200844)</searchLink><br />Environ Sci Technol. 2008 Dec 15;42(24):9217-24. (PMID: <searchLink fieldCode="PM" term="%2219174895%22">19174895)</searchLink><br />Water Res. 2011 Feb;45(4):1659-68. (PMID: <searchLink fieldCode="PM" term="%2221195447%22">21195447)</searchLink><br />J Environ Manage. 2016 Jan 15;166:285-93. (PMID: <searchLink fieldCode="PM" term="%2226517277%22">26517277)</searchLink><br />Mar Pollut Bull. 2014 Feb 15;79(1-2):114-22. (PMID: <searchLink fieldCode="PM" term="%2224393380%22">24393380)</searchLink><br />Environ Monit Assess. 2013 Mar;185(3):2355-66. (PMID: <searchLink fieldCode="PM" term="%2222736208%22">22736208)</searchLink>
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>Beach monitoring; Fecal indicator bacteria; Hydrodynamics; Lake Michigan; Random forest; SHAP
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260827 <i>Date Completed: </i>20260827 <i>Latest Revision: </i>20260923
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260923
– Name: PubmedCentralID
  Label: PubMed Central ID
  Group: ID
  Data: PMC13522073
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1007/s10661-026-15791-3
– Name: AN
  Label: PMID
  Group: ID
  Data: 42658341
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42658341
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s10661-026-15791-3
    Languages:
      – Code: eng
        Text: English
    Subjects:
      – SubjectFull: Chicago
        Type: general
      – SubjectFull: Random Forest
        Type: general
      – SubjectFull: Water Movements
        Type: general
      – SubjectFull: Bathing Beaches statistics & numerical data
        Type: general
      – SubjectFull: Enterococcus growth & development
        Type: general
      – SubjectFull: Enterococcus isolation & purification
        Type: general
      – SubjectFull: Environmental Monitoring methods
        Type: general
      – SubjectFull: Water Microbiology
        Type: general
    Titles:
      – TitleFull: Wave-driven resuspension as the dominant environmental predictor of enterococci at Chicago beaches.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Ferron L
      – PersonEntity:
          Name:
            NameFull: Shrestha A
      – PersonEntity:
          Name:
            NameFull: Silva MR
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 27
              M: 08
              Text: 2026 Aug 27
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1573-2959
          Numbering:
            – Type: volume
              Value: 198
            – Type: issue
              Value: 9
          Titles:
            – TitleFull: Environmental monitoring and assessment
              Type: main
ResultId 1