• Home
  • Search
  • Machine Learning,Generalization, and Transfer Learningfor Predicting the Exceedance of Fecal Indicator Bacteria Thresholdsat Beaches
  • Cite Icon1
  • https://doi.org/10.1021/acs.est.5c02835Copy DOI Icon

Machine Learning,Generalization, and Transfer Learningfor Predicting the Exceedance of Fecal Indicator Bacteria Thresholdsat Beaches

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Beach water testing for fecal indicator bacteria (FIB)is a keyelement of public health protection for beachgoers. Because the processcan be expensive and time-consuming, many beaches are infrequentlymonitored, putting the health of the public at risk. Machine learning(ML) models using large sets of FIB, weather, and other types of environmentaldata have been applied to predict FIB levels at beaches. If ML modelsdeveloped using data from frequently monitored beaches in one locationcould be effectively applied to another location (referred to as “generalization”),public health protections could be easily extended to those infrequentlymonitored beaches. We found that source to target generalization augmentedby transfer learning (TL) can predict FIB threshold exceedance witha specificity of 0.70 to 0.81 and sensitivity ranging from 0.28 to0.76, depending on the beaches and TL methods. This degree of specificityand the high end of the sensitivity range are comparable to the performanceof regression and ML models developed by using data from a given beachand applied to that same beach. With the addition of TL, we observedstatistically significant improvements in model performance over sourceto target generalization, with increases of 28.3% in WF1 scores and5.4% in AUC. Future research into optimizing the selection of data-richsource beaches for developing models that can be applied to a giventarget beach may further improve transfer learning.

Similar Papers
  • PDF
  • Research Article
  • Citations4

Perception without preconception: comparison between the human and machine learner in recognition of tissues from histological sections

  • Sep 30, 2022
  • Scientific Reports
  • Sanghita Barui +4
  • Research Article
  • Citations1

Leveraging finite element model with transfer learning for data-driven-based structural damage identification

  • Mar 19, 2026
  • Journal of Vibration Engineering & Technologies
  • Pei Yi Siow +3
  • Research Article
  • Citations46

Transfer learning enables prediction of steel corrosion in concrete under natural environments

  • Feb 24, 2024
  • Cement and Concrete Composites
  • Haodong Ji +3
  • PDF
  • Research Article
  • Citations48

Machine Learning Models for Blood Glucose Level Prediction in Patients With Diabetes Mellitus: Systematic Review and Network Meta-Analysis.

  • Nov 20, 2023
  • JMIR Medical Informatics
  • Kui Liu +9
  • Research Article

Comparison of Prognostic Performance Between a Machine Learning Model and Manually Measured Grey-White-Matter Ratio on Early Brain Computed Tomography After Out-of-Hospital Cardiac Arrest

  • May 01, 2026
  • Cureus
  • Fumiya Inoue +3
  • Research Article
  • Citations1

Continuous Evaluation Frameworks for Retrospective Evaluation of Clinical Machine Learning Models.

  • Feb 26, 2026
  • Critical care (London, England)
  • Annamalai Natarajan +4
  • PDF
  • Research Article
  • Citations8

Facilitating Machine Learning Model Comparison and Explanation through a Radial Visualisation

  • Oct 28, 2021
  • Energies
  • Jianlong Zhou +2
  • PDF
  • Research Article
  • Citations11

Fecal indicators and antibiotic resistance genes exhibit diurnal trends in the Chattahoochee River: Implications for water quality monitoring

  • Nov 10, 2022
  • Frontiers in Microbiology
  • Karena H Nguyen +6
  • Research Article
  • Citations9

Evaluating external generalizability of machine learning models for recycled aggregate concrete property prediction

  • Jul 15, 2024
  • Journal of Cleaner Production
  • Shreyas Pandurang Jadhav +3
  • PDF
  • Research Article
  • Citations52

An examination of daily CO2 emissions prediction through a comparative analysis of machine learning, deep learning, and statistical models

  • Jan 01, 2025
  • Environmental Science and Pollution Research
  • Adewole Adetoro Ajala +3
  • Research Article
  • Citations17

Machine Learning Can Accurately Predict Overnight Stay, Readmission, and 30-Day Complications Following Anterior Cruciate Ligament Reconstruction

  • Jul 09, 2022
  • Arthroscopy: The Journal of Arthroscopic & Related Surgery
  • Cesar D Lopez +6
  • Research Article

Comprehensive machine learning models for prediction of heart failure in 476,393 women and men from the UK Biobank reveal sex differences and underutilized risk factors

  • Oct 28, 2024
  • European Heart Journal
  • T F Kok +5
  • Research Article
  • Citations2

Performance Enhancement of Hybrid Algorithm for Bank Telemarketing

  • Apr 20, 2021
  • Turkish Journal of Computer and Mathematics Education (TURCOMAT)
  • Rohan Desai
  • PDF
  • Research Article
  • Citations23

Application of machine learning for lung cancer survival prognostication-A systematic review and meta-analysis.

  • Apr 05, 2024
  • Frontiers in Artificial Intelligence
  • Alexander J Didier +5
  • Research Article

Comparing machine and deep learning models for pediatric anxiety classification using structured EHRs and area-based measures of health data

  • May 12, 2026
  • PLOS One
  • Eric W Lee +17
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.