Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

One-Tube RPA-CRISPR-Cas13a assay with rational design for single-molecule detection of waterborne viruses in drinking water treatment.

Biosensors & bioelectronics·2026
Same author

Pollutant fate of groundwater LNAPLs under unknown pollution source information by stochastic methods.

Journal of contaminant hydrology·2026
Same author

Assessment of glymphatic system function using DTI-ALPS in depressive disorders: a study of its correlation with clinical features and plasma GFAP levels.

Quantitative imaging in medicine and surgery·2026
Same author

Critical elements for groundwater contamination source identification (GCSI) in sparse/discontinuous data scenarios: Physical constraints and spatiotemporal information.

Water research·2026
Same author

Metabolic adaptation to IMMT deficiency through the ATF6-PPARγ axis is contingent on TP53 mutation status in breast cancer.

Cell death & disease·2026
Same author

Capture sequencing demonstrates promising public health potential for post-COVID wastewater surveillance: a comparative multi-technique and spatiotemporal analysis.

Environment international·2026

Related Experiment Video

Updated: Jun 27, 2025

Dissolved Solute Sampling Across an Oxic-Anoxic Soil-Water Interface Using Microdialysis Profilers
11:43

Dissolved Solute Sampling Across an Oxic-Anoxic Soil-Water Interface Using Microdialysis Profilers

Published on: March 24, 2023

1.3K

Bidirectional machine learning-assisted sensitivity-based stochastic searching approach for groundwater DNAPL source

Zeyu Hou1,2, Yingzi Lin3,4, Tongzhe Liu5,6

  • 1Key Laboratory of Songliao Aquatic Environment, Ministry of Education, Jilin Jianzhu University, Changchun, 130118, China. houzeyu890829@163.com.

Environmental Science and Pollution Research International
|April 29, 2024
PubMed
Summary

This study introduces a machine learning method to identify groundwater contamination sources and transport parameters. The approach improves accuracy and efficiency compared to traditional methods, offering more precise contaminant source information.

Keywords:
Bidirectional pattern recognitionGroundwater contaminationMachine learningSensitivity-based stochastic searchingSource characterization

More Related Videos

Cost-effective Method for Microbial Source Tracking Using Specific Human and Animal Viruses
11:29

Cost-effective Method for Microbial Source Tracking Using Specific Human and Animal Viruses

Published on: December 3, 2011

12.2K
A Modified EPA Method 1623 that Uses Tangential Flow Hollow-fiber Ultrafiltration and Heat Dissociation Steps to Detect Waterborne Cryptosporidium and Giardia spp.
12:11

A Modified EPA Method 1623 that Uses Tangential Flow Hollow-fiber Ultrafiltration and Heat Dissociation Steps to Detect Waterborne Cryptosporidium and Giardia spp.

Published on: July 9, 2012

20.4K

Related Experiment Videos

Last Updated: Jun 27, 2025

Dissolved Solute Sampling Across an Oxic-Anoxic Soil-Water Interface Using Microdialysis Profilers
11:43

Dissolved Solute Sampling Across an Oxic-Anoxic Soil-Water Interface Using Microdialysis Profilers

Published on: March 24, 2023

1.3K
Cost-effective Method for Microbial Source Tracking Using Specific Human and Animal Viruses
11:29

Cost-effective Method for Microbial Source Tracking Using Specific Human and Animal Viruses

Published on: December 3, 2011

12.2K
A Modified EPA Method 1623 that Uses Tangential Flow Hollow-fiber Ultrafiltration and Heat Dissociation Steps to Detect Waterborne Cryptosporidium and Giardia spp.
12:11

A Modified EPA Method 1623 that Uses Tangential Flow Hollow-fiber Ultrafiltration and Heat Dissociation Steps to Detect Waterborne Cryptosporidium and Giardia spp.

Published on: July 9, 2012

20.4K

Area of Science:

  • Environmental Science
  • Machine Learning
  • Hydrogeology

Background:

  • Dense non-aqueous phase liquid (DNAPL) contamination poses significant challenges in groundwater remediation.
  • Accurate identification of DNAPL source characteristics and contaminant transport parameters is crucial for effective site management.
  • Existing methods often struggle with computational demands and accuracy in complex subsurface environments.

Purpose of the Study:

  • To develop an efficient machine learning-based parallel global searching method for DNAPL source identification.
  • To improve the accuracy and reduce uncertainty in estimating contaminant transport parameters.
  • To provide a more robust and computationally efficient alternative to traditional inversion techniques.

Main Methods:

  • Designed a Bayesian inversion framework incorporating a swarm intelligence organized hybrid-kernel extreme learning machine (SIO-HKELM).
  • Developed an adaptive inverse-HKELM for initial parameter estimation and prior information correction.
  • Integrated a sensitivity-based Metropolis criterion (MC) with dynamic particle swarm optimization (SD-PSO) for enhanced search ergodicity.

Main Results:

  • SIO-HKELM demonstrated superior generalization and robustness over KELM and SVR, approximating numerical model mappings with high accuracy (R²=0.9944 for forward, R²=0.6440 for inverse).
  • The adaptive inverse-HKELM approach reduced inversion uncertainty and accelerated convergence to posterior distributions within approximately 60 iterations.
  • SD-PSO-MC effectively covered the search space, restrained "equifinality," and reduced estimation errors to <8%, outperforming the multichain Markov chain Monte Carlo (MCMC) approach.

Conclusions:

  • The proposed machine learning-based parallel global searching method offers a precise and efficient tool for DNAPL source characterization and contaminant transport parameter inversion.
  • The SD-PSO-MC approach provides more accurate real source information compared to traditional MCMC methods.
  • This study advances the application of advanced machine learning techniques in hydrogeological contaminant investigations.