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

Plant-associated microbial enrichment is linked to trace emerging contaminant removal in full-scale constructed wetland.

Bioresource technology·2026
Same author

Patterns and mechanisms of cross-media antimicrobial resistance development in a typical reclaimed water-receiving urban river.

Water research·2026
Same author

From fixed to condition-dependent emission factors: probabilistic tabular learning for wastewater N<sub>2</sub>O inventories.

Water research·2026
Same author

Temporal sulfur redox reprogramming enables control-oriented intensification of sulfur-based autotrophic denitrification.

Water research·2026
Same author

Machine learning-integrated multi-objective application and optimization framework for sulfur-based reactive filler towards nutrient removal.

Water research·2026
Same author

Machine learning-driven prediction and control system for practical application of sulfur-based autotrophic denitrification biofilters.

Water research·2026

Related Experiment Video

Updated: Jun 5, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

502

Augmented machine learning for sewage quality assessment with limited data.

Jia-Qiang Lv1,2, Wan-Xin Yin3, Jia-Min Xu2

  • 1State Key Laboratory of Urban Water Resource and Environment, School of Environment, Harbin Institute of Technology, Harbin, 150090, China.

Environmental Science and Ecotechnology
|December 11, 2024
PubMed
Summary
This summary is machine-generated.

A new hybrid model improves sewer monitoring by combining mechanistic and machine learning approaches. This enhances prediction of harmful compounds like sulfide and methane, even with limited data.

Keywords:
Hybrid modelMachine learningMechanistic augmentationSewer systemSulfide and methane

More Related Videos

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

6.8K
Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates
08:56

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates

Published on: January 13, 2023

2.1K

Related Experiment Videos

Last Updated: Jun 5, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

502
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

6.8K
Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates
08:56

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates

Published on: January 13, 2023

2.1K

Area of Science:

  • Environmental Engineering
  • Water Resource Management
  • Computational Science

Background:

  • Sewer systems generate sulfide and methane, causing corrosion and greenhouse gas emissions.
  • Accurate modeling of these compounds is crucial for effective sewer management.
  • Data scarcity and varying sampling frequencies limit traditional machine learning model development.

Purpose of the Study:

  • To develop a novel model for enhanced monitoring of methane and sulfide in sewers.
  • To address data accessibility and sampling frequency challenges in sewer water quality modeling.
  • To improve the accuracy and reliability of predictive models for sewer environments.

Main Methods:

  • Introduction of a mechanistically enhanced hybrid (ME-Hybrid) model.
  • Integration of mechanistic modeling with data-driven machine learning (ML) approaches.
  • Harmonization of datasets with varying sampling frequencies and generation of synthetic samples for ML training.

Main Results:

  • The ME-Hybrid model, specifically integrating backpropagation neural networks with mechanistic frequency harmonization, outperformed pure ML and linear interpolation for sulfide prediction (R² = 0.94).
  • Synthetic samples generated via mechanistic augmentation closely mimicked real samples, maintaining high predictive accuracy (R² > 0.76) even with 50% data reduction.
  • The model demonstrated strong performance in assessing sewer methane concentrations (R² = 0.94), confirming its applicability and generalization capabilities.

Conclusions:

  • The ME-Hybrid model offers a reliable framework for sewer compound modeling and prediction, particularly under data scarcity.
  • This approach enhances sewer monitoring, aiding strategies to minimize environmental impacts and improve urban resilience.
  • The study supports the development of sustainable urban water systems through improved sewer management.