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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

47
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
47
Typical Model Studies01:30

Typical Model Studies

354
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.
354

You might also read

Related Articles

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

Sort by
Same author

Enhancing interpretable soft sensing with embedded hybrid modeling: the GraphTrans approach for industrial processes.

ISA transactions·2026
Same author

Endometrial Cancer of the Uterine Isthmus: A Cohort Study on Clinicopathological Features and Prognosis.

Cancer medicine·2026
Same author

Dietary Fermented Chinese Chive Juice Improves Growth Performance and Reshapes the Fresh Meat Volatile Flavor Profile of Small-Tailed Han Sheep.

Animals : an open access journal from MDPI·2026
Same author

Distribution of divalent small interfering RNA into neurons of sensory ganglia produces selective, durable knockdown of Nav1.7 and strong analgesia.

Pain·2026
Same author

Epidemiology of respiratory infectious diseases after the relaxation of COVID-19 policies: a retrospective study in Xiamen, China.

Frontiers in public health·2026
Same author

Oral Colon-Targeted Lipid Nanoparticles Enhance Upadacitinib Delivery and Efficacy in a Murine Model of Ulcerative Colitis.

International journal of molecular sciences·2026

Related Experiment Video

Updated: Jun 19, 2025

Continuous Hydrologic and Water Quality Monitoring of Vernal Ponds
06:37

Continuous Hydrologic and Water Quality Monitoring of Vernal Ponds

Published on: November 13, 2017

9.2K

Learning a neural network-based soft sensor with double-errors parallel optimization towards effluent variable

Dong Li1, Chunhua Yang1, Yonggang Li1

  • 1The School of Automation, Central South University, Changsha, 410083, China.

Journal of Environmental Management
|July 24, 2024
PubMed
Summary

This study introduces an improved neural network soft sensor for wastewater treatment plants (WWTPs). It enhances prediction accuracy and efficiency for water quality indicators by optimizing model training and variable selection.

Keywords:
Effluent variable predictionNeural network optimizationSoft sensorVariable selectionWastewater treatment

More Related Videos

Continuous Instream Monitoring of Nutrients and Sediment in Agricultural Watersheds
12:50

Continuous Instream Monitoring of Nutrients and Sediment in Agricultural Watersheds

Published on: September 26, 2017

11.2K
Comparison of Scale in a Photosynthetic Reactor System for Algal Remediation of Wastewater
05:40

Comparison of Scale in a Photosynthetic Reactor System for Algal Remediation of Wastewater

Published on: March 6, 2017

9.0K

Related Experiment Videos

Last Updated: Jun 19, 2025

Continuous Hydrologic and Water Quality Monitoring of Vernal Ponds
06:37

Continuous Hydrologic and Water Quality Monitoring of Vernal Ponds

Published on: November 13, 2017

9.2K
Continuous Instream Monitoring of Nutrients and Sediment in Agricultural Watersheds
12:50

Continuous Instream Monitoring of Nutrients and Sediment in Agricultural Watersheds

Published on: September 26, 2017

11.2K
Comparison of Scale in a Photosynthetic Reactor System for Algal Remediation of Wastewater
05:40

Comparison of Scale in a Photosynthetic Reactor System for Algal Remediation of Wastewater

Published on: March 6, 2017

9.0K

Area of Science:

  • Environmental Engineering
  • Artificial Intelligence
  • Water Quality Monitoring

Background:

  • Machine learning and AI models are increasingly used for predicting water quality in wastewater treatment plants (WWTPs).
  • Existing models face challenges with accuracy and efficiency due to the complex, dynamic nature of wastewater treatment processes.
  • Time-varying, nonlinear, and high-dimensional data in WWTPs compromise prediction performance and computational speed.

Purpose of the Study:

  • To develop a more accurate and computationally efficient neural network-based soft sensor for real-time effluent variable prediction in WWTPs.
  • To address the limitations of current data-driven soft sensors in handling complex wastewater treatment dynamics.
  • To improve the timely prediction of key water quality indicators for effective WWTP management.

Main Methods:

  • An ensemble variable selection method combining Pearson correlation coefficient (PCC) and mutual information (MI) based on the Activity Based Classification (ABC) principle was used.
  • Optimal process variables were selected as auxiliary variables to reduce data dimensionality and model complexity.
  • A novel double-errors parallel optimization methodology was proposed to simultaneously minimize point prediction error and distribution error, enhancing neural network training efficiency and fitting quality.

Main Results:

  • The proposed soft sensor demonstrated precise effluent variable prediction on both the Benchmark Simulation Model no. 1 (BMS1) and an actual oxidation ditch WWTP dataset.
  • Quantitative assessment showed excellent performance with RMSE, MAE, and R² values.
  • The method significantly expedited neural network training convergence speed and improved overall prediction performance.

Conclusions:

  • The developed soft sensor effectively enhances prediction accuracy and computational efficiency for water quality indicators in WWTPs.
  • The double-errors parallel optimization and ensemble variable selection contribute to superior model performance.
  • This approach offers a valuable tool for the effective optimization and management of wastewater treatment processes.