Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Hybrid modeling for industrial fermentation processes with an "Intra-Batch Experimental Design".

Journal of industrial microbiology & biotechnology·2026

Same author

Impact of Agitation Power Input on Aspergillus oryzae Metabolism: Application of Multi-Omics on an Industrial Enzyme Fermentation.

Biotechnology and bioengineering·2026

Same author

Modeling denitrification byproducts during bioelectrochemical denitrification mediated by hydrogen oxidizing bacteria.

Bioresource technology·2026

Same author

Towards operational net-zero pathways in industrial wastewater treatment systems using digital decision support tools.

Water research·2026

Same author

Photoautotrophic polyhydroxyalkanoate (PHA) accumulation in mixed purple bacteria using formate, carbon dioxide and carbon monoxide.

Bioresource technology·2026

Same author

Rapid Waste Activated Sludge Reduction and Stabilization via a Biofilm-Based Acidic Aerobic Digestion Process.

Environmental science & technology·2026

Same journal

Pyrolysis temperature shapes the structure and filtration capacity of spent-coffee-ground biochar for 1-μm microplastics and bacteria removal from wastewater.

Water science and technology : a journal of the International Association on Water Pollution Research·2026

Same journal

Effect of cooling and cover material on the performance of a solar humidification-dehumidification system used for brine concentration.

Water science and technology : a journal of the International Association on Water Pollution Research·2026

Same journal

Comparative multi-criteria assessment of decentralized wastewater treatment technologies for coastal tourist communities and island slaughterhouses: a design framework with uncertainty analysis for Latin America.

Water science and technology : a journal of the International Association on Water Pollution Research·2026

Same journal

An improved relative frequency method for flood season partitioning.

Water science and technology : a journal of the International Association on Water Pollution Research·2026

Same journal

Drivers of wastewater dynamics: a statistical analysis of England's large wastewater treatment works.

Water science and technology : a journal of the International Association on Water Pollution Research·2026

Same journal

A review on modification of piezoelectric materials for wastewater treatment: mechanisms, applications, and future perspectives.

Water science and technology : a journal of the International Association on Water Pollution Research·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 15, 2026

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

Transfer learning for quantitative image analysis of biosolids.

Sebastian Olivier Nymann Topalian¹, Nima Nazemzadeh², Alonso Malacara-Becerra^2,3

¹Process and Systems Engineering Centre (PROSYS), Department of Chemical and Biochemical Engineering, Technical University of Denmark, Building 228 A, Kgs. Lyngby 2800, Denmark

Water Science and Technology : a Journal of the International Association on Water Pollution Research

|October 15, 2025

Summary

This summary is machine-generated.

Quantitative image analysis improves biosolid dewatering efficiency. A Random Forest model integrating process, lab, and transfer learning data enhanced organic solids recovery prediction by 14%.

Keywords:

centrifugal decanter quantitative image analysis sludge dewatering transfer learning

More Related Videos

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

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

Published on: June 18, 2020

Discrimination and Characterization of Heterocellular Populations Using Quantitative Imaging Techniques

Discrimination and Characterization of Heterocellular Populations Using Quantitative Imaging Techniques

Published on: June 30, 2017

Related Experiment Videos

Last Updated: Jan 15, 2026

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

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

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

Published on: June 18, 2020

Discrimination and Characterization of Heterocellular Populations Using Quantitative Imaging Techniques

Discrimination and Characterization of Heterocellular Populations Using Quantitative Imaging Techniques

Published on: June 30, 2017

Area of Science:

Environmental Engineering
Wastewater Treatment Technologies
Biosolids Management

Background:

Dewatering stabilized biosolids is crucial for industrial wastewater treatment efficiency.
Predicting organic solids recovery in decanters is challenging due to complex factors.
Quantitative image analysis offers a novel approach to enhance dewatering process understanding.

Purpose of the Study:

To develop a systematic workflow for quantitative image analysis to predict decanter organic solids recovery.
To integrate data from operational conditions, laboratory measurements, and image analysis for improved prediction.
To evaluate the effectiveness of different modeling techniques (PLS, RF) and data sources.

Main Methods:

Data collection from two industrial wastewater treatment plant campaigns.
Application of quantitative image analysis and transfer learning techniques.
Development and comparison of Partial Least Squares (PLS) and Random Forest (RF) models.

Main Results:

A Random Forest model combining process, laboratory, and transfer learning data achieved the best recovery prediction, improving it by 14% over baseline.
Clustering of particle images and RF prediction highlighted a dependency on specific crystalline particles.
Random Forest models generally outperformed PLS models in recovery prediction.

Conclusions:

Quantitative image analysis, particularly with transfer learning, significantly enhances biosolid dewatering efficiency prediction.
The study provides a transferable diagnostic workflow for optimizing dewatering in systems with heterogeneous particle mixtures.
Further refinement is needed to address prediction consistency across varying organic solids concentrations.