An efficient approach based on bi-sensitivity analysis and genetic algorithm for calibration of activated sludge models

Chen, Wenliang; Lü, Xiwu; Yao, Chonghua; Zhu, Guangcan; Wang, Chao

doi:10.1016/j.cej.2014.07.131

Cited by 12 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OpenBox library [58] in python is used as the implementation for Bayesian Blackbox optimization approach. Genetic Algorithm, GA, is another approach that has been used with success for parameter fitting in kinetic models [59]. GA is employed in ADToolbox using pyGAD library [60].…”

Section: Optimization Modulementioning

confidence: 99%

ADToolbox: Incorporating Metagenomics Data for Improved Prediction of Anaerobic Digestion Dynamics

Ghadermazi,

Rico,

Rimmelman

et al. 2024

Preprint

View full text Add to dashboard Cite

Handling the global food waste requires sustainable solutions. Anaerobic digestion (AD) is a common approach for waste remediation and bioenergy production which has been traditionally used mainly for methane production. Shifting the focus from methane to volatile fatty acids (VFAs), such as acetic, propionic, and butyric acids, offers promising alternatives due to their diverse applications and higher added value. Achieving desired AD product distributions requires a comprehensive understanding of factors like temperature, pH, feedstock composition, and the complex microbial dynamics inherent in AD. Various AD modeling approaches exist, from simple equations to complex flux balance analysis (FBA) and machine learning (ML) model. The Anaerobic Digestion Model No. 1 (ADM 1) is a commonly used kinetic model, striking a reasonable balance between parameter requirements and biochemical details involved in the model. Yet, it falls short in capturing specific VFAs like caproic acid and integrating microbial information directly. We present ADToolbox, a Python package for modeling AD metabolism. ADToolbox incorporates metagenomic information into an enhanced ADM model. The model accommodates a more detailed feedstock degradation model and VFA and methanogenesis metabolism. ADToolbox provides a variety of interfaces such as command line interface and an interactive web interface line interface, and a Python API, facilitating large-scale metagenomic analyses and modeling simulations. In this article we indicate that prioritizing the microbial aspect of AD enhances flexibility and predictive power in terms of VFA production accuracy, contributing to sustainable waste management strategies. Explore ADToolbox at https://chan-csu.github.io/ADToolbox for detailed documentation.

show abstract

Section: Optimization Modulementioning

confidence: 99%

ADToolbox: Incorporating Metagenomics Data for Improved Prediction of Anaerobic Digestion Dynamics

Ghadermazi,

Rico,

Rimmelman

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The effects of parameters on the model outputs can be determined by sensitivity analysis methodology [25]. If a parameter was determined reliably, the measured data should be highly sensitive to any changes in this parameter [6].…”

Section: Parameter Identifiability and Sensitivity Analysismentioning

confidence: 99%

A simple kinetic modeling approach for aerobic stabilization of real waste activated sludge

Bahar

Çığgın

2016

Chemical Engineering Journal

View full text Add to dashboard Cite

“…Pang et al ( 2019 ) developed a fluctuant influent responsive Q-learning based BPR optimizing control method. An efficient approach based on bi-sensitivity analysis and genetic algorithm for calibration of activated sludge models was proposed by Chen et al ( 2015 ). However, the algorithm for the identification of PAOs has not been reported yet.…”

Section: Introductionmentioning

confidence: 99%

Identification of Genome Sequences of Polyphosphate-Accumulating Organisms by Machine Learning

Liu

Nan

et al. 2021

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

In the field of sewage treatment, the identification of polyphosphate-accumulating organisms (PAOs) usually relies on biological experiments. However, biological experiments are not only complicated and time-consuming, but also costly. In recent years, machine learning has been widely used in many fields, but it is seldom used in the water treatment. The present work presented a high accuracy support vector machine (SVM) algorithm to realize the rapid identification and prediction of PAOs. We obtained 6,318 genome sequences of microorganisms from the publicly available microbial genome database for comparative analysis (MBGD). Minimap2 was used to compare the genomes of the obtained microorganisms in pairs, and read the overlap. The SVM model was established using the similarity of the genome sequences. In this SVM model, the average accuracy is 0.9628 ± 0.019 with 10-fold cross-validation. By predicting 2,652 microorganisms, 22 potential PAOs were obtained. Through the analysis of the predicted potential PAOs, most of them could be indirectly verified their phosphorus removal characteristics from previous reports. The SVM model we built shows high prediction accuracy and good stability.

show abstract

An efficient approach based on bi-sensitivity analysis and genetic algorithm for calibration of activated sludge models

Cited by 12 publications

References 32 publications

ADToolbox: Incorporating Metagenomics Data for Improved Prediction of Anaerobic Digestion Dynamics

ADToolbox: Incorporating Metagenomics Data for Improved Prediction of Anaerobic Digestion Dynamics

A simple kinetic modeling approach for aerobic stabilization of real waste activated sludge

Identification of Genome Sequences of Polyphosphate-Accumulating Organisms by Machine Learning

Contact Info

Product

Resources

About