Next Generation Sequencing Analysis of Wastewater Treatment Plant Process via Support Vector Regression

Negara, Mohamad Agung Prawira; Cornelissen, Emile; Geurkink, A.K.; Euverink, Gerrit Jan Willem; Jayawardhana, Bayu

doi:10.1016/j.ifacol.2019.11.006

Cited by 6 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various regression methods (linear, nonlinear, or Bayesian) using nonlinear static, dynamic, or spatially distributed models, can be used in these cases. Negara et al (2019) has used SVM to solve a nonlinear regression problem that maps metagenomics data from a wastewater treatment plant into the process parameters. Finally, reinforcement learning algorithms use feedback-based learning algorithms where actions and rewards are defined, involving the decision-making agent and environment, in order to maximize a given utility/value function.…”

Section: Artificial Intelligence Methods In Dwds Current Lines Of Enq...mentioning

confidence: 99%

Clean and Safe Drinking Water Systems via Metagenomics Data and Artificial Intelligence: State-of-the-Art and Future Perspective

Mahajna

Dinkla²,

Euverink

et al. 2022

Front. Microbiol.

View full text Add to dashboard Cite

The use of next-generation sequencing technologies in drinking water distribution systems (DWDS) has shed insight into the microbial communities’ composition, and interaction in the drinking water microbiome. For the past two decades, various studies have been conducted in which metagenomics data have been collected over extended periods and analyzed spatially and temporally to understand the dynamics of microbial communities in DWDS. In this literature review, we outline the findings which were reported in the literature on what kind of occupancy-abundance patterns are exhibited in the drinking water microbiome, how the drinking water microbiome dynamically evolves spatially and temporally in the distribution networks, how different microbial communities co-exist, and what kind of clusters exist in the drinking water ecosystem. While data analysis in the current literature concerns mainly with confirmatory and exploratory questions pertaining to the use of metagenomics data for the analysis of DWDS microbiome, we present also future perspectives and the potential role of artificial intelligence (AI) and mechanistic models to address the predictive and mechanistic questions. The integration of meta-omics, AI, and mechanistic models transcends metagenomics into functional metagenomics, enabling deterministic understanding and control of DWDS for clean and safe drinking water systems of the future.

show abstract

Section: Artificial Intelligence Methods In Dwds Current Lines Of Enq...mentioning

confidence: 99%

Clean and Safe Drinking Water Systems via Metagenomics Data and Artificial Intelligence: State-of-the-Art and Future Perspective

Mahajna

Dinkla²,

Euverink

et al. 2022

Front. Microbiol.

View full text Add to dashboard Cite

show abstract

“…This is because this method has shown good generalization ability, avoiding the problems of training overfitting that occur in other similar methods [29]. Recently, it has also been used in the field of wastewater treatment to predict different parameters of the treatment process [30][31][32][33][34][35][36][37].…”

Section: Methodsmentioning

confidence: 99%

Gross Solids Content Prediction in Urban WWTPs Using SVM

Pérez

Fernández

et al. 2021

Water

View full text Add to dashboard Cite

The preliminary treatment of wastewater at wastewater treatment plants (WWTPs) is of great importance for the performance and durability of these plants. One fraction that is removed at this initial stage is commonly called gross solids and can cause various operational, downstream performance, or maintenance problems. To avoid this, data from more than two operation years of the Villapérez Wastewater Treatment Plant, located in the northeast of the city of Oviedo (Asturias, Spain), were collected and used to develop a model that predicts the gross solids content that reaches the plant. The support vector machine (SVM) method was used for modelling. The achieved model precision (Radj2 = 0.7 and MSE = 0.43) allows early detection of trend changes in the arrival of gross solids and will improve plant operations by avoiding blockages and overflows. The results obtained indicate that it is possible to predict trend changes in gross solids content as a function of the selected input variables. This will prevent the plant from suffering possible operational problems or discharges of untreated wastewater as actions could be taken, such as starting up more pretreatment lines or emptying the containers.

show abstract

“…In Negara et al (2019) by analyzing the (local) sensitivity of each modeled process variable to each genus (NGS data) and based on the SVR found in the previous step, an indication of the influence of the microbial structure on process performance was found. Table 3 shows the sensitivity analysis (SA) of four process variables related to the genera found in the system.…”

Section: Ngs Data Analysismentioning

confidence: 99%

NGS-enriched activated sludge modelling of industrial wastewater treatment plant

Negara

Keesman

Euverink

et al. 2023

Preprint

View full text Add to dashboard Cite

Metagenomics advances with the Next Generation Sequencing (NGS) technology offer detailed insights into the microbial communities and their activities in a Wastewater Treatment Plant (WWTP). Since it has been shown recently that the microbial communities can be related to process data through machine learning, we investigate in this paper the enrichment of Activated Sludge Model 1 (ASM1) using time-series NGS data. We first present a modified ASM1 (mod-ASM1) to describe the industrial wastewater treatment at North Water's WWTP facility in Delfzijl, the Netherlands. Subsequently, we identify the parameters for the ten weeks (weeks 40-50, 2014) of process data from North Water WWTP with prior parameters from the recommended ones from IWA. We further established a subset of parameters that are correlated to NGS data. Based on this relationship, a parameter-varying mod-ASM1 is obtained where the parameter variation is directly linked to the NGS data. We validate the NGS-enriched mod-ASM1 in the prediction of process data in the subsequent three weeks (weeks 50-53, 2014). While the enriched mod-ASM1 gives a good estimation of the COD effluent data, it cannot capture the production of nitrogen, which is often missed when the static model is deployed.

show abstract

Next Generation Sequencing Analysis of Wastewater Treatment Plant Process via Support Vector Regression

Cited by 6 publications

References 5 publications

Clean and Safe Drinking Water Systems via Metagenomics Data and Artificial Intelligence: State-of-the-Art and Future Perspective

Clean and Safe Drinking Water Systems via Metagenomics Data and Artificial Intelligence: State-of-the-Art and Future Perspective

Gross Solids Content Prediction in Urban WWTPs Using SVM

NGS-enriched activated sludge modelling of industrial wastewater treatment plant

Contact Info

Product

Resources

About