Prediction of wastewater treatment plants process performance parameters based on microbial communities using machine learning techniques

Cornelissen, Emile (2018) Prediction of wastewater treatment plants process performance parameters based on microbial communities using machine learning techniques. Research Project, Industrial Engineering and Management.

Preview	Text Thesis_EmileCornelissen.pdf Download (4MB) | Preview
	Text toestemming.pdf Restricted to Registered users only Download (120kB)

Abstract

Wastewater treatment plants (WWTPs) use a wide variety of microorganisms to remove contaminants from the astewater. This thesis researches the relationship between microbial communities and process performance. This relationship is crucial to improve process performance and provides insight in the diagnosis and prognosis of the process. The biological process of the WWTP is highly complex due to its nonlinear and dynamic behaviour and the diversity of the microbial community. Two machine learning techniques, artificial neural networks and support vector regression are used to model this complex system. Using data from nextgeneration sequencing, the microbial community composition was revealed. This data was used as input for the machine learning models to predict a selection of process performance parameters. Both models showed beyond satisfactory results in the training and test stages. By analyzing the sensitivity of each modeled process parameter to each microorganism, an indication of the influence of the microbial structure on process performance is established.

Item Type:	Thesis (Research Project)
Supervisor name:	Jayawardhana, B.
Degree programme:	Industrial Engineering and Management
Thesis type:	Research Project
Language:	English
Date Deposited:	07 Dec 2018
Last Modified:	23 Aug 2019 14:48
URI:	https://fse.studenttheses.ub.rug.nl/id/eprint/18915

Actions (login required)

View Item