Pregled bibliografske jedinice broj: 1086898
Use of Machine Learning in the Function of Sustainability of Wastewater Treatment Plants
Use of Machine Learning in the Function of Sustainability of Wastewater Treatment Plants // International Center for Numerical Methods in Engineering (CIMNE), 2020 / Serrat, C. ; Casas, J.R. ; Gibert, V (ur.).
Barcelona, 2020. str. 1-9 doi:10.23967/dbmc.2020.144 (pozvano predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1086898 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Use of Machine Learning in the Function of
Sustainability of Wastewater Treatment Plants
Autori
Volf, Goran
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
International Center for Numerical Methods in Engineering (CIMNE), 2020
/ Serrat, C. ; Casas, J.R. ; Gibert, V - Barcelona, 2020, 1-9
ISBN
978-84-121101-8-0
Skup
15th International Conference on Durability of Building Materials and Components (DBMC 2020)
Mjesto i datum
Barcelona, Španjolska, 20.10.2020. - 23.10.2020
Vrsta sudjelovanja
Pozvano predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Wastewater Treatment Plant ; Machine Learning ; Model Trees ; Function of Sustainability ; Management
Sažetak
Wastewater treatment plants (WWTP) are complex and dynamic systems whose management and sustainability can be improved by using different modelling and prediction approaches of their work. A machine learning tool for development of model trees was used in this paper in order to develop a model for chemical oxygen demand (COD) in the wastewater effluent from the WWTP with activated sludge to increase its sustainability and helps in its management purposes. Measured data, both in influent and effluent of the WWTP were used for modelling. For the COD model, machine learning tool Weka and algorithm for development of model trees M5P were used. Obtained model has a high descriptive power and correlation coefficient and thus can be used for prediction and modelling purposes, which can help in management and sustainability of the WWTP. Also, the purpose of this paper is to show the benefits of using machine learning tools for developing WWTP models.
Izvorni jezik
Engleski
Znanstvena područja
Građevinarstvo
Napomena
This work has been supported by the University
of Rijeka under the projects number
17.06.2.1.02 (River-Sea Interaction in the
Context of Climate Change) and uniri-tehnic-18-
129 5570 (Implementation of innovative
methodologies, approaches and tools for
sustainable river basin management). Also,
this work is part of the project Influence of
summer fire on soil and water quality founded
by the Croatian Science Foundation.
