The dissolved oxygen prediction based on the machine learning techniques

Voza, Danijela; Dehghani, Hesam; Veličković, Milica

Conference Object Open access M33

Proceedings_IOC_2023-507-510full.pdf (3.39MB)

2023

Voza, Danijela
Dehghani, Hesam
Veličković, Milica

University of Belgrade, Technical Faculty in Bor

Proceedings - 54th International October Conference on Mining and Metallurgy - IOC 2023, 18-21 October 2023, Bor Lake, Serbia, 2023, 485-488

485

488

English

M33 - Conference paper at an international conference, printed in full

One of the most reliable indicators of surface water quality is dissolved oxygen (DO). In order to take timely reactions in water pollution prevention and reduction, it is very useful to predict the changes in this parameter. In this study, a comparative analysis of the efficiency of different machine learning models in DO prediction was carried out. The aim was to examine which of the selected techniques indicate the best performance in DO prediction - Decision Tree, Random Forest, Gradient Boost Regression, Support Vector Regression, Multi-Layer Perceptron, and K - Nearest Neighbors Regression (KNN). According to the results, it can be concluded the best-fitted model on the created dataset is KNN.

Dissolved Oxygen, Machine learning, Prediction, Water quality, Tisa River

ISBN

978-86-6305-140-9

URI

https://ioc.tfbor.bg.ac.rs/public/2023/Proce...
https://repozitorijum.tfbor.bg.ac.rs/handle/...

dc.rights.license	CC-BY-NC-ND
dc.identifier.uri	https://ioc.tfbor.bg.ac.rs/public/2023/Proceedings_IOC_2023.pdf
dc.identifier.uri	https://repozitorijum.tfbor.bg.ac.rs/handle/123456789/5794
dc.description.abstract	One of the most reliable indicators of surface water quality is dissolved oxygen (DO). In order to take timely reactions in water pollution prevention and reduction, it is very useful to predict the changes in this parameter. In this study, a comparative analysis of the efficiency of different machine learning models in DO prediction was carried out. The aim was to examine which of the selected techniques indicate the best performance in DO prediction - Decision Tree, Random Forest, Gradient Boost Regression, Support Vector Regression, Multi-Layer Perceptron, and K - Nearest Neighbors Regression (KNN). According to the results, it can be concluded the best-fitted model on the created dataset is KNN.
dc.language.iso	en
dc.publisher	University of Belgrade, Technical Faculty in Bor
dc.source	Proceedings - 54th International October Conference on Mining and Metallurgy - IOC 2023, 18-21 October 2023, Bor Lake, Serbia, 2023, 485-488
dc.subject	Dissolved Oxygen
dc.subject	Machine learning
dc.subject	Prediction
dc.subject	Water quality
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject	Tisa River
dc.title	The dissolved oxygen prediction based on the machine learning techniques
dc.type	conferenceObject
dc.type.version	publishedVersion
dc.citation.spage	485
dc.citation.epage	488
dc.citation.rank	M33
dc.creator	Voza, Danijela
dc.creator	Dehghani, Hesam
dc.creator	Veličković, Milica
dc.date.accessioned	2024-01-10T10:56:08Z
dc.date.available	2024-01-10T10:56:08Z
dc.date.issued	2023
dc.identifier.isbn	978-86-6305-140-9


The dissolved oxygen prediction based on the machine learning techniques	3


Proceedings_IOC_2023-507-510full.pdf	0