Prediction of the Dissolved Oxygen by Using Multi-Layer Perceptron and KNN Approaches: A Case Study in Coosa River, Alabama, USA
The dissolved oxygen amount of a water body, such as a reservoir, stream, or river, is an important water quality parameter that may affect society's health directly. The daily mean dissolved oxygen of the Coosa River was investigated in this presented study. The multi-layer Perceptron (MLP) ap...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Cluj University Press
2024-03-01
|
Series: | Aerul şi Apa: Componente ale Mediului |
Subjects: | |
Online Access: | https://aerapa.conference.ubbcluj.ro/2024/pdf/243_250_Kaya_etal_AWC_2024.pdf |
_version_ | 1797199795943636992 |
---|---|
author | Yunus Ziya KAYA Mustafa DEMİRCİ Bestami TAŞAR Hasan GÜZEL |
author_facet | Yunus Ziya KAYA Mustafa DEMİRCİ Bestami TAŞAR Hasan GÜZEL |
author_sort | Yunus Ziya KAYA |
collection | DOAJ |
description | The dissolved oxygen amount of a water body, such as a reservoir, stream, or river, is an important water quality parameter that may affect society's health directly. The daily mean dissolved oxygen of the Coosa River was investigated in this presented study. The multi-layer Perceptron (MLP) approach and k-nearest neighbor (KNN) algorithm, recently widely used for hydrological and environmental problems, was chosen for the prediction. Daily water temperature (Max, Min, and Mean), daily mean specific conductivity, daily median water pH, and discharge parameters were inputs in the MLP and KNN models. A total of 3535 daily records were implemented into the model. 2951 daily data were used as the training set, while 584 was the test set. Results were compared with each other by using statistical evaluation methods. The KNN approach was also generated by applying the same training and test sets. Based on the results, it is evident that the MLP (Multilayer Perceptron) model provided satisfactory dissolved oxygen prediction results. However, the KNN (K-Nearest Neighbors) model outperformed the MLP approach, despite having a lower correlation coefficient than the MLP. |
first_indexed | 2024-04-24T07:21:26Z |
format | Article |
id | doaj.art-e08dc8a31e5e475baa44500bd981ac9f |
institution | Directory Open Access Journal |
issn | 2067-743X 2344-4401 |
language | English |
last_indexed | 2024-04-24T07:21:26Z |
publishDate | 2024-03-01 |
publisher | Cluj University Press |
record_format | Article |
series | Aerul şi Apa: Componente ale Mediului |
spelling | doaj.art-e08dc8a31e5e475baa44500bd981ac9f2024-04-21T10:29:22ZengCluj University PressAerul şi Apa: Componente ale Mediului2067-743X2344-44012024-03-012024124325010.24193/AWC2024_21Prediction of the Dissolved Oxygen by Using Multi-Layer Perceptron and KNN Approaches: A Case Study in Coosa River, Alabama, USAYunus Ziya KAYA0Mustafa DEMİRCİ1Bestami TAŞAR2Hasan GÜZEL 3Osmaniye Korkut Ata University, Engineering Faculty, Civil Eng. Department, yunuszkaya@osmaniye.edu.trIskenderun Technical University, Eng. Faculty, Civil Engineering DepartmentIskenderun Technical University, Eng. Faculty, Civil Engineering DepartmentIskenderun Technical University, Eng. Faculty, Civil Engineering DepartmentThe dissolved oxygen amount of a water body, such as a reservoir, stream, or river, is an important water quality parameter that may affect society's health directly. The daily mean dissolved oxygen of the Coosa River was investigated in this presented study. The multi-layer Perceptron (MLP) approach and k-nearest neighbor (KNN) algorithm, recently widely used for hydrological and environmental problems, was chosen for the prediction. Daily water temperature (Max, Min, and Mean), daily mean specific conductivity, daily median water pH, and discharge parameters were inputs in the MLP and KNN models. A total of 3535 daily records were implemented into the model. 2951 daily data were used as the training set, while 584 was the test set. Results were compared with each other by using statistical evaluation methods. The KNN approach was also generated by applying the same training and test sets. Based on the results, it is evident that the MLP (Multilayer Perceptron) model provided satisfactory dissolved oxygen prediction results. However, the KNN (K-Nearest Neighbors) model outperformed the MLP approach, despite having a lower correlation coefficient than the MLP. https://aerapa.conference.ubbcluj.ro/2024/pdf/243_250_Kaya_etal_AWC_2024.pdfwater quality; mlpknndissolved oxygen |
spellingShingle | Yunus Ziya KAYA Mustafa DEMİRCİ Bestami TAŞAR Hasan GÜZEL Prediction of the Dissolved Oxygen by Using Multi-Layer Perceptron and KNN Approaches: A Case Study in Coosa River, Alabama, USA Aerul şi Apa: Componente ale Mediului water quality; mlp knn dissolved oxygen |
title | Prediction of the Dissolved Oxygen by Using Multi-Layer Perceptron and KNN Approaches: A Case Study in Coosa River, Alabama, USA |
title_full | Prediction of the Dissolved Oxygen by Using Multi-Layer Perceptron and KNN Approaches: A Case Study in Coosa River, Alabama, USA |
title_fullStr | Prediction of the Dissolved Oxygen by Using Multi-Layer Perceptron and KNN Approaches: A Case Study in Coosa River, Alabama, USA |
title_full_unstemmed | Prediction of the Dissolved Oxygen by Using Multi-Layer Perceptron and KNN Approaches: A Case Study in Coosa River, Alabama, USA |
title_short | Prediction of the Dissolved Oxygen by Using Multi-Layer Perceptron and KNN Approaches: A Case Study in Coosa River, Alabama, USA |
title_sort | prediction of the dissolved oxygen by using multi layer perceptron and knn approaches a case study in coosa river alabama usa |
topic | water quality; mlp knn dissolved oxygen |
url | https://aerapa.conference.ubbcluj.ro/2024/pdf/243_250_Kaya_etal_AWC_2024.pdf |
work_keys_str_mv | AT yunusziyakaya predictionofthedissolvedoxygenbyusingmultilayerperceptronandknnapproachesacasestudyincoosariveralabamausa AT mustafademirci predictionofthedissolvedoxygenbyusingmultilayerperceptronandknnapproachesacasestudyincoosariveralabamausa AT bestamitasar predictionofthedissolvedoxygenbyusingmultilayerperceptronandknnapproachesacasestudyincoosariveralabamausa AT hasanguzel predictionofthedissolvedoxygenbyusingmultilayerperceptronandknnapproachesacasestudyincoosariveralabamausa |