Estimation of Average Stream Flows Using Various Machine Learning Algorithms: A Case Study of Köprüçay

Yunus Ziya Kaya

Makale detayları

Estimation of Average Stream Flows Using Various Machine Learning Algorithms: A Case Study of Köprüçay

Yazarlar:

Yunus Ziya Kaya

Yayıncı:

Gazi University

Ana Başlıklar:

Su Kaynakları Mühendisliği

Dergi:

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji Vol.13 Issue 1, pp.130-142

Belge Tipi:

Makale

Yayın Tarihi:

3/2025

Belge Dili:

Türkçe

Document ID (Org No.):

2001343541

pISSN:

2147-9526

Anahtar kelimeler:

Özet:

 The average stream flows contain important clues about the adequacy of the basins water resources. Along with climate change, there are regional changes in parameters that directly concern stream flows, such as precipitation and temperature. These changes also cause regional differences in average flows. In this study, the average flows of the Köprüçay station located in the Beşkonak district of the Serik district of Antalya province, whose records are shared by the Electricity Administration, were examined. The average flow of the station between the years 1957 and 2011 was modeled using Multi-Layer Perceptron MLP, Support Vector Machines SVM, and Random Forest RF machine learning algorithms. The study consists of two parts. In the first part, the data between the years 1957-2011 were used as both training and test sets, and the most appropriate algorithm was decided in this way. In the second part, after the algorithm selection, the average flows between the years 2012-2022, for which records were not available, were estimated. In the models, the annual average maximum, minimum, average temperature and average precipitation data of Türkiye were used as input. As a result, it was seen that the most suitable algorithm for estimating the average current in Köprüçay would be RF.

 The average stream flows contain important clues about the adequacy of the basins water resources. Along with climate change, there are regional changes in parameters that directly concern stream flows, such as precipitation and temperature. These changes also cause regional differences in average flows. In this study, the average flows of the Köprüçay station located in the Beşkonak district of the Serik district of Antalya province, whose records are shared by the Electricity Administration, were examined. The average flow of the station between the years 1957 and 2011 was modeled using Multi-Layer Perceptron MLP, Support Vector Machines SVM, and Random Forest RF machine learning algorithms. The study consists of two parts. In the first part, the data between the years 1957-2011 were used as both training and test sets, and the most appropriate algorithm was decided in this way. In the second part, after the algorithm selection, the average flows between the years 2012-2022, for which records were not available, were estimated. In the models, the annual average maximum, minimum, average temperature and average precipitation data of Türkiye were used as input. As a result, it was seen that the most suitable algorithm for estimating the average current in Köprüçay would be RF.

 The average stream flows contain important clues about the adequacy of the basins water resources. Along with climate change, there are regional changes in parameters that directly concern stream flows, such as precipitation and temperature. These changes also cause regional differences in average flows. In this study, the average flows of the Köprüçay station located in the Beşkonak district of the Serik district of Antalya province, whose records are shared by the Electricity Administration, were examined. The average flow of the station between the years 1957 and 2011 was modeled using Multi-Layer Perceptron MLP, Support Vector Machines SVM, and Random Forest RF machine learning algorithms. The study consists of two parts. In the first part, the data between the years 1957-2011 were used as both training and test sets, and the most appropriate algorithm was decided in this way. In the second part, after the algorithm selection, the average flows between the years 2012-2022, for which records were not available, were estimated. In the models, the annual average maximum, minimum, average temperature and average precipitation data of Türkiye were used as input. As a result, it was seen that the most suitable algorithm for estimating the average current in Köprüçay would be RF.

 Akarsu ortalama akımları havzanın su kaynaklarının yeterliliği hakkında önemli ipuçları barındırmaktadır. İklim değişikliği ile birlikte yağış ve sıcaklık gibi akarsu akımlarını doğrudan ilgilendiren parametrelerde bölgesel değişimler yaşanmaktadır. Yaşanan bu değişimler ortalama akımlarda da bölgesel farklılıklar görülmesine neden olmaktadır. Bu çalışmada Elektrik İdaresinin kayıtlarını paylaştığı Antalya ili Serik İlçesi Beşkonak Bucağında yer alan Köprüçay istasyonuna ait ortalama akımlar incelenmiştir. İstasyona ait 1957-2011 yılları arasındaki ortalama akımlar Multi-Layer Perceptron MLP, Destek Vektör Makinaları DVM ve Random Forest RF makine öğrenme algoritmaları ile modellenmiştir. Çalışma iki kısımdan oluşmaktadır. İlk kısımda 1957-2011 yılları arasındaki veriler hem eğitim hem test kümesi olarak kullanılmış en uygun algoritmaya bu şekilde karar verilmiştir. İkinci kısımda algoritma seçiminden sonra kayıtları mevcut olmayan 2012-2022 yılları arasındaki ortalama akımlar tahmin edilmiştir. Modellemelerde ülkemize ait yıllık ortalama maksimum, minimum, ortalama sıcaklık ve ortalama yağış verileri girdi olarak kullanılmıştır. Sonuç olarak Köprüçay özelinde ortalama akım tahmininde en uygun algoritmanın RF olacağı görülmüştür.

Makale detayları

Estimation of Average Stream Flows Using Various Machine Learning Algorithms: A Case Study of Köprüçay

Yazarlar:

Yunus Ziya Kaya

Yayıncı:

Gazi University

Ana Başlıklar:

Su Kaynakları Mühendisliği

Dergi:

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji Vol.13 Issue 1, pp.130-142

Belge Tipi:

Makale

Yayın Tarihi:

3/2025

Belge Dili:

Türkçe

Document ID (Org No.):

2001343541

pISSN:

2147-9526

Average Flows

MLP

SVM

RF

PredictionOrtalama Akımlar

MLP

DVM

Random Forest

Tahmin

Sayı

Makale detayları

Yazarlar: Yunus Ziya Kaya

Yayıncı: Gazi University

Ana Başlıklar: Su Kaynakları Mühendisliği

Dergi: Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji Vol.13 Issue 1, pp.130-142

Belge Tipi: Makale

Yayın Tarihi: 3/2025

Belge Dili: Türkçe

Document ID (Org No.): 2001343541

pISSN: 2147-9526

Sayı

Yazarlar:

Yunus Ziya Kaya

Yayıncı:

Gazi University

Ana Başlıklar:

Su Kaynakları Mühendisliği

Dergi:

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji Vol.13 Issue 1, pp.130-142

Belge Tipi:

Makale

Yayın Tarihi:

3/2025

Belge Dili:

Türkçe

Document ID (Org No.):

2001343541

pISSN:

2147-9526