Prediction of electrical conductivity using ANN and MLR: a case study from Turkey

• Autorzy: Ekemen Keskin Tülay , Özler Emre , Şander Emrah , Düğenci Muharrem , Mohammed Yadgar Ahmed

Identyfikatory

DOI

10.1007/s11600-020-00424-1

• Języki publikacji: EN

Abstrakty

EN

The study areas are located in Turkey (Kastamonu, Bartın, Karabük, Sivas) and contain very diferent rock types, various mining and agricultural activity opportunities. So, the areas have groundwaters that have diferent chemical compositions and electrical conductivity (EC) values. The EC can be measured using EC meter, and it must be measured in situ. But, the measurement of EC in situ is laborious, time-consuming, expensive, and difcult in arduous terrain environments. In recent years, machine learning models have been a primary focus of interest for a lot of study by providing often highly accurate forecast for solutions of such problems. The aim of the study is to forecast EC of groundwater using artifcial neural networks (ANN) and multiple linear regressions (MLR). Twelve diferent hydrochemical parameters, which afect the EC, such as major/minor ions and trace elements, were used in the analysis. Multilayer feed-forward ANN trained with backpropagation in Python machine learning libraries was used in this study. In order to obtain the most appropriate ANN architecture, trialand-error procedure was used and diferent numbers of hidden layers, neurons, activation functions, optimizers, and test sizes were constructed. This study also tests the usability of input parameters in EC prediction studies. As a result, comparisons between the measured and predicted values indicated that the machine learning models could be successfully applied and provide high accuracy and reliability for EC and similar parameters forecasting.

Słowa kluczowe

EN

water quality parameters; artificial neural network; ANN; multiple linear regression; MLR; prediction of EC

PL

parametry jakości wody; sztuczna sieć neuronowa; SSN; wielokrotna regresja liniowa

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2020
• Tom: Vol. 68, no. 3
• Strony: 811--820
• Opis fizyczny: Bibliogr. 27 poz.

Twórcy

autor

Ekemen Keskin Tülay

• Civil Engineering Department, Faculty of Engineering, University of Karabük, Karabük, Turkey

autor

Özler Emre

• Environmental Engineering Department, Faculty of Engineering, University of Karabük, Karabük, Turkey

autor

Şander Emrah

• Civil Engineering Department, Faculty of Engineering, University of Karabük, Karabük, Turkey

autor

Düğenci Muharrem

• Industrial Engineering Department, Faculty of Engineering, University of Karabük, Karabük, Turkey

autor

Mohammed Yadgar Ahmed

• Civil Engineering Department, Faculty of Engineering, University of Karabük, Karabük, Turkey

Bibliografia

• 1. Çetin M, Uğur A, Bayzan Ş (2006) İleri beslemeli yapay sinir ağlarında backpropagation (geriye yayılım) algoritmasının sezgisel yaklaşımı. Akademik Bilişim Kongresi, Pamukkale Üniversitesi, Denizli, Şubat 2006
• 2. Djeddou M, Achour B (2015) The use of a neural network technique for the prediction of sludge volume index in municipal wastewater treatment plant. Larhyss 24:351–370
• 3. Ekemen T (2001) Tecer Dağı (Sivas-Ulaş) Kaynaklarının Hidrojeoloji İncelemesi (Hydrogeological Investigation of the Tecer Mountain Springs (Sivas-Ulaş)). M.Sc. Thesis Graduate School of Natural and Applied Sciences, Cumhuriyet University, Sivas, Turkey
• 4. Ekemen T (2006) Yıldız Irmağı Havzasının (Sivas) Hidrojeoloji İncelemesi (Hydrogeological Investigation of the Yıldız River Basin (Sivas)). PhD. Thesis Graduate School of Natural and Applied Sciences, Cumhuriyet University, Sivas, Turkey
• 5. Ghassan AA, Aman J (2011) A new approach based on honeybee to improve intrusion detection system using neural network and bees algorithm. In: Software engineering and computer systems, communications in computer and information science, vol 181, pp 777–792
• 6. Ghorbani MA, Aalami MT, Naghipour N (2017) Use of artificial neural networks for electrical conductivity modeling in Asi River. Appl Water Sci 7:1761–1772
• 7. Graf R, Zhu S, Sivakumar B (2019) Forecasting river water temperature time series using a wavelet-neural network hybrid modelling approach. J Hydrol 578:124115
• 8. Gupta MM, Jin L, Homma N (2003) Static and dynamic neural networks fundamentals to advanced theory. Wiley, Hoboken
• 9. Hamed MM, Khalafallah MG, Hassanien EA (2004) Prediction of wastewater treatment plant performance using artificial neural networks. Environ Model Softw 19:919–928
• 10. Haykin S (1999) Neural networks. A comprehensive foundation, 2nd edn. Prentice-Hall, New Jersey
• 11. Henri T (1961) Economic forecast and policy. North Holland, Amsterdam
• 12. Mahanta J (2017) https://towardsdatascience.com/introduction-to-neural-networks-advantages-and-applications-96851bd1a207?gi=5d46d27597eb9, (09.04.2019)
• 13. Niu F, Recht B, Christopher R, Wright SJ (2011) Hogwild: a lock-free approach to parallelizing stochastic gradient descent, 1–22
• 14. Karaboğa D, Öztürk C (2009) Neural networks training by artificial bee colony algorithm on pattern classification. Neural Netw World 19:279–292
• 15. Keskin TE (2010) Nitrate and heavy metal pollution resulting from agricultural activity: a case study from Eskipazar (Karabuk, Turkey). Environ Earth Sci 61:703–721
• 16. Keskin TE (2013) Mineral-water interaction and hydrogeochemistry of groundwater around Bartın coal mine, Turkey. Fresenius Environ Bull 22:2750–2762
• 17. Keskin TE, Toptaş S (2012) Heavy metal pollution in the surrounding ore deposits and mining activity: a case study from Koyulhisar (Sivas-Turkey). Environ Earth Sci 67:859–866
• 18. Keskin TE, Düğenci M, Kaçaroğlu F (2015) Prediction of water pollution sources using artificial neural networks in the study areas of Sivas, Karabu¨k and Bartın (Turkey). Environ Earth Sci 73:5333–5347
• 19. Luo W, Zhu S, Wu S, Dai J (2019) Comparing artificial intelligence techniques for chlorophyll-a prediction in US lakes. Environ Sci Pollut Res 26(29):30524–30532
• 20. Memon NA, Unar MA, Ansarı AK, Khaskheli GB, Memon BA (2008) Predictive potentiality of artificial neural networks for predicting the electrical conductivity (EC) of drinking water of Hyderabad city. In: 12th WSEAS international conference on computers, Heraklion, Greece, July 23–25, pp 487–490
• 21. Memon NA, Unar MA, Mastorakis NE, Khaskheli GB (2009) Total dissolved solids (TDS) modeling by artificial neural networks in the distribution system of drinking water of Hyderabad city. In: Proceedings of the 13th WSEAS International conference on computers, Rodos, Greece, 23–25 July, pp 607–611
• 22. Naeamikhah N, Nasrabadi T, Sirdari ZZ (2017) Role of different parameters in the quantification of generated sludge in the oxylator unit of water-treatment plants, using artificial neural network model (case study of jalalieh water treatment plant, Tehran, Iran). Appl Ecol Environ Res 15:129–142
• 23. Nemati S, Naghipour L (2014) Artificial neural network modeling of total dissolved solid in the Simineh River Iran. J Civil Eng Urbanism 4:08–13
• 24. Nelles O (2001) Nonlinear system identification. Classical approaches to neural networks and fuzzy models. Springer, Berlin
• 25. Özler E (2016) Küre (Kastamonu) Pb-Zn-Cu Maden Alanı Çevresinin Hidrojeokimyasal Özelliklerinin ve Su-Kayaç Etkileşiminin İncelemesi. M.Sc. Thesis, (Advisor: Assoc. Prof. Dr. Tülay EKEMEN KESKİN). Graduate School of Natural and Applied Sciences, Karabük University, Karabük, Turkey
• 26. Zhou Z, Wang H, Lou P (2010) Manufacturing Intelligence for Industrial Engineering: Methods for System Self-Organization, Learning, and Adaptation, IGI Global, ISBN 978-1-60566-864-2, United States of America
• 27. Zhu S, Heddam S, Nyarko EK, Nyarko MH, Piccolroaz S, Wu S (2019) Modeling daily water temperature for rivers: comparison between adaptive neuro-fuzzy inference systems and artificial neural networks models. Environ Sci Pollut Res 26(1):402–420

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021)