Applicability of radial-based artificial neural networks (RBNN) on coliform calculation: A case of study


Creative Commons License

Aydın Er B., Şişman A., Ardalı Y.

Sigma Journal of Engineering and Natural Sciences, vol.40, no.4, pp.724-731, 2022 (ESCI) identifier

  • Publication Type: Article / Article
  • Volume: 40 Issue: 4
  • Publication Date: 2022
  • Doi Number: 10.14744/sigma.2022.00088
  • Journal Name: Sigma Journal of Engineering and Natural Sciences
  • Journal Indexes: Emerging Sources Citation Index (ESCI), Scopus, Academic Search Premier, Directory of Open Access Journals
  • Page Numbers: pp.724-731
  • Keywords: Artificial Neural Network, Black Sea, Colifor, Deep Sea Discharge
  • Ondokuz Mayıs University Affiliated: Yes

Abstract

Due to the increasing population, urbanization and economic reasons, it is inevitable to use deep-sea discharges. The fact that there is no alternative and less pollution of the environment is the reason for the preference of deep-sea discharges. In this study, it is aimed to estimate the coliform values of the Tekkekoy deep sea discharge system, which is chosen as an application area, by using a radial-based artificial neural network structure. Firstly, samples taken from the field were examined in a laboratory environment. Values obtained as a result of laboratory studies were used as input in Radial basis artificial neural network (RBNN) architecture. It has been determined that the models prepared by using various combinations have correlation values ranging from 91.5% to 97.2%. The best performing models were models prepared using 10 neurons. From these successful results, it was determined that RBNN structures are useful in coliform prediction.