Original scientific paper

https://doi.org/10.15255/KUI.2019.004

Prediction of Climatic Parameters from Physicochemical Parameters using Artificial Neural Networks: Case Study of Ain Defla (Algeria)

Lamia Gheraba ; Laboratoire de Biomatériaux et Phénomènes de Transport (LBMPT), Université de Médéa, Pôle urbain, 26 000, MEDEA, Algeria
Latifa Khaouane ; Laboratoire de Biomatériaux et Phénomènes de Transport (LBMPT), Université de Médéa, Pôle urbain, 26 000, MEDEA, Algeria
Othmane Benkortbi orcid.org/0000-0002-1965-7171 ; Laboratoire de Biomatériaux et Phénomènes de Transport (LBMPT), Université de Médéa, Pôle urbain, 26 000, MEDEA, Algeria
Salah Hanini ; Laboratoire de Biomatériaux et Phénomènes de Transport (LBMPT), Université de Médéa, Pôle urbain, 26 000, MEDEA, Algeria
Mabrouk Hamadache ; Laboratoire de Biomatériaux et Phénomènes de Transport (LBMPT), Université de Médéa, Pôle urbain, 26 000, MEDEA, Algeria

Abstract

The knowledge of the climate of a region is a primordial task in that it allows predictions of climatic parameters in the future. In this study, monthly maximum and minimum air temperature (T_air,min, T_air,max), relative humidity (RH), and sunshine duration (SD) were modelled by multiple linear regression (MLR), and multilayer perceptron methods (MLP). For the four climatic parameters, the internal and external validations of MLP-ANN model showed high R2 and Q2 values in the range 0.81–0.98. The agreement between calculated and experimental values confirmed the ability of ANN-based equation to predict these parameters quickly and at lower cost.


This work is licensed under a Creative Commons Attribution 4.0 International License.

Keywords

climatic parameters; neural network; modelling; physicochemical parameters

Hrčak ID:

222488

URI

https://hrcak.srce.hr/222488

Publication date:

30.7.2019.

Article data in other languages: croatian

Visits: 1.488 *