Modelling Colored Dissolved Organic Matter (CDOM) using Neuro Fuzzy Technique: a Comparative Study.

 

 

 

 

HEDDAM Salim (1), LADLANI Ibtissem (2), HOUICHI Larbi (3), DJEMILI Lakhdar (4)

 (1)Maître de conférences (MCB), Faculté des Science, Département des Sciences Agronomiques, Université 20 Août 1955, SKIKDA, E-mail: Cette adresse e-mail est protégée contre les robots spammeurs. Vous devez activer le JavaScript pour la visualiser..  

(2)Doctorant(e) en Sciences,Université Badji Mokhtar Annaba, Faculté desSciences de l’Ingénieur, Département d’Hydraulique. E-mail: Cette adresse e-mail est protégée contre les robots spammeurs. Vous devez activer le JavaScript pour la visualiser.

(3)Maître de conférences (MCA). Institut d’Architecture de Génie Civil et d’Hydraulique, Université Hadj Lakhdar - Batna. E-mail: Cette adresse e-mail est protégée contre les robots spammeurs. Vous devez activer le JavaScript pour la visualiser.

(4)Maître de conférences (MCA), Université Badji Mokhtar Annaba, Faculté desSciences de l’Ingénieur, Département d’Hydraulique. E-mail: Cette adresse e-mail est protégée contre les robots spammeurs. Vous devez activer le JavaScript pour la visualiser.

 

 

 

AbstractColored dissolved organic matter (CDOM) is part of the dissolved organic matter (DOM), which can be mainly divided into two groups-natural organic matter (NOM) and anthropogenic organic matter. With two other components, chlorophyll and non-algal particles (NAP), CDOM plays an important role in determining photochemical characteristics of water in nature. The prediction of colored dissolved organic matter (CDOM) using artificial intelligence techniques (AI) has received little attention in the past few decades. In this study, colored dissolved organic matter (CDOM) was modelled using Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and multiple linear regression (MLR) models, as a function of Water temperature (TE), pH, specific conductance (SC) and turbidity (TU). Evaluation of the prediction accuracy of the models is based on the root mean square error (RMSE), mean absolute error (MAE), coefficient of correlation (CC) and Willmott's index of agreement (d).The results indicated that ANFIS can be applied successfully for prediction of colored dissolved organic matter (CDOM). In both models, 60 % of the data set was randomly assigned to the training set, 20 % to the validation set, and 20 % to the test set. The system proposed in this paper shows a novelty approach with regard to the usage of ANFIS models for colored dissolved organic matter (CDOM) concentration modelling.

 

Key-Words— Colored Dissolved Organic Matter, CDOM, ANFIS, MLR, modelling

 

I.     INTRODUCTION

 

Dissolved organic matter, DOM, in natural waters is one of the largest pools of organic carbon in the biosphere. The fraction absorbing light from 300 to 800 nm, Colored dissolved organic matter (CDOM), historically referred to as Gelbstoff, yellow substances or humic material is the primary absorber of sunlight [1]. Colored dissolved organic matter (CDOM) is defined as the light absorbing component of total dissolved organic matter (DOM) that absorbs light in the ultraviolet and visible range of the electromagnetic spectrum [2]. Thus, CDOM is a major determinant of the optical properties of natural waters and it directly affects both the availability and spectral quality of light [1]. Increased supply of CDOM by rivers will reduce the photic depth in the shelf regions in particular, resulting in continued light limitation even after sea ice retreat [3]. Studying the concentration and distribution of CDOM in aquatic ecosystems, particularly the estuarine and coastal regions, will greatly improve the understanding of the dynamics of dissolved organic carbon (DOC), terrestrial-oceanic carbon cycle, and the impact of anthropogenic activities on water quality [4]. Knowledge of CDOM distributions and dynamics, the processes controlling CDOM, and its influence on optical properties are limited by the methods currently used for measurement [5]. To date, routine methods used for determination of Colored Dissolved Organic Matter (CDOM) in natural waters include rapidly quantifying CDOM via remote sensing based method.

 

The objectives of this study were to predict river CDOM concentration as a function of water quality variables by using Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and multiple linear regression (MLR) models.

 

 

Télécharger l'article