Application of artificial intelligence to estimate phycocyanin pigment concentration using water quality data: a comparative study

Salim Heddam,Ozgur Kisi,Hadi Sanikhani

doi:10.1007/s13201-019-1044-3

Abstract

In the present investigation, the usefulness and capabilities of four artificial intelligence (AI) models, namely feedforward neural networks (FFNNs), gene expression programming (GEP), adaptive neuro-fuzzy inference system with grid partition (ANFIS-GP) and adaptive neuro-fuzzy inference system with subtractive clustering (ANFIS-SC), were investigated in an attempt to evaluate their predictive ability of the phycocyanin pigment concentration (PC) using data from two stations operated by the United States Geological Survey (USGS). Four water quality parameters, namely temperature, pH, specific conductance and dissolved oxygen, were utilized for PC concentration estimation. The four models were evaluated using root mean square errors (RMSEs), mean absolute errors (MAEs) and correlation coefficient (R). The results showed that the ANFIS-SC provided more accurate predictions in comparison with ANFIS-GP, GEP and FFNN for both stations. For USGS 06892350 station, the R, RMSE and MAE values in the test phase for ANFIS-SC were 0.955, 0.205 μg/L and 0.148 μg/L, respectively. Similarly, for USGS 14211720 station, the R, RMSE and MAE values in the test phase for ANFIS-SC, respectively, were 0.950, 0.050 μg/L and 0.031 μg/L. Also, using several combinations of the input variables, the results showed that the ANFIS-SC having only temperature and pH as inputs provided good accuracy, with R, RMSE and MAE values in the test phase, respectively, equal to 0.917, 0.275 μg/L and 0.200 μg/L for USGS 06892350 station. This study proved that artificial intelligence models are good and powerful tools for predicting PC concentration using only water quality variables as predictors.

Highlights

Nowadays, cyanobacterial harmful algal bloom (HAB) has become a serious problem, contributes seriously to the degradation of the drinking water quality and affects human health and the aquatic life with long-lasting effects (Sivapragasam et al 2010), including bad odors and tastes, reduction in water clarity and oxygen depletion during bloom decay (Sharaf et al 2019)
Monitoring cyanobacteria known as blue–green algae (CBG) is of great importance for freshwater ecosystems; it has been very difficult over the years to ensure effective and adequate monitoring of cyanobacteria in freshwater (Backer 2002)
We develop and apply four models, namely (i) feedforward neural networks (FFNNs), (ii) gene expression programming (GEP), (iii) adaptive neuro-fuzzy inference system with grid partition (ANFISGP) and (vi) adaptive neuro-fuzzy inference system with subtractive clustering (ANFIS-specific conductance (SC)), for predicting pigment concentration (PC)

Summary

Introduction

Cyanobacterial harmful algal bloom (HAB) has become a serious problem, contributes seriously to the degradation of the drinking water quality and affects human health and the aquatic life with long-lasting effects (Sivapragasam et al 2010), including bad odors and tastes, reduction in water clarity and oxygen depletion (hypoxia or anoxia) during bloom decay (Sharaf et al 2019). Simis et al (2005) introduced a basic optical model-based reflectance band ratio algorithm, for modeling PC of highly eutrophic Loosdrecht and Ijsselmeer lakes, Netherlands They have used band settings of the MEdium Resolution Imaging Spectrometer (MERIS), and they have found a very high coefficient of determination (R2) equal to 0.94 between measured PC and predicted PC by the proposed algorithm, with measured specific absorption coefficients at 620 nm called apc*(620). We develop and apply four models, namely (i) feedforward neural networks (FFNNs), (ii) gene expression programming (GEP), (iii) adaptive neuro-fuzzy inference system with grid partition (ANFISGP) and (vi) adaptive neuro-fuzzy inference system with subtractive clustering (ANFIS-SC), for predicting PC using data from two stations operated by the United States Geological Survey (USGS)

Materials and methods

Findings

Conclusions