Up to journal
for Research & Developement
Journal of Materials Science: Materials in Electronics
Impact Factor
2000 - 2020
Open Access

Iranian Water Researches Journal
Evaluation of river bio-resilience with artificial intelligence models(case study: Aliabad river)

 submission: 07/08/2019 | acception: 05/01/2020 | publication: 14/09/2020


naghmeh jafarzadeh1, s.ahmad mirbagheri firozabadi2*, taher rajaee3, afshin daneh kar4, maryam robati5

1-Science and Research Branch, Islamic Azad University,tehran،naghme.jafarzadeh@gmail.com

2-KN.Toosi,university tehran، mirbagheri@kntu.ac.ir

3-qom university، taher_rajaee@yahoo.com

4-tehran university،afdanehkar@gmail.com

5-Science and Research Branch, Islamic Azad University,tehran،maryamrobati1984@gmail.com



Abstract Introduction: The prediction of ecological resilience in water resources such as rivers is an important issue that needs to be considered for better management of land-use systems and water supplies. When the accessibility of a vital resource varies between the times of overabundance and extreme scarcity, management regimes must manifest flexibility and authority to adapt while maintaining legitimacy. The concept of resilience acknowledges the ability of societies to live and develop with dynamic environments. The ecological importance and reorganization features of algae, particularly as indicators of nutrient pollution, make them favorable as evaluation endpoints for Numeric nutrient criteria development water quality management aim under the Clean Water Act. But most environmental models do not address water quality in relation to river biology over time and offer little prediction for future periods.Time series modeling and forecasting has basic importance to various applied amplitude. Many important models have been proposed in the literature for improving the accuracy and the performance of the time series modeling and forecasting. In spite of various studies on intelligent modeling in the field of water management, no study has yet investigated the environmental resilience of the river in Iran using the time series and artificial intelligence models. Methods: The resilience indicators examined for rivers with four criteria - the biology, impact of pollutants, climate change, and time. The following criteria were investigated in accordance with the following factors: Diatom algae, chemical parameters, discharge variations, and ۱۰-year time series, The input data for modeling relations in the river ecosystem for Diatom were based on the factors influencing the physical and chemical parameters of this algae (EPA۲۰۱۷), and also on the basis of statistical methods of their correlation coefficients. Resilience index based on Diatoms population with regard to Diatomic-Trophic index was determined. In this respect, this study proposes a gene expression programming (GEP), hybrid wavelet-gene expression programming (WGEP), support vector machine(SVM) and wavelet support vector machine (WSVM) for prediction of monthly variations of Lavarak Station’s water quality that affect bio indicators. The ۱۰-years (۲۰۰۲-۲۰۱۲) monthly data used in this study were measured from Jajrood river located in Tehran, Iran. At first, the measured discharge (Q) and other quality parameters that affect the bio indicators datasets are initially decomposed into several sub-series using discrete wavelet transform (DWT). Then, this new sub-series is then imposed on the (GEP) (SVM) models as input patterns to predict monthly bio indicator one month ahead. Results: The results of the new proposed WGEP and WSVM models are compared with SVM and GEP models. The performance of this model was evaluated using Nash-Sutcliffe efficiency t (NS), root mean square error (RMSE), and mean absolute error (MAE). A comparison between the four models shows the superiority of the hybrid models over the classic models. The achieved results even point to the superiority of a single SVM model over the GEP model. With regard to the studies conducted to determine bio-resiliency index, the abundance of Diatom algae in the river within the standard of resilience the WSVM hybrid model was better while the WGEP was the second best. But due to the modeling process and the results, the WGEP model is used to determine the formula and the effect of each parameter is defined in the scenario. It can also be effective in expressing changes in one or more independent parameters. The results of this study showed that, considering the capacity and the ability of AI models to deal with the nonlinear nature and dynamics of hydrological processes, the ability of wavelet analysis to extract certain periods of a time series has the potential for more and more reasonable prediction in Different environmental processes can be achieved.


Keywords: Gene Expression  Resiliency  Support Vector Machine  Wavelet  Bio indicator. 

Download fulltext PDF

It's not open access




  •  No announces available