Using Artificial Intelligent to Model Predict the Biological Resilience With an Emphasis on Population of cyanobacteria in Jajrood River in The Eastern Tehran, Iran.

Abstract

Prediction of bio-resilience in water resources such as rivers is important for better management of land-use systems and water resources. This study has proposed the use of artificial intelligent (AI) models for assessing the relationship among the biological conditions in Jajrood River. For this purpose, the qualitative monthly data of the river related to 2008-2018 were applied. Different resilience indicators for preparation of scenarios were determined using the canonical correlation analysis (CCA) method. Appropriate time-series scenarios (5scenarios) were modelled via Gene Expression Programming (GEP) plus Support Vector Machine (SVM), the bio-indicators were predicted. In order to reduce the error, the wavelet hybrids (W-GEP and W-SVM) were also used for modelling. Validation of the models was performed using Nash-Sutcliffe efficiency (E), root mean square error (RMSE), and mean‏ absolute error (MAE). In all the models investigated, Scenario 3 and Scenario 4 had the highest and lowest accuracies as 0.98 and 0.33 in validation, respectively. The third scenario combined with NO3 -, BODt-1, BOD, PO3-, and Q provided the best results. Then, the values of 0.98, 0.94, 0.82, and 0.78 were obtained for its validation by WSVM, WGEP, SVM, and GEP models, respectively. These findings suggested the superiority of hybrid models and SVM over classical models and GEP in water quality assessment respectively. Examination of the scenarios revealed that NO3 - and DO had the highest and the lowest impact on Shannon index of Cyanophyceae algae over time, as a bio-indicator of water quality in the river, respectively.