Investigating the Interrelationships between Hydro-Social Parameters in the Asian Continent Using Data Mining Methods

Water scarcity and subsequent social and economic crises have doubled the need to use new interdisciplinary knowledge-based approaches in reforming water resources management structures and policies and implementing water resources plans and projects. In the meantime, recognizing the interrelationships of the social sciences and their water resources systems has become a problem that its solution help us to correct existing dysfunctional structures. Therefore, the main purpose of this study is to prove the interrelationship of some social parameters and water resources on a continental scale with the use of software modeling tools. In this study, per capita data on renewable water resources and social parameters including the ratio of rural population to urban population, population density, number of Internet users and education index on an annual scale are considered. The statistical period of the data was 13 years (2005-2007) and this study was performed for 42 countries in Asia whose per capita water resources were declining. Then, using soft copmuting methods such as Artificial Neural Network (ANN), Decision Tree (M5) and Adaptive Fuzzy-neural Inference System (ANFIS), the interrelationship between per capita water resources and social parameters was modeled. Modeling results were evaluated by the criteria of determination coefficient (R2), root mean square error (RMSE) and mean absolute error (MAE) values. Finally, the results indicate the superior performance of ANFIS method compared to the other two models in evaluating the interaction of per capita water resources and social parameters. Also, after the ANFIS model, the M5 and ANN models had better performance, respectively.