newly optimized learning machine for assessing the uncertainties of water quality modeling by evolutionary algorithm

Water resources management is one of the crucial branches of civil engineering science. due to the increase in the world's population, the human requirement for pure drinking water has increased, which is why solving the challenges related to water with global warming is one of the necessities of civil engineers' research. at the same time, recent scientific methods are one of the best auxiliary tools to meet human needs. since we can describe many phenomena based on complex mathematical equations, analytical solving is almost impossible. therefore, using new methods with simplicity and accuracy is necessary for nonlinear relationship perception. one of these methods is artificial intelligence (ai). this research used the extreme learning machine (elm) model and genetic algorithm (ga) to create a new hybrid model genetic extreme learning machine (gaelm). ai and hybrid models were used to simulate and predict the water quality parameter changes. the study area in this work was the colorado river basin, located in the united states. the desired qualitative parameters were electrical conductivity (ec) and dissolved oxygen (do). finally, using seven approaches, the models' performance was compared. the results showed that the best simulation assigned to the gaelm(ec) model with indices rmse and r equal to 0.1304, and 0.9284, respectively.