An evaluation model of water quality based on DSA-ELM method

Abstract

The evaluation technology of water quality is of great significance for monitoring and management of surface water quality. In this paper, the Extreme Learning Machine algorithm was optimized with the Dolphin Swarm Algorithm. Optimal weight and threshold of Extreme Learning Machine algorithm was searched by the process of creating a virtual team and seeking the best position of Dolphin Swarm. Four parameters of Ph, dissolved oxygen(DO), Potassium permanganate index (CODMn) and ammonia-nitrogen(NH3-N) were chosen to evaluate the level of the water and the Extreme Learning Machine algorithm optimized by Dolphin Swarm Algorithm (DSA-ELM) was used as the evaluation model of the water quality. In this paper, the water quality of 18 monitoring sites of Huai river was evaluated by DSA-ELM and ELM method. Compared the ELM algorithm model, the DSA-ELM model has the advantage of high accuracy and good stability.