Suspended sediment prediction using integrative soft computing models: on the analogy between the butterfly optimization and genetic algorithms

Abstract

The present study investigates the capability of two metaheuristic optimization approaches, namely the Butterfly Optimization Algorithm (BOA) and the Genetic Algorithm (GA), integrated with machine learning models in Suspended Sediment Load (SSL) prediction. The Adaptive Neuro-Fuzzy Inference System (ANFIS), Artificial Neural Network (ANN), and Multiple Linear Regression (MLR) are applied as the predictive data-driven models. Independent input variables, i.e., the water temperature (T), river discharge (Q), and specific conductance (SC) are used for the prediction of SSL based on several statistical indices. The results indicate that the performances of all studied models were close to one another; moreover, the metaheuristic algorithms were found to increase the accuracy of the ANFIS and ANN models for approximately 11.73 percent and 4.30 percent, respectively. In general, the BOA outperformed the GA in enhancing the optimization performance of the learning process in the applied machine learning models.

Keywords:

• Data mining
• butterfly optimization algorithm
• neural computing
• suspended sediment load

Acknowledgments

All data used in this study were obtained from the U.S. Geological Survey (USGS) Web server. The authors wish to great acknowledge the staff of the USGS web server who are associated with data of USGS web sites.

Disclosure statement

The authors have declared no conflict of interest.