Improved adaptive neuro-fuzzy inference system with bacterial foraging optimization algorithm for suspended sediment concentration estimation

Article type: Research Article

Authors: Li, Weidong^{a; b; *} | Fan, Jinsheng^{c; *} | Li, Zhenying^{a; b} | Wang, Chisheng^d | Zhang, Xuehai^{a; b} | Duan, Jinlong^{a; b}

Affiliations: [a] Key Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou, China | [b] Henan Key Laboratory of Grain Photoelectric Detection and Control, Henan University of Technology, Zhengzhou, China | [c] Yellow River Engineering Consulting Co., Ltd, Post-Doctoral Programme, Zhengzhou, China | [d] Key Laboratory for Geo-Environmental Monitoring of Great Bay Area, MNR, Shenzhen University, Shenzhen, China

Correspondence: [*] Corresponding authors. Weidong Li, Henan University of Technology, Zhengzhou, China. E-mail: wdli@haut.edu.cn. and Jinshen Fan, Yellow River Engineering Consulting Co., Zhengzhou, China. E-mail: fanjs@yrec.cn.

Abstract: The accuracy of predicting river-suspended sediment concentration (SSC) is crucial for evaluating the functional lifespan of reservoirs, analyzing river geomorphological evolution, and assessing riverbed stability. In this study, we aim to develop new models for SSC prediction at two hydrological stations near Puerto Rico, USA, by integrating the bacterial foraging optimization algorithm and adaptive neural fuzzy inference network (ANFIS). The models comprise ANFIS with grid partition (ANFIS-GP), ANFIS with subtractive clustering (ANFIS-SC), and ANFIS with fuzzy c-means clustering (ANFIS-FCM). Additionally, we employ an artificial neural network (ANN) and the sediment rating curve (SRC) for predicting daily series data of flow discharge-suspended sediment concentration (SSC). Different scenarios are considered based on varying input and output variables, leading to predictions for four distinct scenarios. At the Rio Valenciano Station, the MRSE values for ANFIS-BFO, ANFIS-FCM, ANFIS-GP, ANFIS-SC, ANN, and SRC are 2.2172, 2.5389, 2.6627, 2.7549, 2.7994, and 3.7882, respectively. For the Quebrada Blanca Station, the MRSE values for ANFIS-BFO, ANFIS-FCM, ANFIS-SC, ANFIS-GP, ANN, and SRC are 0.8295, 0.8664, 0.8964, 0.9110, 0.9684, and 1.6742, respectively. It can be inferred that ANFIS-BFO exhibits superior prediction results compared to all other models. Furthermore, ANFIS-SC and ANFIS-FCM demonstrate slightly better prediction performance than ANFIS-GP. In comparison to ANN, ANFIS-GP, ANFIS-SC, and ANFIS-FCM exhibit slightly superior prediction performance.

Keywords: ANFIS, ANN, bacterial foraging optimization algorithm, modeling, suspended sediment

DOI: 10.3233/JIFS-232277

Journal: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 2, pp. 3945-3961, 2024