Application of Soft Computing for Time Series Water-Level Prediction in Jamuna River

Subodh Chandra Sarkar ； Abul Bashar ； Mohammad Sultan Mahmud ； Risul Islam Rasel

《International Journal of Systematic Innovation》 6卷6期 (2021/12) Pp. 13-21

https://doi.org/10.6977/IJoSI.202112_6(6).0003

摘要

Time series analysis is one of the essential and complicated research methods. It is a well-known fact that improving time series prediction accuracy is a vital yet challenging issue. Recently, soft computing has become popular in time series forecasting in various application areas. Soft computing is a fusion of research of evolutionary and genetic algorithms, neural networks, fuzzy set theory, and fuzzy systems and provides rapid dissemination of results. This study investigates a model for time series water-level prediction using soft computing techniques which is reliable and effective. To illustrate the applicability and capability of soft computing, the Jamuna river, Bangladesh, was used as a case study. We used four areas of the Jamuna river (i.e., Aricha, Bahdurabad, Shariacandi, and Sirajganj) water-level and rainfall events with daily data collected in the past 12 years. In experiments, past 2 to 4 days' time-series wa-ter-level with and without rainfall has been applied to predict 1 to 4 days ahead water-level. The experimental results demonstrated that the adaptive neurofuzzy inference system (ANFIS) performs superiorly to traditional methods, such as nonlinear autoregressive neural network with external input (NARX) and focused time-delay neural network (FTDNN).

關鍵字

Time series analysis ； soft-computing ； water-level prediction ； ANFIS ； NARX ； FTDNN