Weighted error-output recurrent Xavier echo state network for concept drift handling in water level prediction

Published: 01 Jan 2024, Last Modified: 20 May 2025Appl. Soft Comput. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Novel weight selection method enhances stability and accuracy.•Modified EDDM and AFF tackle concept drift, improving adaptability and training speed.•Unique error-output algorithm mitigates error accumulation in multi-step prediction.•Outperforms in long-term water level prediction, showcasing practicality.
Loading