Novel Uncertainty-Aware Deep Neuroevolution Algorithm to Quantify Tidal Forecasting

• Published in: IEEE transactions on industry applications 2022-05, Vol.58 (3), p.3324-3332
• Main Authors: Jalali, Seyed Mohammad Jafar, Ahmadian, Sajad, Noman, Md Kislu, Khosravi, Abbas, Islam, Syed Mohammed Shamsul, Wang, Fei, Catalao, Joaao P. S.
• Format: Article
• Language: English
• Subjects: Algorithms; Coastal zone; Datasets; Deep learning; Deep neuroevolution (DNE); Forecasting; Harmonic analysis; Machine learning; Mathematical models; Ocean currents; Oceans; Optimization; Prediction algorithms; Predictive models; tidal current forecasting; Tidal currents; Training; Uncertainty; uncertainty quantification; Upper bounds; Vessels; Water level fluctuations; Water levels
• ISSN: 0093-9994; 1939-9367
• DOI: 10.1109/TIA.2022.3162186

Tide refers to a phenomenon that causes the change of water level in oceans. Tidal level forecasting plays an important role in many real-world applications especially those related to oceanic and coastal areas. For instance, accurate forecasting of tidal level can significantly increase the vessels' safety as an excessive level of tidal makes serious problems in the movement of vessels. In this work, we propose a deep learning-based prediction interval framework in order to model the forecasting uncertainties of tidal current datasets. The proposed model develops optimum prediction intervals (PIs) focused on the deep learning-based CNN-LSTM model (CLSTM), and nonparametric approach termed as the lower upper bound estimation (LUBE) model. Moreover, we develop a novel deep neuroevolution algorithm based on a two-stage modification of the gaining-sharing knowledge optimization algorithm to optimize the architecture of the CLSTM automatically without the procedure of trial and error. This leads to a decline in the complexity raises in designing manually the deep learning architectures, as well as an enhancement in the performance of the PIs. We also utilize coverage width criterion to establish an excellent correlation appropriately between both the PI coverage probability and PI normalized average width. We indicate the searching efficiency and high accuracy of our proposed framework named as MGSK-CLSTM-LUBE by examining over the practical collected tidal current datasets from the Bay of Fundy, NS, Canada.