Hybrid Technique to Improve the River Water Level Forecasting Using Artificial Neural Network‐Based Marine Predators Algorithm

Abstract

Water level (WL) forecasting has become a difficult undertaking due to spatiotemporal fluctuations in climatic factors and complex physical processes. This paper proposes a novel hybrid machine learning model based on an artificial neural network (ANN) and the Marine Predators algorithm (MPA) for modeling monthly water levels of the Tigris River in Al-Kut, Iraq. Data preprocessing techniques are employed to enhance data quality and determine the optimal input model. Historical data for water level and climatic factors data are utilized from 2011 to 2020 to build and assess the model. MPA-ANN algorithm’s performance is compared with recent constriction coefficient-based particle swarm optimization and chaotic gravitational search algorithm (CPSOCGSA-ANN) and slime mold algorithm (SMA-ANN) to reduce uncertainty and raise the prediction range. The finding demonstrated that singular spectrum analysis is a highly effective method to denoise time series. MPA-ANN outperformed CPSOCGSA-ANN and SMA-ANN algorithms based on different statistical criteria. The suggested novel methodology offers good results with scatter index (SI) = 0.0009 and coefficient of determination (R2 = 0.98).

Review of Recent Trends in the Hybridisation of Preprocessing-Based and Parameter Optimisation-Based Hybrid Models to Forecast Univariate Streamflow

“…This measure represents the average absolute error compared to the observed record. It is also known as the relative mean error [145,146].…”

Henry Hub monthly natural gas price forecasting using CEEMDAN–Bagging–HHO–SVR

“…The forecasting performance of SVR is mainly affected by C and gamma (Ngo N et al, 2022), so we used optimization algorithms to optimize these two parameters. Based on previous literature and the performance of the three optimization algorithms in this paper, for fairness, we have the same settings for all three algorithms (Lu et al, 2022;Mohammed S et al, 2022;Sharma and Shekhawat et al, 2022;Su X et al, 2022): iterations: 30; population: 20; and lower and upper bound [0.1,1]. In the Bagging algorithm, the main factors that affect its performance include base learners and data samples (Mohammed and Kora et al, 2023).…”

Long Short-Term Memory Optimization Using Hybrid Sparrow Search Algorithm and Particle Swarm Optimization in Prediction of Water Level at Sluice Gates

“…Previous research on predicting water level using forecasting techniques using the Long Short-Term Memory algorithm was carried out by (Baek et al, 2020;Shuofeng et al, 2021;Kardhana et al, 2022;Kusudo et al, 2022;Noor et al, 2022). Other research uses the Artificial Neural Network algorithm (Kartini et al, 2021;Mohammed et al, 2022;Jayathilake et al, 2023). Apart from that, there are also those that use the GRA-NARX Neural Network algorithm (Liu et al, 2022), Multilayer Perceptron Neural Network, Elman Neural Network (Deng et al, 2022) and Transformer Neural Network (Xu et al, 2023).…”