Wave data prediction with optimized machine learning and deep learning techniques

Domala, Vamshikrishna; Lee, Wonhee; Kim, Tae-wan

doi:10.1093/jcde/qwac048

Cited by 15 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predicting complex dynamic patterns, such as random waves, may be more challenging due to the intricate and nonlinear relationships between different wave features. To improve accuracy and reliability for modeling complex wave dynamics, alternative neural network architectures, such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs), could be considered [51]. Developing accurate predictive capabilities would require access to extensive wave observation data [52].…”

Section: Mlp-regressor Modelmentioning

confidence: 99%

A Multi-Approach Analysis for Monitoring Wave Energy Driven by Coastal Extremes

Matar,

Abcha,

Abroug

et al. 2024

Water

View full text Add to dashboard Cite

This research investigates the behavior and frequency evolution of extreme waves in coastal areas through a combination of physical modeling, spectral analysis, and artificial intelligence (AI) techniques. Laboratory experiments were conducted in a wave flume, deploying various wave spectra, including JONSWAP (γ = 7), JONSWAP (γ = 3.3), and Pierson–Moskowitz, using the dispersive focusing technique, covering a broad range of wave amplitudes. Wave characteristics were monitored using fifty-one gauges at distances between 4 m and 14 m from the wave generator, employing power spectral density (PSD) analysis to investigate wave energy subtleties. A spectral approach of discrete wavelets identified frequency components. The energy of the dominant frequency components, d5 and d4, representing the peak frequency (fp = 0.75 Hz) and its first harmonic (2fp = 1.5 Hz), respectively, exhibited a significant decrease in energy, while others increased, revealing potential correlations with zones of higher energy dissipation. This study underscores the repeatable and precise nature of results, demonstrating the Multilayer Perceptron (MLP) machine learning algorithm’s accuracy in predicting the energy of frequency components. The finding emphasizes the importance of a multi-approach analysis for effectively monitoring energy in extreme coastal waves.

show abstract

Section: Mlp-regressor Modelmentioning

confidence: 99%

A Multi-Approach Analysis for Monitoring Wave Energy Driven by Coastal Extremes

Matar,

Abcha,

Abroug

et al. 2024

Water

View full text Add to dashboard Cite

show abstract

“…Here, five cross-validation tasks are used as the most popular [25], [32], [33]. First, different hyper-parameters for each algorithm within reasonable ranges are set up.…”

Section: Grid Serach With Corss-validation Strategymentioning

confidence: 99%

Machine Learning-Based Day-Ahead Prediction of Price-Setting Scheduled Energy in the Korean Electricity Trading Mechanism

2023

View full text Add to dashboard Cite

Power generation companies, which participate in the electricity trading mechanism, need to determine optimal capacity bidding strategy to maximize their operational profit in Korea. Since the Price-setting Power Generation Schedule determines the profit of power generators, it is important to predict Price-setting Scheduled Energy during the trading day before the bidding phase. We propose a methodology for predicting the Pricing-setting Scheduled Energy from the power exchange without optimizing it. Instead of simulating the planning process, machine learning algorithms are applied and compared in the process of predicting the Pricing-setting Scheduled Energy. The input variables consist of seasonal and price information including calendar, fuel cost, and system marginal price. Three categories of machine learning (ML) algorithms including single, bagging and boosting approaches are implemented and tested to compare their performances. The computational experiments show that ML algorithms with price variable are shown to be better in terms of the considered measures. In addition, boosting approach is more effective than single and bagging approaches.

show abstract

“…Machine learning (ML) is also a unique approach to predict wave heights. Various types of ML-based models can be utilized for real-time coastal and ocean environmental monitoring [17] and to improve the accuracy of wave height prediction and estimations [18,19].…”

Section: Introductionmentioning

confidence: 99%

Analyzing the effectiveness of MEMS sensor and IoT in predicting wave height using machine learning models

Mishra

Singh

Chaudhary

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Wave height is a critical consideration in the planning and execution of maritime projects. Wave height forecasting methods include numerical and machine learning techniques. The traditional process involves using numerical wave prediction models, which have great success but are highly complex as they re-quire adequate information on nonlinear wind–wave and wave-wave interactions such as wave ener-gy-balance equation. On the contrary, machine learning techniques can predict wave height without prior knowledge of the above-mentioned complex interactions. This research aims to predict wave height using Micro-electromechanical Systems (MEMS), Internet of Things (IoTs), and Machine Learning (ML) based approaches. A floating buoy is developed using MEMS inertial measurement unit and IoT microcontrol-ler. An experiment is conducted in which the developed buoy is subjected to different wave heights in real time. The change in 3-Axis acceleration and 3-Axis gyroscope signals are acquired in a computer via IoT. These signals are analyzed using Machine learning-based classification models to predict wave height accurately. The obtained validation accuracy of the machine learning models K-NN (K-Nearest Neighbor), SVM (Support Vector Machine), and the bagged tree is 0.9906, 0.9368, and 0.9887 respec-tively, which indicates that MEMS and IoT can be used to classify & predict wave heights in real-time accurately.

show abstract

Wave data prediction with optimized machine learning and deep learning techniques

Cited by 15 publications

References 23 publications

A Multi-Approach Analysis for Monitoring Wave Energy Driven by Coastal Extremes

A Multi-Approach Analysis for Monitoring Wave Energy Driven by Coastal Extremes

Machine Learning-Based Day-Ahead Prediction of Price-Setting Scheduled Energy in the Korean Electricity Trading Mechanism

Analyzing the effectiveness of MEMS sensor and IoT in predicting wave height using machine learning models

Contact Info

Product

Resources

About