Phase-resolved real-time ocean wave prediction with quantified uncertainty based on variational Bayesian machine learning

Zhang, Jincheng; Zhao, Xiaowei; Jin, Siya; Greaves, Deborah

doi:10.1016/j.apenergy.2022.119711

Cited by 33 publications

(7 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In ref. [79], the wave energy is predicted using Bayesian machine learning. The prediction error of this machine for short-term wave prediction is up to 55.4%, which is 11.7% less than linear wave theory and certain machine learning methods.…”

Section: Tidal Energymentioning

confidence: 99%

Towards the application of renewable energy technologies in green ports: Technical and economic perspectives

Parhamfar,

Sadeghkhani,

Adeli

2023

IET Renewable Power Gen

View full text Add to dashboard Cite

With growing concerns over environmental degradation and climate change, the shipping industry is under increasing pressure to reduce its environmental impact. This has led to the development of green port initiatives in the field of maritime transport and logistics, which aim to promote sustainable practices and reduce the environmental footprint of ports and their operations. One of the key strategies for achieving this goal is the use of renewable energy technologies (RETs). This paper summarizes the potentials, challenges, and economic analysis of RETs applications in green ports, emphasizing those that require aquatic environments for operation, including floating photovoltaic systems, offshore wind turbines, and ocean energy. The paper investigates the concept of green ports and explores the feasibility of integrating RETs into these facilities. Also, the potential of the various RETs is presented in terms of technical and economic aspects and installed capacity. Additionally, due to high flexibility in electrical systems and compatibility with maritime transportation, the use of fuel cells in green ports has been discussed as a feasible solution for supplying power to ports (either as the primary or backup source). The findings of this study show that RETs can significantly contribute to achieving sustainable goals in the maritime industry and pave the way for the creation of more efficient and environmentally friendly ports.

show abstract

Section: Tidal Energymentioning

confidence: 99%

Towards the application of renewable energy technologies in green ports: Technical and economic perspectives

Parhamfar,

Sadeghkhani,

Adeli

2023

IET Renewable Power Gen

View full text Add to dashboard Cite

show abstract

“…However, in contrast to the flow over solid surfaces, the applications of ML approaches to air-sea interactions have been quite limited and mainly focused on predicting wave characteristics (e.g. O'Donncha et al 2018O'Donncha et al , 2019Rasp & Lerch 2018;Sun et al 2022;Zhang et al 2022;Dakar et al 2023;Lou et al 2023;Xu, Zhang & Shi 2023). The existing works have employed different ML frameworks to reduce the computational complexity in estimating statistical wave conditions, such as significant wave height and peak wave period, and in low-dimensional learning of wave propagation (e.g.…”

Section: Introductionmentioning

confidence: 99%

“…In previous research, limited efforts have been made to reconstruct the turbulent flow above/below surface waves based only on wave observations (e.g. Smeltzer et al 2019;Gakhar, Koseff & Ouellette 2020;Xuan & Shen 2023;Zhang et al 2023). Using convolutional neural network (CNN) classifiers, Gakhar et al (2020) demonstrated that surface elevation information alone can be used to determine the physical features at the bottom boundary (see also Mandel et al 2017;Gakhar, Koseff & Ouellette 2022).…”

Section: Introductionmentioning

confidence: 99%

A machine learning model for reconstructing skin-friction drag over ocean surface waves

Yousefi,

Hora,

Yang

et al. 2024

J. Fluid Mech.

View full text Add to dashboard Cite

In order to improve the predictive abilities of weather and climate models, it is essential to understand the behaviour of wind stress at the ocean surface. Wind stress is contingent on small-scale interfacial dynamics typically not directly resolved in numerical models. Although skin friction contributes considerably to the total stress up to moderate wind speeds, it is notoriously challenging to measure and predict using physics-based approaches. This work proposes a supervised machine learning (ML) model that estimates the spatial distribution of the skin-friction drag over wind waves using solely wave elevation and wave age, which are relatively easy to acquire. The input–output pairs are high-resolution wave profiles and their corresponding surface viscous stresses collected from laboratory experiments. The ML model is built upon a convolutional neural network architecture that incorporates the Mish nonlinearity as its activation function. Results show that the model can accurately predict the overall distribution of viscous stresses; it captures the peak of viscous stress at/near the crest and its dramatic drop to almost null just past the crest in cases of intermittent airflow separation. The predicted area-aggregate skin friction is also in excellent agreement with the corresponding measurements. The proposed method offers a practical pathway for estimating both local and area-aggregate skin friction and can be easily integrated into existing numerical models for the study of air–sea interactions.

show abstract

“…In the absence of accurate physics-based sea-surface drag models [40,41], machine learning (ML) approaches may offer a practical alternative. Nonetheless, despite various applications of ML methods in the field of fluid mechanics and turbulence research [42][43][44][45], their utilization in air-sea interaction studies has been predominantly focused on estimating statistical wave characteristics such as significant wave height and peak wave period [46][47][48][49][50][51]. Yet, the feasibility of using ML techniques to reconstruct the turbulent flow over/below surface waves requires to be explored in more detail.…”

Section: Introductionmentioning

confidence: 99%

Data-driven met-ocean model for offshore wind energy applications

Yousefi,

Hora,

Yang

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In recent years, the global transition towards green energy, driven by environmental concerns and increasing electricity demands, has remarkably reshaped the energy landscape. The transformative potential of marine wind energy is particularly critical in securing a sustainable energy future. To achieve this objective, it is essential to have an accurate understanding of wind dynamics and their interactions with ocean waves for the proper design and operation of offshore wind turbines (OWTs). The accuracy of met-ocean models depends critically on their ability to correctly capture sea-surface drag over the multiscale ocean surface—a quantity typically not directly resolved in numerical models and challenging to acquire using either field or laboratory measurements. Although skin friction drag contributes considerably to the total wind stress, especially at moderate wind speeds, it is notoriously challenging to predict using physics-based approaches. The current work introduces a novel approach based on a convolutional neural network (CNN) model to predict the spatial distributions of skin friction drag over wind-generated surface waves using wave profiles, local wave slopes, local wave phases, and the scaled wind speed. The CNN model is trained using a set of high-resolution laboratory measurements of air-side velocity fields and their respective surface viscous stresses obtained over a range of wind-wave conditions. The results demonstrate the capability of our model to accurately estimate both the instantaneous and area-aggregate viscous stresses for unseen wind-wave regimes. The proposed CNN-based wall-layer model offers a viable pathway for estimating the local and averaged skin friction drag in met-ocean simulations.

show abstract

Phase-resolved real-time ocean wave prediction with quantified uncertainty based on variational Bayesian machine learning

Cited by 33 publications

References 50 publications

Towards the application of renewable energy technologies in green ports: Technical and economic perspectives

Towards the application of renewable energy technologies in green ports: Technical and economic perspectives

A machine learning model for reconstructing skin-friction drag over ocean surface waves

Data-driven met-ocean model for offshore wind energy applications

Contact Info

Product

Resources

About