Machine learning for satellite-based sea-state prediction in an offshore windfarm

Tapoglou, Evdokia; Forster, Rodney M.; Dorrell, R. M.; Parsons, D.

doi:10.1016/j.oceaneng.2021.109280

Cited by 10 publications

(8 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, further work is needed to use ANN's to integrate long-time series of SAR data and develop computationally efficient sea-state models below the resolution of numerical forecasts. Such nested models balance the need for fine-scale spatial resolution, accuracy, and forward temporal forecasting needed to optimize operations and maintenance, reducing the LCOE in offshore wind energy sector Tapoglou and Dorrell (2020).…”

Section: Satellite Data For Wave Forecastingmentioning

confidence: 99%

Satellite data for the offshore renewable energy sector: synergies and innovation opportunities

Medina-Lopez,

McMillan,

Lazic

et al. 2021

Preprint

View full text Add to dashboard Cite

Can satellite data be used to address challenges currently faced by the Offshore Renewable Energy (ORE) sector? What benefit can satellite observations bring to resource assessment and maintenance of ORE farms? Can satellite observations be used to assess the environmental impact of offshore renewables leading towards a more sustainable ORE sector? This review paper faces these questions presenting a holistic view of the current interactions between satellite and ORE sectors, and future needs to make this partnerships grow. The aim of the work is to start the conversation between these sectors by establishing a common ground. We present offshore needs and satellite technology limitations, as well as potential opportunities and areas of growth. To better understand this, the reader is guided through the history, current developments, challenges and future of offshore wind, tidal and wave energy technologies. Then, an overview on satellite observations for ocean applications is given, covering types of instruments and how they are used to provide different metocean variables, satellite performance, and data processing and integration. Past, present and future satellite missions are also discussed. Finally, the paper focuses on innovation opportunities and the potential of synergies between the ORE and satellite sectors. Specifically, we pay attention to improvements that satellite observations could bring to standard measurement techniques: assessing uncertainty, wind, tidal and wave conditions forecast, as well as environmental monitoring from space. Satellite-enabled measurement of ocean physical processes and applications for fisheries, mammals and birds, and habitat change, are also discussed in depth.

show abstract

Section: Satellite Data For Wave Forecastingmentioning

confidence: 99%

Satellite data for the offshore renewable energy sector: synergies and innovation opportunities

Medina-Lopez,

McMillan,

Lazic

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In oceanography and Earth sciences, ML has a diverse range of real-time applications. The primary applications of machine learning in oceanography include ocean weather and climate prediction, wave modeling, SWH, and wind speed predictions in regular sea state conditions [29,30] and in complex sea state conditions [29,31,32]. For instance, the study in [29] developed an ensemble of neural networks for the prediction of significant wave height from satellite images in an offshore region of a wind farm.…”

Section: Introductionmentioning

confidence: 99%

“…The primary applications of machine learning in oceanography include ocean weather and climate prediction, wave modeling, SWH, and wind speed predictions in regular sea state conditions [29,30] and in complex sea state conditions [29,31,32]. For instance, the study in [29] developed an ensemble of neural networks for the prediction of significant wave height from satellite images in an offshore region of a wind farm. The study by Stefanakos [31] integrated the Fuzzy Inference System with the Adaptive Network-based Fuzzy Inference System to predict wind and SWH parameters from a nonstationary wave parameters time series.…”

Section: Introductionmentioning

confidence: 99%

“…Studies in the literature used other dataset types for predicting SWH. The majority of studies used buoy measurements for modeling SWH [32,36,37], while some recent studies used satellite imagery and extracted image features and used them for SWH prediction [12,14,29]. Only few papers have utilized altimeter data features for SWH forecasting [35].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep-Learning-Based Feature Extraction Approach for Significant Wave Height Prediction in SAR Mode Altimeter Data

2022

View full text Add to dashboard Cite

Predicting sea wave parameters such as significant wave height (SWH) has recently been identified as a critical requirement for maritime security and economy. Earth observation satellite missions have resulted in a massive rise in marine data volume and dimensionality. Deep learning technologies have proven their capabilities to process large amounts of data, draw useful insights, and assist in environmental decision making. In this study, a new deep-learning-based hybrid feature selection approach is proposed for SWH prediction using satellite Synthetic Aperture Radar (SAR) mode altimeter data. The introduced approach integrates the power of autoencoder deep neural networks in mapping input features into representative latent-space features with the feature selection power of the principal component analysis (PCA) algorithm to create significant features from altimeter observations. Several hybrid feature sets were generated using the proposed approach and utilized for modeling SWH using Gaussian Process Regression (GPR) and Neural Network Regression (NNR). SAR mode altimeter data from the Sentinel-3A mission calibrated by in situ buoy data was used for training and evaluating the SWH models. The significance of the autoencoder-based feature sets in improving the prediction performance of SWH models is investigated against original, traditionally selected, and hybrid features. The autoencoder–PCA hybrid feature set generated by the proposed approach recorded the lowest average RMSE values of 0.11069 for GPR models, which outperforms the state-of-the-art results. The findings of this study reveal the superiority of the autoencoder deep learning network in generating latent features that aid in improving the prediction performance of SWH models over traditional feature extraction methods.

show abstract

“…The convolutional neural network was applied to Sentinel-1 image in VV polarization for SWH estimation by Xue et al [28] . Evdokia et al [29] predicted sea-state in an offshore wind farm based on machine learning techniques. Gao et al [31] established the SWH retrieval model based on the support vector machine in an ASAR WM.…”

Section: Introductionmentioning

confidence: 99%

Wave Height Estimation and Validation Based on the UFS Mode Data of Gaofen-3 in South China Sea

Cui

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The ultrafine strip (UFS) of the Gaofen-3 (GF-3) satellite provides extensive ocean wave details due to the high spatial resolution of 3 m. In this article, a new empirical model is developed to estimate wave height from GF-3 UFS mode data in South China Sea (SCS). Traditional methods either have more input parameters or complex forms or complex transformations, and most of them depend on the visible wave pattern. The model has the advantages of fewer input parameters and unnecessary visual wave patterns. The wave height estimation model is developed based on the collated data pairs between GF-3 UFS data in horizontal-horizontal polarization and the ERA5 reanalysis dataset from 2018 to 2021. The datasets are randomly divided into two groups. One group (about 80%) is used to develop the empirical relation; the other group (about 20%) and some altimeter data are used for significant wave height (SWH) verification. The comparison of the model data with the remaining ERA5 (ECMWF Reanalysis v5) data and the altimeter shows that the root-mean-square error is 0.41 and 0.47 m, the scatter index is 29.24% and 29.79%, and the correlation coefficient is 0.90 and 0.82, respectively. These statistical indices suggest that the developed model is suitable for SWH retrievals. So, the study results indicate that the GF-3 UFS mode data provide valuable information about wave conditions in the SCS.

show abstract

Machine learning for satellite-based sea-state prediction in an offshore windfarm

Cited by 10 publications

References 41 publications

Satellite data for the offshore renewable energy sector: synergies and innovation opportunities

Satellite data for the offshore renewable energy sector: synergies and innovation opportunities

Deep-Learning-Based Feature Extraction Approach for Significant Wave Height Prediction in SAR Mode Altimeter Data

Wave Height Estimation and Validation Based on the UFS Mode Data of Gaofen-3 in South China Sea

Contact Info

Product

Resources

About