Forecasting Significant Wave Height using RNN-LSTM Models

P, Martina Maria Pushpam; S, Felix Enigo V

doi:10.1109/iciccs48265.2020.9121040

Cited by 14 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RNN is deep learning that can deal with temporal sequences because RNN has an internal state (memory) that can store information from the current input to deal with future inputs recursively [239]. Due to the temporal nature of the sequence, RNN is suitable for handwriting recognition or speech recognition.…”

Section: ) Deep Learningmentioning

confidence: 99%

Machine Learning Methods in Smart Lighting Toward Achieving User Comfort: A Survey

et al. 2022

View full text Add to dashboard Cite

Smart lighting has become a universal smart product solution, with global revenues of up to US$5.9 billion by 2021. Six main factors drive the technology: light-emitting diode (LED) lighting, sensors, control, analytics, and intelligence. The Internet of things (IoT) concept with the end device, platform, and application layer plays an essential role in optimizing the advantages of LED lighting in the emergence of smart lighting. The ultimate aim of smart lighting research is to introduce low energy efficiency and high user comfort, where the latter is still in the infancy stage. This paper presents a systematic literature review (SLR) from a bird's eye view covering full-length research topics on smart lighting, including issues, implementation targets, technological solutions, and prospects. In addition to that, this paper also provides a detailed and extensive overview of emerging machine learning techniques as a key solution to overcome complex problems in smart lighting. A comprehensive review of improving user comfort is also presented, such as the methodology and taxonomy of activity recognition as a promising solution and user comfort metrics, including light utilization ratio, unmet comfort ratio, light to comfort ratio, power reduction rate, flickering perception, Kruithof's comfort curve, correlated color temperature, and relative mean square error. Finally, we discuss in-depth open issues and future challenges in increasing user comfort in smart lighting using activity recognition.

show abstract

Section: ) Deep Learningmentioning

confidence: 99%

Machine Learning Methods in Smart Lighting Toward Achieving User Comfort: A Survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Belonging to a class of artificial recurrent neural networks (RNNs), the long shortterm memory was specifically developed to deal with the vanishing gradient problem and is highly efficient at data time series analysis [23,39]. Particularly, LSTMs have an advantage over conventional feed-forward neural networks and other RNNs in that they can selectively remember patterns in data for long durations, and this is accomplished by a series of forget ( f t ), input (i t ), and output (o t ) gates, in addition to the sigmoid function (σ) and Hadamard ( ) product operator [40].…”

Section: The Long Short-term Memory Networkmentioning

confidence: 99%

“…For example, Ni and Ma [22] used LSTM and Principal Component Analysis (PCA)-identified parameters to predict wave height from four buoys in the polar westerlies. Pushpam and Enigo used LSTM trained on three years of buoy data to perform 3, 6, 12, and 24 h significant wave height predictions [23]. Fan et al also used LSTM in significant wave height predictions and additionally found that when SWAN was fed buoy-observed surface wind speed, the hybridized SWAN-LSTM model outperformed the single SWAN usage [24].…”

Section: Introductionmentioning

confidence: 99%

Bidirectional Modeling of Surface Winds and Significant Wave Heights in the Caribbean Sea

Bethel

Zhou

Cao

2021

JMSE

View full text Add to dashboard Cite

Though the ocean is sparsely populated by buoys that feature co-located instruments to measure surface winds and waves, their data is of vital importance. However, due to either minor instrumentation failure or maintenance, intermittency can be a problem for either variable. This paper attempts to mitigate the loss of valuable data from two opposite but equivalent perspectives: the conventional reconstruction of significant wave height (SWH) from Caribbean Sea buoy-observed surface wind speeds (WSP) and the inverse modeling of WSP from SWH using the long short-term memory (LSTM) network. In either direction, LSTM is strongly able to recreate either variable from its counterpart with the lowest correlation coefficient (r2) measured at 0.95, the highest root mean square error (RMSE) is 0.26 m/s for WSP, and 0.16 m for SWH. The highest mean absolute percentage errors (MAPE) for WSP and SWH are 1.22% and 5%, respectively. Additionally, in the event of complete instrument failure or the absence of a buoy in a specific area, the Simulating WAves Nearshore (SWAN) wave model is first validated and used to simulate mean and extreme SWH before, during, and after the passage of Hurricane Matthew (2016). Synthetic SWH is then fed to LSTM in a joint SWAN—LSTM model, and the corresponding WSP is reconstructed and compared with observations. Although the reconstruction is highly accurate (r2 > 0.9, RMSE < 1.3 m/s, MAPE < 0.8%), there remains great room for improvement in minimizing error and capturing high-frequency events.

show abstract

“…Shahabi [24] proposed a GMDH network to predict the SWH of north Atlantic coast based on the buoys data and achieved better results at the 6-step to 12-step period prediction than time-series and machine learning models. Pushpam [25] used the long-short-term memory (LSTM) network to reconstruct and predict the wave height of Bay of Bengal, which achieved better performance than the traditional forward ANNs and recursive neural networks (RNN). Kaloop [26] proposed a wavelet-particle-swarm optimization extreme learning machine (ELM) to estimate the ocean wave height, and the experiment results on buoys data of the US south-east coast outperformed SOS, LSTM, and SVR.…”

Section: Introductionmentioning

confidence: 99%

Wavelet-Based ResNet: A Deep-Learning Model for Prediction of Significant Wave Height

Liu

Sun

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Predicting significant wave height (SWH) is significant for coastal energy evaluation and utilization, port construction, and shipping planning. It has been reported that SWH is difficult to forecast for the complex marine conditions and chaos in nature. Current methods either require reliable prior information or reach the upper limit of prediction accuracy. To this end, this paper proposes a wavelet-based residual network to predict SWH with high accuracy. First, the time-series data of wave-related factors collected by the ocean buoy station is decomposed using the wavelet transformation. Then, the transformation results are used as the inputs to train the residual neural network. Finally, the data obtained from the NOAA's National Data Buoy Center is used to prove the outperformed prediction accuracy of the proposed method. The analysis results suggested that wavelet transformation can improve the prediction performance of the neural network, and the proposed model achieves better performance compared with several other deep neural network schemes.

show abstract

Forecasting Significant Wave Height using RNN-LSTM Models

Cited by 14 publications

References 8 publications

Machine Learning Methods in Smart Lighting Toward Achieving User Comfort: A Survey

Machine Learning Methods in Smart Lighting Toward Achieving User Comfort: A Survey

Bidirectional Modeling of Surface Winds and Significant Wave Heights in the Caribbean Sea

Wavelet-Based ResNet: A Deep-Learning Model for Prediction of Significant Wave Height

Contact Info

Product

Resources

About