TD-LSTM: Temporal Dependence-Based LSTM Networks for Marine Temperature Prediction

Li, Jun; Zhang, Tong; Han, Guangjie; Gou, Yu

doi:10.3390/s18113797

Cited by 61 publications

(30 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The discrete time series is a set of chronological observation values, temperature, salinity, dissolved oxygen, and daily precipitation are all time series of this kind [18].…”

Section: Problem Formulationmentioning

confidence: 99%

Unsteady Multi-Element Time Series Analysis and Prediction Based on Spatial-Temporal Attention and Error Forecast Fusion

Wang

2020

Future Internet

View full text Add to dashboard Cite

Harmful algal blooms (HABs) often cause great harm to fishery production and the safety of human lives. Therefore, the detection and prediction of HABs has become an important issue. Machine learning has been increasingly used to predict HABs at home and abroad. However, few of them can capture the sudden change of Chl-a in advance and handle the long-term dependencies appropriately. In order to address these challenges, the Long Short-Term Memory (LSTM) based spatial-temporal attentions model for Chlorophyll-a (Chl-a) concentration prediction is proposed, a model which can capture the correlation between various factors and Chl-a adaptively and catch dynamic temporal information from previous time intervals for making predictions. The model can also capture the stage of Chl-a when values soar as red tide breaks out in advance. Due to the instability of the current Chl-a concentration prediction model, the model is also applied to make a prediction about the forecast reliability, to have a basic understanding of the range and fluctuation of model errors and provide a reference to describe the range of marine disasters. The data used in the experiment is retrieved from Fujian Marine Forecasts Station from 2009 to 2011 and is combined into 8-dimension data. Results show that the proposed approach performs better than other Chl-a prediction algorithms (such as Attention LSTM and Seq2seq and back propagation). The result of error prediction also reveals that the error forecast method possesses established advantages for red tides prevention and control.

show abstract

“…The discrete time series is a set of chronological observation values, temperature, salinity, dissolved oxygen, and daily precipitation are all time series of this kind [18].…”

Section: Problem Formulationmentioning

confidence: 99%

Unsteady Multi-Element Time Series Analysis and Prediction Based on Spatial-Temporal Attention and Error Forecast Fusion

Wang

2020

Future Internet

View full text Add to dashboard Cite

show abstract

“…In order to accelerate the convergence of the objective function and make the gradient reach the global minimum more quickly, the Nadam algorithm is used to optimize the training process. The correction valueĝ t of gradient g t is introduced into the Nadam algorithm and compared with Adam at time t, and the gradientĝ t is defined by Formula (12). In addition, the updated gradient ∆θ t is calculated by Formula (13).…”

Section: Model Construction and Predictionmentioning

confidence: 99%

“…Xu et al [11] proposed a novel deep-learning-based indoor temperature prediction method for public buildings, which verified the prediction accuracy in the direction of indoor temperature change and its disadvantage in the horizontal direction. Liu et al [12] analyzed the time dependence of ocean temperatures at multiple depths and proposed a time-dependent ocean temperature prediction method, and the test results showed a better predictive performance than both support vector regression (SVR) and a multilayer perceptron regressor (MLPR). Wallschied et al [13] verified the feasibility of LSTM on temperature prediction.…”

Section: Introductionmentioning

confidence: 99%

The Temperature Prediction of Permanent Magnet Synchronous Machines Based on Proximal Policy Optimization

et al. 2020

View full text Add to dashboard Cite

Accurate temperature prediction plays an important role in the thermal protection of permanent magnet synchronous motors. A temperature prediction method of permanent magnet synchronous machines (PMSMs) based on proximal policy optimization is proposed. In the proposed method, the actor-critic framework of reinforcement learning is introduced to model the effective temperature prediction mechanism, and the correlations between the input features are then analyzed to select the appropriate input features. Finally, the simplified proximal policy optimization algorithm is introduced to optimize the value of the prediction temperature of PMSMs. Experimental results reveal the high accuracy and reliability of the proposed method compared with an exponential weighted moving average method (EWMA), a recurrent neural network (RNN), and long short-term memory (LSTM).

show abstract

“…The symbol ˖ represents the scalar product of the two vectors. The variable σg is the sigmoid function, and σh and σc are the hyperbolic tangent functions, respectively [13] [14]. Figure 2 illustrates diagrammatically how these equations work, where each rectangle represents a single LSTM cell and three σ denote three gates, respectively.…”

Section: A Lstm Networkmentioning

confidence: 99%

Integrated deep learning model for predicting electrical power generation from wave energy converter

Wang

2019

2019 25th International Conference on Automation and Computing (ICAC)

View full text Add to dashboard Cite

The continuous improvement of wave and tidal energy technologies has widely boosted the development of marine energy plants. An accurate predication of the electrical power generation of marine energy not only saves costs for operation and maintenance but also improves manage the electricity consumption and reduce the uncertainty due to the intermittency of the ocean wave and tidal resources. This paper presents an integrated deep learning (DL) network comprising the long short term memory (LSTM) algorithm and the principal component analysis (PCA) to predict the electrical power generation from a wave energy converter (WEC). The results from this integrated data-driven model show the remarkable performance compared with the LSTM alone and other machine learning models. Furthermore, the experiments have shown that the high-frequency oscillating waves and the long term features in the wave have a significant impact on the model's accuracy. This finding demonstrates the superiority of the proposed model in its ability to deal with time sequence data and the effect of the high-frequency oscillating signals on the results over other machine learning methods.

show abstract

TD-LSTM: Temporal Dependence-Based LSTM Networks for Marine Temperature Prediction

Cited by 61 publications

References 25 publications

Unsteady Multi-Element Time Series Analysis and Prediction Based on Spatial-Temporal Attention and Error Forecast Fusion

Unsteady Multi-Element Time Series Analysis and Prediction Based on Spatial-Temporal Attention and Error Forecast Fusion

The Temperature Prediction of Permanent Magnet Synchronous Machines Based on Proximal Policy Optimization

Integrated deep learning model for predicting electrical power generation from wave energy converter

Contact Info

Product

Resources

About