Prediction of Sea Surface Temperature in the East China Sea Based on LSTM Neural Network

Abstract

Sea surface temperature (SST) is an important physical factor in the interaction between the ocean and the atmosphere. Accurate monitoring and prediction of the temporal and spatial distribution of SST are of great significance in dealing with climate change, disaster prevention, disaster reduction, and marine ecological protection. This study establishes a prediction model of sea surface temperature for the next five days in the East China Sea using long-term and short-term memory neural networks (LSTM). It investigates the influence of different parameters on prediction accuracy. The sensitivity experiment results show that, based on the same training data, the length of the input data of the LSTM model can improve the model’s prediction performance to a certain extent. However, no obvious positive correlation is observed between the increase in the input data length and the improvement of the model’s prediction accuracy. On the contrary, the LSTM model’s performance decreases with the prediction length increase. Furthermore, the single-point prediction results of the LSTM model for the estuary of the Yangtze River, Kuroshio, and the Pacific Ocean are accurate. In particular, the prediction results of the point in the Pacific Ocean are the most accurate at the selected four points, with an RMSE of 0.0698 °C and an R2 of 99.95%. At the same time, the model in the Pacific region is migrated to the East China Sea. The model was found to have good mobility and can well represent the long-term and seasonal trends of SST in the East China Sea.

Meta-Analysis of Satellite Observations for United Nations Sustainable Development Goals: Exploring the Potential of Machine Learning for Water Quality Monitoring

“…Among the popular advanced networks for feed-forward neural networks (FNNs) are the MLP [31,40,161,162,238,240,245,248], mixture density networks (MDNs) [21,28,251,268], extreme learning machine (ELM) [30], cascade forward neural network (CFNN) [30], radial basis function neural network (RBFNN) [242], and Bayesian neural networks (BNNs) [251]. Additionally, recurrent neural networks, such as LSTM, and GRU have also gained significant popularity in this field due to their ability to handle sequential data and capture temporal dependencies [22,42,48,194,249,266]. CNNs, such as the well-known convolutional neural network [43,194,220,257,260,262,264,265], the DINCAE [50,255,259], and generative adversarial neural networks (GANs) [277], may not have been widely used, but they have a significant advantage in dealing with spatial dependencies.…”

“…These architectures play a pivotal role in capturing both temporal dependencies and spatial relationships in the data, enabling accurate predictions and robust modeling of intricate regression tasks. Deep recurrent neural network architectures and their variants that are time-or sequence-dependent, such as gated recurrent units (GRUs), recurrent neural networks (RNNs), LSTM networks, and transformers, are specifically designed to handle sequential data where the current data point is dependent on previous ones and have performed exceptionally well in time-series analysis [22,42,48,194,249,266].…”

“…RNN is the most basic of these architectures, where the hidden state of the network is updated at each time step using the current input and the previous hidden state [194]. However, RNNs suffer from the vanishing and exploding gradient problem where the gradients become exponentially small or infinitely large during backpropagation, and this phenomenon results in model weights remaining constant during the training updates of long sequences [22,42,48,194,249,266]. LSTM and GRU are variant networks of the RNN which were designed to eliminate these problems.…”

Micro-Climate Computed Machine and Deep Learning Models for Prediction of Surface Water Temperature Using Satellite Data in Mundan Water Reservoir

“…The output vectors passing through the network between consecutive time steps t, t + 1 are denoted by h (t) . The forget gate, input gate, and output gate are the three gates that make up an LSTM network and are used to update and control the cell states [38][39][40][41][42]. The gates are customized by hyperbolic tangent and sigmoid activation functions.…”

Short-Term Prediction of Global Sea Surface Temperature Using Deep Learning Networks

“…In the past, the SST prediction was mainly focused on special sea areas, such as the coastal areas of China [42][43][44], the Indian Ocean [39,[45][46][47], and the Black Sea [48]. However, there are fewer studies on global SST prediction using deep learning networks.…”