# Prediction of Sea Surface Temperature using Long Short-Term Memory

## TL;DR

This paper introduces a novel application of LSTM neural networks for predicting sea surface temperature over one week and one month, demonstrating its effectiveness in modeling long-term dependencies in SST data.

## Contribution

First to apply recurrent neural networks, specifically LSTM, to sea surface temperature prediction, achieving accurate long-term forecasts and online updating capabilities.

## Key findings

- LSTM effectively models long-term SST dependencies.
- The proposed architecture achieves high prediction accuracy.
- Online updating enhances prediction performance.

## Abstract

This letter adopts long short-term memory(LSTM) to predict sea surface temperature(SST), which is the first attempt, to our knowledge, to use recurrent neural network to solve the problem of SST prediction, and to make one week and one month daily prediction. We formulate the SST prediction problem as a time series regression problem. LSTM is a special kind of recurrent neural network, which introduces gate mechanism into vanilla RNN to prevent the vanished or exploding gradient problem. It has strong ability to model the temporal relationship of time series data and can handle the long-term dependency problem well. The proposed network architecture is composed of two kinds of layers: LSTM layer and full-connected dense layer. LSTM layer is utilized to model the time series relationship. Full-connected layer is utilized to map the output of LSTM layer to a final prediction. We explore the optimal setting of this architecture by experiments and report the accuracy of coastal seas of China to confirm the effectiveness of the proposed method. In addition, we also show its online updated characteristics.