Convolutional LSTM networks for seawater temperature prediction

  • Jun Liu
  • , Tong Zhang
  • , Yu Gou
  • , Xiaoyu Wang
  • , Bo Li
  • , Wenxue Guan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The seawater temperature has the characteristics of both spatial and temporal. To better predict seawater temperature, we propose a convolutional long short-term memory recurrent neural network method based on thermohaline data. We use convolutional neural networks to extract features from the thermohaline data in near time domains to obtain corresponding values of these features. These features are input into the LSTM recurrent neural network for the temporal prediction of seawater temperature. The method was empirically evaluated and compared to the RNN methods considering only a single variable and the methods considering temperature and salinity. The results show that the Thermohaline Convolutional LSTM Model has significant advantages over other methods and can predict changes in seawater temperature more accurate at different depths.

Original languageEnglish
Title of host publicationICSIDP 2019 - IEEE International Conference on Signal, Information and Data Processing 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728123455
DOIs
StatePublished - Dec 2019
Externally publishedYes
Event2019 IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2019 - Chongqing, China
Duration: 11 Dec 201913 Dec 2019

Publication series

NameICSIDP 2019 - IEEE International Conference on Signal, Information and Data Processing 2019

Conference

Conference2019 IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2019
Country/TerritoryChina
CityChongqing
Period11/12/1913/12/19

Keywords

  • Convolutional Neural Network
  • Long short-term memory
  • seawater temperature prediction
  • ther-mohaline data
  • time series

Fingerprint

Dive into the research topics of 'Convolutional LSTM networks for seawater temperature prediction'. Together they form a unique fingerprint.

Cite this