Skip to main content

IMIS

[ report an error in this record ] Print this page

Sea surface temperature data (1870-2021) used for deep learning related to ENSO prediction
Citation
Hu, C.; China University of Geosciences (CUG); (2023): Sea surface temperature data (1870-2021) used for deep learning related to ENSO prediction. https://marineinfo.org/doc/dataset/8167

Availability: CC0 To the extent possible under law, the person who associated CC0 with this dataset has waived all copyright and related or neighboring rights to this dataset.

Description
Sea surface temperature data in the Pacific Ocean between 1870 and 2021 used for deep learning for ENSO prediction. more

There are 4645 samples in CMIP data: 1 to 2265 samples are 15 historical simulation data by CMIP6 in 151 years (151 × 15 = 2265 in total), 2266 to 4645 samples are 17 historical simulation data by CMIP5 in 140 years (140 × 17 = 2380 in total). And the Simple Ocean Assimilation data (SODA) spans 100 years, where the first 80 years of SODA data are used for retraining and the last 20 years of SODA data are used for validation. The input predictors are used in the ENSO index prediction experiment with a spatial resolution of 5° (latitude) × 5 ° (longitude), and spatial range of 0°-360°E, 55°S-60°N. The data dimension includes (year, month, latitude, longitude). Monthly ocean surface temperature anomaly (SSTA) of the NINO 3 and NINO 4 regions (5S-5N and 160E-90W) is also used for ENSO types prediction, with a time span from 1870 to 2021.

Scope
Themes:
Physical > Hydrography (e.g. T,S) - near surface only
Keywords:
ENSO (El Niño-Southern Oscillation) · Ocean surface temperature · Pacific Ocean I. · Prediction

Temporal coverage
1 January 1870 - 31 December 2021
Not relevant

Parameter
Sea surface temperature

Contributor
China University of Geosciences (CUG), moredata creator

Dataset status: Completed
Data type: Data
Metadatarecord created: 2023-01-03
Information last updated: 2023-01-17
All data in the Integrated Marine Information System (IMIS) is subject to the VLIZ privacy policy