Sea Surface Temperature Dataset for Yellow Sea Coastal Waters (2000-2020): Physics-Guided Deep Learning for SST Forecasting

Read full text
Authors: Fan Donglin, Wang zeyu, He hongchang
Cited by: 0

Abstract

This dataset contains processed sea surface temperature (SST) data for the Yellow Sea coastal waters, spanning from January 1, 2000 to December 31, 2020. The data covers the region 120.025°E to 123.175°E in longitude and 33.025°N to 36.175°N in latitude at daily temporal resolution and 0.05° × 0.05° spatial resolution. The dataset is derived from the Global Ocean OSTIA (Operational Sea Surface Temperature and Sea Ice Analysis) provided by the Copernicus Marine Environment Monitoring Service (CMEMS). The data has been preprocessed for deep learning applications, including normalization to zero mean and unit variance, and chronological partitioning into training (70%), validation (15%), and test (15%) subsets. This dataset supports the research described in "Dynamic Physics-Guided Learning for SST Forecasting via Online State Correction" submitted to GIScience & Remote Sensing. Data format: NetCDF (.nc) Spatial dimensions: 64 × 64 grid points Temporal coverage: 7,671 daily observations Missing values: Land areas are masked

Fields of Study & Subjects

Oceanographic and Atmospheric Processes Model Reduction and Neural Networks Hydrological Forecasting Using AI

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
12 January 2026
Document type
Dataset