There is a newer version of the record available.

Published December 9, 2024 | Version v1
Dataset Open

Replication Data for: ``Global Estimation of Subsurface Eddy Kinetic Energy of Mesoscale Eddies Using a Multiple-input Residual Neural Network''

  • 1. ROR icon University of Science and Technology of China

Description

This dataset contains the Python scripts for training the fully connected neural network model (FCNN), surface-input Residual neural network model (ResNet), multiple-input fully connected neural network model (MI-FCNN), and multiple-input residual neural network model (MI-ResNet), as well as the Matlab files for post-processing reanalysis and observational datasets.

Files

ML_code.zip

Files (1.2 GB)

Name Size Download all
md5:c13ca24234f967223b34d2e79a60ae0e
436.8 MB Preview Download
md5:1ea42c8db06bb0b5bea1e2eeb6219ffe
792.1 MB Preview Download