There is a newer version of the record available.

Published August 19, 2021 | Version v1
Dataset Open

A Deep Learning-Based Hybrid Model of Global Terrestrial Evaporation

  • 1. Hydro-Climate Extremes Lab (H-CEL), Ghent University

Description

This repository contains the codes and datasets used in the research article "A Deep Learning-Based Hybrid Model of Global Terrestrial Evaporation".

The repository contains the following files: 1) Codes - contains scripts used for training the deep learning models used in the study, and for creating the figures in the article. 2) Input - contains all the processed input used for training the deep learning models and the datasets used for creating the figures in the article. 3) Output - contains the final deep learning models and the outputs (evaporation and transpiration stress factor) outputs from the hybrid model developed in the study.

Formats: All scripts are in the programming language Python. The datasets are in HDF5 and NetCDF formats

Files

code_koppa_et_al_hybrid_model.zip

Files (30.3 GB)

Name Size Download all
md5:ef1307b7432000c8c04d8c88705e4112
30.5 kB Preview Download
md5:7886621409904deae90fdf4a3dfb22e6
1.5 GB Preview Download
md5:0b1432afdb97fdc16951c19fad92d8f0
28.8 GB Preview Download

Additional details

Funding

DOWN2EARTH – DOWN2EARTH: Translation of climate information into multilevel decision support for social adaptation, policy development, and resilience to water scarcity in the Horn of Africa Drylands 869550
European Commission
DRY-2-DRY – Do droughts self-propagate and self-intensify? 715254
European Commission