Input data for deep learning model-analog

This repository contains input data required to run the Deep Learning Model-Analog (GitHub), as presented in the paper titled "Using Deep Learning to Identify Initial Error Sensitivity for Interpretable ENSO Forecasts" by Toride et al. A preprint is available at https://arxiv.org/abs/2404.15419.

The cesm2 directory contains the Community Earth System Model Version 2 Large Ensemble (CESM2-LE), while the real directory contains the Ocean Reanalysis System 5 (ORAS5) datasets. These datasets have been processed to provide detrended monthly anomalies and have been interpolated to two different resolutions: 2° × 2° and 5° × 5°. The 5°×5° files are used as input, while the 2°×2° files are used for analog forecasting.