Using Deep Learning to Identify Initial Error Sensitivity for Interpretable ENSO Forecasts

1 code implementation • 23 Apr 2024 • Kinya Toride, Matthew Newman, Andrew Hoell, Antonietta Capotondi, Jakob Schlör, Dillon Amaya

We introduce an interpretable-by-design method, optimized model-analog, that integrates deep learning with model-analog forecasting, a straightforward yet effective approach that generates forecasts from similar initial climate states in a repository of model simulations.