Using Deep Learning to Identify Initial Error Sensitivity for Interpretable ENSO Forecasts
Kinya Toride, Matthew Newman, Andrew Hoell, Antonietta Capotondi,, Jakob Schl\"or, Dillon J. Amaya

TL;DR
This paper presents an interpretable deep learning-enhanced model-analog method for ENSO forecasting, improving accuracy and revealing physical sensitivities in initial conditions, with broad climate application potential.
Contribution
It introduces an interpretable hybrid framework combining deep learning and model-analog forecasting for climate prediction, enhancing accuracy and physical insight.
Findings
10% improvement in ENSO forecast accuracy at 9-12 months
Enhanced regional sensitivity insights linked to physical processes
Forecasts show different initial error sensitivities for El Niño and La Niña
Abstract
We introduce an interpretable-by-design method, optimized model-analog, that integrates deep learning with model-analog forecasting which generates forecasts from similar initial climate states in a repository of model simulations. This hybrid framework employs a convolutional neural network to estimate state-dependent weights to identify initial analog states that lead to shadowing target trajectories. The advantage of our method lies in its inherent interpretability, offering insights into initial-error-sensitive regions through estimated weights and the ability to trace the physically-based evolution of the system through analog forecasting. We evaluate our approach using the Community Earth System Model Version 2 Large Ensemble to forecast the El Ni\~no-Southern Oscillation (ENSO) on a seasonal-to-annual time scale. Results show a 10% improvement in forecasting equatorial Pacific…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsReservoir Engineering and Simulation Methods · Energy Load and Power Forecasting
