Predicting extreme events from data using deep machine learning: when and where

TL;DR

This paper presents a deep learning framework using convolutional neural networks to predict the timing and location of extreme events in 2D physical systems, validated on synthetic and real-world data.

Contribution

It introduces a model-free deep learning approach for simultaneous spatiotemporal prediction of extreme events in nonlinear systems.

Findings

Effective prediction of extreme events within specified time horizons.

Ability to localize the predicted event location with certain resolution.

Trade-offs identified between prediction horizon, spatial resolution, and accuracy.

Abstract

We develop a deep convolutional neural network (DCNN) based framework for model-free prediction of the occurrence of extreme events both in time ("when") and in space ("where") in nonlinear physical systems of spatial dimension two. The measurements or data are a set of two-dimensional snapshots or images. For a desired time horizon of prediction, a proper labeling scheme can be designated to enable successful training of the DCNN and subsequent prediction of extreme events in time. Given that an extreme event has been predicted to occur within the time horizon, a space-based labeling scheme can be applied to predict, within certain resolution, the location at which the event will occur. We use synthetic data from the 2D complex Ginzburg-Landau equation and empirical wind speed data of the North Atlantic ocean to demonstrate and validate our machine-learning based prediction framework. The trade-offs among the prediction horizon, spatial resolution, and accuracy are illustrated, and the detrimental effect of spatially biased occurrence of extreme event on prediction accuracy is discussed. The deep learning framework is viable for predicting extreme events in the real world.