Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 359 - Advances in Spatial and Spatio-Temporal Statistics
Type: Contributed
Date/Time: Wednesday, August 5, 2020 : 10:00 AM to 2:00 PM
Sponsor: Section on Statistics and the Environment
Abstract #312431
Title: Uncertainty Quantification and Inference for Spatio-Temporal Forecasting via Echo State Mixture Density Networks with Relevance Propagation
Author(s): Ranadeep Daw* and Christopher Wikle
Companies: University of Missouri and University of Missouri
Keywords: Echo State Network; Mixture Density Network; Spatio-Temporal Data; Uncertainty Quantification; Layerwise Relevance Propagation
Abstract:

Echo state networks (ESN) have been shown to be a powerful tool for the prediction of time series and spatio-temporal data. ESNs are a reservoir computing version of recurrent neural networks (RNNs) in which the weight matrices controlling hidden layers are generated randomly, thus providing a huge computational advantage over traditional RNNs. Deep versions of the ESN consist of multiple hidden layers, again using randomly generated weight matrices. The principle challenge for statistical consideration of such models is uncertainty quantification (UQ) and interpretation. Here we demonstrate for the first time that effective UQ can be accomplished by coupling the ESN to a mixture density network (MDN), and that interpretation of the fitted network can be accomplished via Layerwise Relevance Propagation (LRP). Specifically, LRP can determine which input components are most important in generating forecasts with the model. The approach is demonstrated via simulation study based on noisy versions of classic nonlinear dynamics models. Finally, we apply the approach to long-lead forecasting of Pacific sea surface temperature data.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program