DeepExtrema: A Deep Learning Approach for Forecasting Block Maxima in Time Series Data
This addresses forecasting extreme events in time series, which is critical for human and natural systems, but appears incremental as it builds on existing statistical and deep learning approaches.
The paper tackles the problem of forecasting extreme values in time series data by proposing DeepExtrema, a framework that combines a deep neural network with generalized extreme value distribution to predict block maxima. Experiments on real-world and synthetic data showed it outperforms baseline methods.
Accurate forecasting of extreme values in time series is critical due to the significant impact of extreme events on human and natural systems. This paper presents DeepExtrema, a novel framework that combines a deep neural network (DNN) with generalized extreme value (GEV) distribution to forecast the block maximum value of a time series. Implementing such a network is a challenge as the framework must preserve the inter-dependent constraints among the GEV model parameters even when the DNN is initialized. We describe our approach to address this challenge and present an architecture that enables both conditional mean and quantile prediction of the block maxima. The extensive experiments performed on both real-world and synthetic data demonstrated the superiority of DeepExtrema compared to other baseline methods.