AA-forecast: anomaly-aware forecast for extreme events
- 13 March 2023
- journal article
- research article
- Published by Springer Nature in Data Mining and Knowledge Discovery
- Vol. 37 (3) , 1209-1229
Abstract
Time series models often are impacted by extreme events and anomalies, both prevalent in real-world datasets. Such models require careful probabilistic forecasts, which is vital in risk management for extreme events such as hurricanes and pandemics. However, it’s challenging to automatically detect and learn from extreme events and anomalies for large-scale datasets which often results in extra manual efforts. Here, we propose an anomaly-aware forecast framework that leverages the effects of anomalies to improve its prediction accuracy during the presence of extreme events. Our model has trained to extract anomalies automatically and incorporates them through an attention mechanism to increase the accuracy of forecasts during extreme events. Moreover, the framework employs a dynamic uncertainty optimization algorithm that reduces the uncertainty of forecasts in an online manner. The proposed framework demonstrated consistent superior accuracy with less uncertainty on three datasets with different varieties of anomalies over the current prediction models.Keywords
All Related Versions
Funding Information
- Directorate for Computer and Information Science and Engineering (1937833, 2028481)
This publication has 19 references indexed in Scilit:
- Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting2019
- Differential and persistent risk of excess mortality from Hurricane Maria in Puerto Rico: a time-series analysisThe Lancet Planetary Health, 2018
- Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context2018
- Deep and Confident Prediction for Time Series at Uber2017
- Short-term load forecasting using a two-stage sarimax modelEnergy, 2017
- Anomaly detection based on uncertainty fusion for univariate monitoring seriesMeasurement, 2017
- Risk-Based Assessment of Unplanned Outage Events and Costs for Combined-Cycle PlantsJournal of Engineering for Gas Turbines and Power, 2013
- Long Short-Term MemoryNeural Computation, 1997
- Robust Locally Weighted Regression and Smoothing ScatterplotsJournal of the American Statistical Association, 1979
- Distribution of Residual Autocorrelations in Autoregressive-Integrated Moving Average Time Series ModelsJournal of the American Statistical Association, 1970