Multivariate Segment Expandable Encoder-Decoder Model for Time Series Forecasting
Open Access
- 9 December 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 185012-185026
Abstract
Accurate time series forecasting is critical in a variety of fields, including transportation, weather prediction, energy management, infrastructure monitoring, and finance. Forecasting highly skewed and heavy-tailed time series, particularly in multivariate environments, is still difficult. In these cases, accurately capturing the relationships between variables is critical for successful model design. This is especially true when dealing with extreme events like droughts or floods in streamflow forecasting, which can have severe consequences on public safety and social well-being. We present the Multivariate Segment-Expandable Encoder Decoder (MSEED), a novel framework designed to address the challenges of extreme-adaptive multivariate time series forecasting. MSEED features a hierarchical encoder-decoder architecture, a short-term-enhanced subnet, and a feature assembling layer that integrates spatial and temporal information across multivariate inputs. By capturing quantile distributions across segmented subsequences at multiple scales, the model is able to detect complex patterns, enhancing both the accuracy and robustness of forecasts. Additionally, MSEED incorporates a simple vanilla encoder-decoder model for strengthening rolling predictions. The framework has been tested on four challenging real-world datasets, focusing on two critical forecasting scenarios: long-term predictions (three days ahead) and rolling predictions (every four hours) to simulate real-time decision-making in water resource management. MSEED consistently outperforms state-of-the-art models, showing improvements in forecasting accuracy ranging from 18% to 74%.Keywords
This publication has 35 references indexed in Scilit:
- A Smart Home Energy Management System Utilizing Neurocomputing-Based Time-Series Load Modeling and Forecasting Facilitated by Energy Decomposition for Smart Home AutomationIEEE Access, 2022
- Deep learning for anomaly detection in multivariate time series: Approaches, applications, and challengesInformation Fusion, 2022
- Piecewise linear neural networks and deep learningNature Reviews Methods Primers, 2022
- Neural networks based multivariate time series forecasting of solar radiation using meteorological data of different cities of BangladeshResults in Engineering, 2022
- A stream prediction model based on attention-LSTMEarth Science Informatics, 2021
- DeepAR: Probabilistic forecasting with autoregressive recurrent networksInternational Journal of Forecasting, 2020
- A Novel Segmentation and Representation Approach for Streaming Time SeriesIEEE Access, 2018
- Forecasting at ScaleThe American Statistician, 2018
- SMOTEBoost: Improving Prediction of the Minority Class in Boosting2003
- Dimensionality Reduction for Fast Similarity Search in Large Time Series DatabasesKnowledge and Information Systems, 2001