Multivariate Segment Expandable Encoder-Decoder Model for Time Series Forecasting

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 thes...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2024-01, Vol.12, p.1-1
Main Authors: Li, Yanhong, Anastasiu, David C.
Format: Article
Language:English
Subjects:
Accuracy
Data models
Deep learning
Drought
Encoders-Decoders
Energy management
Flood forecasting
Flood management
Flood predictions
Forecasting
Heavily-tailed distribution
hydrologic prediction
Kurtosis
LSTM
Multivariate analysis
oversampling policy
Predictive models
Public safety
Rain
Real time
representation learning
Segments
streamflow prediction
Time series
Time series analysis
Transformers
Water resources management
Weather forecasting
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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%.
ISSN:2169-3536
DOI:10.1109/ACCESS.2024.3513256