DTMamba : Dual Twin Mamba for Time Series Forecasting
Authors:
- Zexue WuZWZexue Wu
- Yifeng GongYGYifeng Gong
- Aoqian ZhangAZAoqian Zhang
- Boyang LiBLBoyang Li
Open Access
- 1 April 2026
- journal article
- Published by Tsinghua University Press in Tsinghua Science and Technology
- Vol. 31 (2) , 1124-1136
Abstract
Long-term Time Series Forecasting (LTSF) has always been an important task where models need to effectively capture hidden patterns in the time series in order to make accurate predictions about future states. The State-Of-The-Art (SOTA) models in this area are mostly based on Transformers, but the prediction accuracy still needs to be improved. Recently, Mamba has emerged as a promising approach for modeling sequential data, especially for autoregressive tasks with long sequences. Therefore, in this paper, we propose an LTSF model called DTMamba. DTMamba utilizes innovative dual twin Mamba blocks to extract long-term dependencies in time series, while also incorporating residual network to enhance the overall predictive capability. We perform experiments with 8 publicly available datasets and compare DTMamba with 11 SOTA models. The experimental results show that DTMamba outperforms the SOTA models in terms of performance. In particular, our proposal has obvious advantages when dealing with low-dimensional data and predicting longer time series.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- MambaOut: Do We Really Need Mamba for Vision?2025
- VideoMamba: State Space Model for Efficient Video Understanding2024
- Evaluation of deep learning with long short-term memory networks for time series forecasting in supply chain managementProcedia CIRP, 2021
- Transductive LSTM for time-series prediction: An application to weather forecastingNeural Networks, 2020
- Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather stationSoft Computing, 2020
- Financial Time Series Prediction Based on Deep LearningWireless Personal Communications, 2017
- Identity Mappings in Deep Residual Networks2016
- Deep Residual Learning for Image Recognition2016
- Finding structure in timeCognitive Science, 1990
- Evaluation of forecasting methods for decision supportInternational Journal of Forecasting, 1986