.png){kind=icon}
.png){kind=icon}
Return
Spatio-Temporal Series Prediction Based on Multi-Objective Evolutionary Deep Convolutional Echo State Networks
.png){kind=icon}
PRE
AI
DOI：10.1109/TETCI.2026.3670634.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate prediction of spatio-temporal series remains a challenging task due to complex spatial dependencies, temporal dynamics, and factors such as data sparsity, nonlinearity, and high dimensionality. To address these challenges, this paper proposes a novel framework which integrates a spatio-temporal interpolated deep convolutional echo state network with an improved multi-objective evolutionary algorithm. The model integrates cubic spline interpolation to enhance temporal resolution, a spatial attention mechanism to capture inter-location correlations, and a convolution-based deep echo state network to efficiently model spatio-temporal patterns. A multi-objective evolutionary algorithm is then employed to jointly optimize model hyper-parameters with two objectives of maximizing prediction accuracy and minimizing model complexity. To further improve efficiency, a topological data analysis-based strategy is used to select a representative and diverse subset of candidate solutions, reducing computational cost without compromising optimization quality. Experiments on two real-world meteorological datasets demonstrate that the proposed approach achieves superior prediction accuracy across single and multiple horizons. Ablation study further confirms the importance of each architecture component and the effectiveness of the proposed optimization strategy. The results validate the potential of the proposed model as an efficient tool for real-world spatio-temporal forecasting tasks.
Keywords:
Spatio-temporal series
prediction
deep convolutional echo state networks
topological data analysis
Journal
I
IF:
6.5
Papers:
1.4K
Citations:
4.5K