Xuegong Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xuegong Wang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Chong Li
Department of Automation and Measurement, Ocean University of China, Qingdao 266100, China
1 shared publication - Jin Wu
School of Intelligent Science and Technology, University of Science and Technology Beijing, Beijing 100083, China
1 shared publication Lining Tan
Xian Research Institute of High Technology, Xian, China
1 shared publication- Xinning Wang
Ocean University of China
1 shared publication
Latest Publications
- Open Access
- 11 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 15 (19391404) , 3853-3867
Spatio–Temporal Attention-Based Deep Learning Framework for Mesoscale Eddy Trajectory Prediction
Accurate prediction of mesoscale eddy trajectories requires efficient models with large-size available data instances to capture the main eddy characteristics. However, there is a lack of salient attention mechanisms that can recognize the demand of extracting the aggregated features over multidimensional eddy data sources. Additionally, deep learning techniques are very important for eddy trajectory prediction to dynamically capture properties of mesoscale eddies in the South China Sea. In this article, we propose a spatio–temporal attention-based deep learning framework that can orchestrate heterogeneous data integration and propagation trajectory forecast together. It consists of a novel autoencoder equipped with channel and spatial attention mechanisms (CSA-encoder), and a gated recurrent unit (GRU) network with temporal attention layer (TA-GRU). CSA-encoder compresses stereoscopic eddy data with convolutional layers and generates the small-scale and high-quality dataset as the input of TA-GRU. The finer grained TA-GRU method is extended to accurately predict eddy trajectories with more valuable imagery information so that the temporal attention mechanism can automatically select relevant regions within the next 14 days. Our cross-validation results demonstrate that our framework averagely achieves a lower distance error (9 km) and 54% performance improvement over the baseline GRU technique in the next one day, and outperforms two state-of-the-art techniques of long short-term memory and recurrent neural network by 54.9% and 65.6%, respectively.
- 11 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 15 (19391404) , 3853-3867
Open AccessSpatio–Temporal Attention-Based Deep Learning Framework for Mesoscale Eddy Trajectory Prediction
Accurate prediction of mesoscale eddy trajectories requires efficient models with large-size available data instances to capture the main eddy characteristics. However, there is a lack of salient attention mechanisms that can recognize the demand of extracting the aggregated features over multidimensional eddy data sources. Additionally, deep learning techniques are very important for eddy trajectory prediction to dynamically capture properties of mesoscale eddies in the South China Sea. In this article, we propose a spatio–temporal attention-based deep learning framework that can orchestrate heterogeneous data integration and propagation trajectory forecast together. It consists of a novel autoencoder equipped with channel and spatial attention mechanisms (CSA-encoder), and a gated recurrent unit (GRU) network with temporal attention layer (TA-GRU). CSA-encoder compresses stereoscopic eddy data with convolutional layers and generates the small-scale and high-quality dataset as the input of TA-GRU. The finer grained TA-GRU method is extended to accurately predict eddy trajectories with more valuable imagery information so that the temporal attention mechanism can automatically select relevant regions within the next 14 days. Our cross-validation results demonstrate that our framework averagely achieves a lower distance error (9 km) and 54% performance improvement over the baseline GRU technique in the next one day, and outperforms two state-of-the-art techniques of long short-term memory and recurrent neural network by 54.9% and 65.6%, respectively.