Suixiang Shi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Suixiang Shi has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Lingyu Xu
Department of Computer Engineering and Science, Shanghai University, Shanghai, China
4 shared publications - Jie Yu
School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China
3 shared publications - Yaya Liu
School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
3 shared publications - Xuan Yu
School of Computer Engineering and Science, Shanghai University, Shanghai, 200444, China
2 shared publications - Xuan Yu
Shanghai University, Shanghai, 200041, China
2 shared publications Baiyou Qiao
Northeastern University
1 shared publication
Latest Publications
- 1 December 2021
- Published by Elsevier in Applied Soft Computing
- Vol. 113
A spatial–temporal graph attention network approach for air temperature forecasting
- 1 December 2021
- Published by Elsevier in Applied Soft Computing
- Vol. 113
A spatial–temporal graph attention network approach for air temperature forecasting
- Open Access
- 7 May 2020
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2020, 1-9
A Novel Method for Sea Surface Temperature Prediction Based on Deep Learning
Sea surface temperature (SST) forecasting is the task of predicting future values of a given sequence using historical SST data, which is beneficial for observing and studying hydroclimatic variability. Most previous studies ignore the spatial information in SST prediction and the forecasting models have limitations to process the large-scale SST data. A novel model of SST prediction integrated Deep Gated Recurrent Unit and Convolutional Neural Network (DGCnetwork) is proposed in this paper. The DGCnetwork has a compact structure and focuses on learning deep long-term dependencies in SST time series. Temporal information and spatial information are all included in our procedure. Differential Evolution algorithm is applied in order to configure DGCnetwork’s optimum architecture. Optimum Interpolation Sea Surface Temperature (OISST) data is selected to conduct experiments in this paper, which has good temporal homogeneity and feature resolution. The experiments demonstrate that the DGCnetwork significantly obtains excellent forecasting result, predicting SST by different lengths flexibly and accurately. On the East China Sea dataset and the Yellow Sea dataset, the accuracy of the prediction results is above 98% on the whole and all mean absolute error (MAE) values are lower than 0.33°C. Compared with the other models, root mean square error (RMSE), root mean square percentage error (RMSPE), and mean absolute percentage Error (MAPE) of the proposed approach reduce at least 0.1154, 0.2594, and 0.3938. The experiments of SST time series show that the DGCnetwork model maintains good prediction results, better performance, and stronger stability, which has reached the most advanced level internationally.
- 7 May 2020
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2020, 1-9
Open AccessA Novel Method for Sea Surface Temperature Prediction Based on Deep Learning
Sea surface temperature (SST) forecasting is the task of predicting future values of a given sequence using historical SST data, which is beneficial for observing and studying hydroclimatic variability. Most previous studies ignore the spatial information in SST prediction and the forecasting models have limitations to process the large-scale SST data. A novel model of SST prediction integrated Deep Gated Recurrent Unit and Convolutional Neural Network (DGCnetwork) is proposed in this paper. The DGCnetwork has a compact structure and focuses on learning deep long-term dependencies in SST time series. Temporal information and spatial information are all included in our procedure. Differential Evolution algorithm is applied in order to configure DGCnetwork’s optimum architecture. Optimum Interpolation Sea Surface Temperature (OISST) data is selected to conduct experiments in this paper, which has good temporal homogeneity and feature resolution. The experiments demonstrate that the DGCnetwork significantly obtains excellent forecasting result, predicting SST by different lengths flexibly and accurately. On the East China Sea dataset and the Yellow Sea dataset, the accuracy of the prediction results is above 98% on the whole and all mean absolute error (MAE) values are lower than 0.33°C. Compared with the other models, root mean square error (RMSE), root mean square percentage error (RMSPE), and mean absolute percentage Error (MAPE) of the proposed approach reduce at least 0.1154, 0.2594, and 0.3938. The experiments of SST time series show that the DGCnetwork model maintains good prediction results, better performance, and stronger stability, which has reached the most advanced level internationally.
- 27 March 2019
- Published by Taylor & Francis in Remote Sensing Letters
- Vol. 10 (7) , 609-618
A directed limited penetrable visibility graph (DLPVG)-based method of analysing sea surface temperature
The present paper studies the dynamic association among the sea surface temperature (SST) data through directed limited penetrable visibility graph (DLPVG) method. We analyse the fluctuation trend of temperature in different regions by constructing an SST-dynamic association network to explore the topology structure. By analysing the SST data of the East China Sea, we find that there are association patterns among multivariate SST and a few types of patterns play a significant role in the movement of the sea water. Furthermore, the experiments also show that the multivariate SST has a close relationship with El Niño events, which indicates that the network is of great significance to the research and prediction of the El Niño phenomenon.
- 27 March 2019
- Published by Taylor & Francis in Remote Sensing Letters
- Vol. 10 (7) , 609-618
A directed limited penetrable visibility graph (DLPVG)-based method of analysing sea surface temperature
The present paper studies the dynamic association among the sea surface temperature (SST) data through directed limited penetrable visibility graph (DLPVG) method. We analyse the fluctuation trend of temperature in different regions by constructing an SST-dynamic association network to explore the topology structure. By analysing the SST data of the East China Sea, we find that there are association patterns among multivariate SST and a few types of patterns play a significant role in the movement of the sea water. Furthermore, the experiments also show that the multivariate SST has a close relationship with El Niño events, which indicates that the network is of great significance to the research and prediction of the El Niño phenomenon.
- 2 September 2014
- Published by Springer Nature in Acta Oceanologica Sinica
- Vol. 33 (9) , 82-92
Research on data pre-deployment in information service flow of digital ocean cloud computing
- 2 September 2014
- Published by Springer Nature in Acta Oceanologica Sinica
- Vol. 33 (9) , 82-92
Research on data pre-deployment in information service flow of digital ocean cloud computing
- 1 September 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 312-315
Research on domain knowledge graph based on the large scale online knowledge fragment
Knowledge Graph is a powerful tool to manage large scale knowledge, and is an important means to deal with the problem of the knowledge fragment. Knowledge Graph can be applied to Semantic Search, Question Answering System, Deep Reading and other. The current research mainly focuses on the information fusion of broad-spectrum knowledge, and aims at improving the recall ratio of the knowledge. Based on the previous research, we propose a method for constructing the domain knowledge Graph. We use information extraction technology to extract entities and relationships from open network documents. Meanwhile, we mine the multidimensional relationships between entities, and solve the information conflicts generated by multi-source information fusion. These are important to rich the information and improve the recall ratio and precision ratio of domain knowledge. So the method has important significance to build knowledge graph of specific areas.
- 1 September 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 312-315
Research on domain knowledge graph based on the large scale online knowledge fragment
Knowledge Graph is a powerful tool to manage large scale knowledge, and is an important means to deal with the problem of the knowledge fragment. Knowledge Graph can be applied to Semantic Search, Question Answering System, Deep Reading and other. The current research mainly focuses on the information fusion of broad-spectrum knowledge, and aims at improving the recall ratio of the knowledge. Based on the previous research, we propose a method for constructing the domain knowledge Graph. We use information extraction technology to extract entities and relationships from open network documents. Meanwhile, we mine the multidimensional relationships between entities, and solve the information conflicts generated by multi-source information fusion. These are important to rich the information and improve the recall ratio and precision ratio of domain knowledge. So the method has important significance to build knowledge graph of specific areas.