Song Ding
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
Research Subjects
Song Ding has a total of 69 co-authors. Here are the top co-authors by number of shared publications:
Weijie Zhou
School of Economics, Changzhou University, Jiangsu Changzhou 213159, China; Business College, Changzhou University, Jiangsu Changzhou 213159, China
7 shared publicationsYaoguo Dang
6 shared publicationsXiaoli Wu
School of Economics, Changzhou University, Jiangsu, Changzhou, 213159, China; School of Business, Changzhou University, Jiangsu, Changzhou, 213159, China
4 shared publicationsYao Li
4 shared publications- Xuemei Li
School of Economics, Ocean University of China, Qingdao 266100, China; Institute of Marine Development, Ocean University of China, Qingdao 266100, China
3 shared publications Yao-Guo Dang
3 shared publications
Latest Publications
- 14 February 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 170
Spatio-temporal grey Bernoulli model for green development of marine economy forecasting
- 14 February 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 170
Spatio-temporal grey Bernoulli model for green development of marine economy forecasting
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Engineering Management
- Vol. 73 (00189391) , 1855-1871
A Recursive Discovery of Fractional Dynamics and Its Informed Neural Network Framework With Applications to Heterogeneous Transportation Carbon Emission Forecast
The provincial transportation carbon emissions (TCEs) in China exhibit spatiotemporal heterogeneous characteristics and have become increasingly unpredictable in recent years. To this end, this work proposes a multisource, multiprocess forecasting model, named recursive DFD-PINN, encompassing three crucial components of the discovery of fractional-derivative dynamics, physics-informed neural networks (PINNs), and a recursive mechanism. The newly proposed model is typically designed for forecast tasks of heterogeneous time series dynamics. This model can identify exclusive evolutionary equations describing the provincial TCE systems, leveraging PINN for unified solutions and incorporating short-term temporal dependencies and new updates. Empirically, the comparative experiments indicate that recursive DFD-PINN outperforms six prevailing benchmarks in terms of forecasting accuracy, stability, and robustness against outlier predictions. Furthermore, robustness checks are performed through Monte-Carlo simulations to validate the proposed framework’s stability against randomness in real-world applications. Lastly, the fusion efficacy analysis is conducted by ablation studies to validate the synergy and effectiveness of the fusing components. Supported by the empirical evidence, recursive DFD-PINN is employed to forecast China’s provincial- and national-level TCEs, offering the interpretable use of the hybrid model and informed decision-making for transportation decarbonization.
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Engineering Management
- Vol. 73 (00189391) , 1855-1871
A Recursive Discovery of Fractional Dynamics and Its Informed Neural Network Framework With Applications to Heterogeneous Transportation Carbon Emission Forecast
The provincial transportation carbon emissions (TCEs) in China exhibit spatiotemporal heterogeneous characteristics and have become increasingly unpredictable in recent years. To this end, this work proposes a multisource, multiprocess forecasting model, named recursive DFD-PINN, encompassing three crucial components of the discovery of fractional-derivative dynamics, physics-informed neural networks (PINNs), and a recursive mechanism. The newly proposed model is typically designed for forecast tasks of heterogeneous time series dynamics. This model can identify exclusive evolutionary equations describing the provincial TCE systems, leveraging PINN for unified solutions and incorporating short-term temporal dependencies and new updates. Empirically, the comparative experiments indicate that recursive DFD-PINN outperforms six prevailing benchmarks in terms of forecasting accuracy, stability, and robustness against outlier predictions. Furthermore, robustness checks are performed through Monte-Carlo simulations to validate the proposed framework’s stability against randomness in real-world applications. Lastly, the fusion efficacy analysis is conducted by ablation studies to validate the synergy and effectiveness of the fusing components. Supported by the empirical evidence, recursive DFD-PINN is employed to forecast China’s provincial- and national-level TCEs, offering the interpretable use of the hybrid model and informed decision-making for transportation decarbonization.
- 17 October 2024
- Published by Elsevier in International Review of Economics & Finance
- Vol. 96
Who benefits more from the digital economy: (Non-)Cognitive ability and the labor income premium
- 17 October 2024
- Published by Elsevier in International Review of Economics & Finance
- Vol. 96
Who benefits more from the digital economy: (Non-)Cognitive ability and the labor income premium
- 2 October 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 304
FNNGM: A neural-driven fractional-derivative multivariate fusion model for interpretable real-time CPI forecasts
- 2 October 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 304
FNNGM: A neural-driven fractional-derivative multivariate fusion model for interpretable real-time CPI forecasts
- 9 September 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 259
A novel grey seasonal model with time power for energy prediction
- 9 September 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 259
A novel grey seasonal model with time power for energy prediction
- 17 May 2023
- Published by Elsevier in Information Sciences
- Vol. 642
A novel data-driven seasonal multivariable grey model for seasonal time series forecasting
- 17 May 2023
- Published by Elsevier in Information Sciences
- Vol. 642
A novel data-driven seasonal multivariable grey model for seasonal time series forecasting
- 13 July 2022
- Published by Elsevier in Applied Soft Computing
- Vol. 126
Forecasting the economic indices of the high-tech industries in China using the grey multivariable convolution model
- 13 July 2022
- Published by Elsevier in Applied Soft Computing
- Vol. 126
Forecasting the economic indices of the high-tech industries in China using the grey multivariable convolution model