Publications

You can also find my articles on my Google Scholar profile.

Efficient Traffic Prediction at Scale: A Systematic Study of STGCN Architectural Depth

Published in Accepted to the 2026 IEEE 29th International Conference on Intelligent Transportation Systems (ITSC), Naples, Italy, 2026

We ask whether spatio-temporal graph neural networks for traffic prediction are over-parameterized, using STGCN as a test case. Across four traffic datasets, a single-block STGCN matches or beats the standard 2-block design at a fraction of the computational cost.

Recommended citation: Lone, Soban Nasir, Mohamed Abouelela, Taeyoung Yu, Jiwon Kim, and Constantinos Antoniou. "Efficient Traffic Prediction at Scale: A Systematic Study of STGCN Architectural Depth." Accepted to the 2026 IEEE 29th International Conference on Intelligent Transportation Systems (ITSC), Naples, Italy. arXiv preprint arXiv:2606.09539 (2026).
Download Paper

Alpha-VI DeepONet

Published in Computer Methods in Applied Mechanics and Engineering 449 (2026), 2026

We introduce a novel deep operator network (DeepONet) framework that incorporates generalised variational inference (GVI) using Rényi’s α-divergence to learn complex operators while quantifying uncertainty. We apply this approach to a range of mechanics problems, including gravity pendulum, advection-diffusion, and diffusion-reaction systems.

Recommended citation: Lone, Soban Nasir, Subhayan De, and Rajdip Nayek. "Alpha-VI DeepONet: A prior-robust variational Bayesian approach for enhancing DeepONets with uncertainty quantification." Computer Methods in Applied Mechanics and Engineering 449 (2026) 118552. doi: https://doi.org/10.1016/j.cma.2025.118552
Download Paper

Transfer Learning in Spatiotemporal Graph Neural Networks for Traffic Forecasting: Taxonomy, Analysis, and Future Directions

Published in SSRN preprint, 2025

The first comprehensive survey of transfer learning in GNN-based spatiotemporal traffic forecasting. We systematically review and categorise 42 methods into a unified taxonomy through meta-analysis, compile datasets and open-source implementations, and highlight key challenges and future research directions.

Recommended citation: Lone, Soban Nasir, Mohamed Abouelela, Taeyoung Yu, Jiwon Kim, and Constantinos Antoniou. "Transfer Learning in Spatiotemporal Graph Neural Networks for Traffic Forecasting: Taxonomy, Analysis, and Future Directions." SSRN preprint (2025). https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5933134
Download Paper

Scalable Traffic Prediction via Data Reduction with Coreset Selection

Published in 2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), 2025

We study data reduction through coreset selection as a way to make traffic prediction models scale to large datasets.

Recommended citation: Yu, Taeyoung, Jiwon Kim, Soban Nasir Lone, Mohamed Abouelela, and Constantinos Antoniou. "Scalable Traffic Prediction via Data Reduction with Coreset Selection." In 2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), pp. 2069-2076. IEEE, 2025. doi: https://doi.org/10.1109/ITSC60802.2025.11423766
Download Paper

Recursive Bayesian neural networks

Published in arXiv preprint, 2025

This study proposes a recursive Bayesian neural network (rBNN) framework for uncertainty-aware constitutive modelling in geotechnical engineering, incorporating a sliding window approach to capture temporal dependencies. Validated on numerical and experimental triaxial datasets, the rBNN provides robust confidence intervals, highlighting trade-offs between deterministic and probabilistic models.

Recommended citation: Noor, T., Nasir Lone, S., Ramana, G.V. and Nayek, R., 2025. A recursive Bayesian neural network for constitutive modeling of sands under monotonic loading. arXiv e-prints, pp.arXiv-2501.
Download Paper