EUVIMEDEUVIMED entdecken
Crossref

Towards High Resolution Probabilistic Coastal Inundation Forecasting from Sparse Observations

Kazi Ashik Islam, Zakaria Mehrab, Mahantesh M Halappanavar, Henning Mortveit, Katragadda Sridhar, Jon Derek Loftis, Stefan Hoops, Madhav Marathe

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (45) · 38607-38615

DOI: 10.1609/aaai.v40i45.41203 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Kazi Ashik Islam und 7 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Coastal flooding poses increasing threats to communities worldwide, necessitating accurate and hyper-local inundation forecasting for effective emergency response. However, real-world deployment of forecasting systems is often constrained by sparse sensor networks, where only a limited subset of locations may have sensors due to budget constraints. To approach this challenge, we present Diff-Sparse, a masked conditional diffusion model designed for probabilistic coastal inundation forecasting from sparse sensor observations. Diff-Sparse primarily utilizes the inundation history of a location and its neighboring locations from a context time window as spatiotemporal context. The fundamental challenge of spatiotemporal prediction based on sparse observations in the context window is addressed by introducing a novel masking strategy during training. Digital elevation data and temporal co-variates are utilized as additional spatial and temporal contexts, respectively. A convolutional neural network and a conditional UNet architecture with cross-attention mechanism are employed to capture the spatiotemporal dynamics in the data. We trained and tested Diff-Sparse on coastal inundation data from the Eastern Shore of Virginia and systematically assessed the performance of Diff-Sparse across different sparsity levels (0%, 50%, 95% missing observations). Our experiment results show that Diff-Sparse achieves upto 62% improvement in terms of two forecasting performance metrics compared to existing methods, at 95% sparsity level. Moreover, our ablation studies reveal that digital elevation data becomes more useful at high sparsity levels compared to temporal co-variates.

Zitieren

APA

Islam, K. A., Mehrab, Z., Halappanavar, M. M., Mortveit, H., Sridhar, K., Loftis, J. D., Hoops, S., & Marathe, M. (2026). Towards High Resolution Probabilistic Coastal Inundation Forecasting from Sparse Observations. Proceedings of the AAAI Conference on Artificial Intelligence, 40(45), 38607-38615. https://doi.org/10.1609/aaai.v40i45.41203

Vancouver

Islam KA, Mehrab Z, Halappanavar MM, Mortveit H, Sridhar K, Loftis JD, et al. Towards High Resolution Probabilistic Coastal Inundation Forecasting from Sparse Observations. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(45):38607-38615. doi:10.1609/aaai.v40i45.41203

BibTeX
@article{Islam2026,
  author = {Islam, Kazi Ashik and Mehrab, Zakaria and Halappanavar, Mahantesh M and Mortveit, Henning and Sridhar, Katragadda and Loftis, Jon Derek and Hoops, Stefan and Marathe, Madhav},
  title = {Towards High Resolution Probabilistic Coastal Inundation Forecasting from Sparse Observations},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {45},
  pages = {38607--38615},
  doi = {10.1609/aaai.v40i45.41203}
}
Kostenlos starten →