Attention-Based Geo–Textual Fusion Network for Disaster Risk Prediction

Authors

• Mohammad Shafat Ahsan, Clark University
• Mst Sanjida Alam, Clark University
• Syed Sajjad Ahmed, University of the Potomac
• MD Tanzimul Islam, Webster University
• Hashibul Ahsan Shoaib, St. Francis College
• M.F. Mridha, American International University-Bangladesh
• Md. Jakir Hossen, Multimedia University

Document Type

Article

Abstract

Natural disasters pose recurring threats to human life and infrastructure, demanding intelligent systems that can process heterogeneous data streams and provide actionable insights in real time. Existing approaches often treat textual signals from social media and emergency communications separately from spatial hazard attributes, limiting their effectiveness in capturing the full complexity of evolving crises. This paper proposes an AI-driven geo–textual intelligence framework that integrates disaster-related text with GIS-based hazard features for real-time risk prediction and evacuation planning. The framework employs contextual text encoders and a neural GIS encoder, fused through an attention mechanism that dynamically weights cross-modal signals. Experiments on three datasets; social media disaster tweets, multi-label disaster response messages, and flood hazard GIS attributes. It shows that the proposed model achieves an accuracy of 0.94, macro-F1 of 0.89, IoU of 0.81, and kappa of 0.78, surpassing all classical and deep baselines. Evacuation simulations further demonstrate that the model produces safer and faster routes, reducing travel time from 42.1 to 41.5 minutes and increasing the safety index from 0.61 to 0.81. These results highlight the novelty of aligning linguistic cues with spatial context and underscore the potential of deep geo–textual fusion for enhancing situational awareness and supporting critical decision-making in disaster response. .

Publication Title

IEEE Open Journal of the Computer Society

Publication Date

2026

Volume

7

First Page

1248

Last Page

1259

ISSN

2644-1268

DOI

10.1109/OJCS.2026.3697754

Keywords

Deep learning, disaster response, evacuation planning, geo–textual intelligence, multi-modal fusion, risk prediction

Repository Citation

Ahsan, Mohammad Shafat; Alam, Mst Sanjida; Ahmed, Syed Sajjad; Islam, MD Tanzimul; Shoaib, Hashibul Ahsan; Mridha, M.F.; and Hossen, Md. Jakir, "Attention-Based Geo–Textual Fusion Network for Disaster Risk Prediction" (2026). Student Publications [Scholarly]. 107.
https://commons.clarku.edu/student_publications/107

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.

Copyright Conditions

Ahsan, M. S., Alam, M. S., Ahmed, S. S., Islam, M. T., Shoaib, H. A., Mridha, M. F., & Hossen, M. J. (2026). Attention-Based Geo–Textual Fusion Network for Disaster Risk Prediction. IEEE Open Journal of the Computer Society.