Dynamic Crisis Propagation Modeling and Emergency Scheduling via a Grasshopper-Optimized Spatiotemporal Graph Neural Network
Abstract
Public crises such as natural disasters, pandemics, and large-scale industrial accidents require intelligent real-time decision-support systems capable of accurately predicting crisis severity and optimizing emergency resource allocation. This research introduces a Dynamic Grasshopper-Optimized Spatiotemporal Graph Neural Network (DGO-ST-GNN) designed to model crisis propagation by integrating spatial and temporal dependencies in crisis evolution. The architecture consists of stacked Spatiotemporal Graph Convolution Blocks, combining graph convolution layers for spatial region relationships and gated recurrent temporal units for sequential progression of crisis patterns. To enhance convergence stability, generalization, and performance consistency, a Dynamic Grasshopper Optimization Algorithm (DGOA) adaptively tunes hyperparameters, including learning rate, batch size, convolution depth, and dropout rate at the end of each training epoch. The model is trained on 1,030 manually annotated geo-tagged crisis-related tweets containing crisis type, sentiment polarity, severity level, resource availability, timestamp, and geolocation. Text preprocessing includes tokenization, stop-word removal, and Word2Vec embeddings (300-dimensional), which are used to construct semantic similarity edges for graph generation across urban regions. Data are partitioned using an 80:20 train-validation-test split, and implementation is performed in Python. Experimental evaluation compares DGO-ST-GNN with traditional machine learning models (SVM, Logistic Regression, Random Forest, Naïve Bayes) and deep-learning baselines (CNN, LSTM, CNN-LSTM, BERT, XLNet). The proposed shows superior classification performance for crisis severity prediction,97% accuracy, 95% precision, 96% recall, and 94.9% F1-score, outperforming the strongest baseline Although DGOA increases per-epoch runtime by 38.7%, the improvement significantly strengthens predictive robustness and scalability for real-time emergency response.References
Kazadi, A., Doss-Gollin, J., Sebastian, A., and Silva, A., 2024. FloodGNN-GRU: a spatio-temporal graph neural network for flood prediction. Environmental Data Science, 3, p.e21. https://doi.org/10.1017/eds.2024.19
Lopez, V.K., Nika, A., Blanton, C., Talley, L., and Garfield, R., 2023. Can the severity of a humanitarian crisis be quantified? Assessment of the INFORM severity index. Globalization and health, 19(1), p.7. https://doi.org/10.1186/s12992-023-00907-y
Das, S., Choudhury, M.R., Chatterjee, B., Das, P., Bagri, S., Paul, D., Bera, M., and Dutta, S., 2024. Unraveling the urban climate crisis: Exploring the nexus of urbanization, climate change, and their impacts on the environment and human well-being–A global perspective. AIMS Public Health, 11(3), p.963. https://doi.org/10.3934/publichealth.2024050
Amatya, B. and Khan, F., 2023. Disaster response and management: the integral role of Rehabilitation. Annals of Rehabilitation Medicine, 47(4), pp.237-260. https://doi.org/10.5535/arm.23071
Erokhin, D. and Komendantova, N., 2024. Social media data for disaster risk management and research. International Journal of Disaster Risk Reduction, 114, p.104980. https://doi.org/10.1016/j.ijdrr.2024.104980
Firmansyah, H.B., 2025. Improving Disaster Response With Advanced Machine Learning ToAnalyse Social Media Content. https://doi.org/10.13097/archive-ouverte/unige:183585
Ginzarly, M., Teller, J. and Dujardin, S., 2025. Social media use in disaster response: empowering community resilience. International Journal of Digital Earth, 18(1), p.2521791. https://doi.org/10.1080/17538947.2025.2521791
Solovev, K., 2024. Leveraging Unstructured Data to Address Societal Challenges in the Digital Age (Doctoral dissertation, Justus Liebig University Giessen). https://doi.org/10.22029/jlupub-19035
Mizrak, K.C., 2024. Crisis management and risk mitigation: Strategies for effective response and resilience. Trends, challenges, and practices in contemporary strategic management, pp.254-278. https://doi.org/10.4018/979-8-3693-1155-4.ch013
Fang, H.S., Wang, C., Fang, H., Gou, M., Liu, J., Yan, H., Liu, W., Xie, Y., and Lu, C., 2023. Anygrasp: Robust and efficient grasp perception in spatial and temporal domains. IEEE Transactions on Robotics, 39(5), pp.3929-3945. https://doi.org/10.1109/TRO.2023.3281153
Qhal, E.M.A., 2025. Data-Driven Knowledge Management Frameworks for Effective Risk and Crisis Management: A Cross-Industry Approach. Journal of Applied Data Sciences, 6(2), pp.1437-1453. https://doi.org/10.47738/jads.v6i2.780
Zhou, Y. and Xia, W., 2021. Optimization algorithm and simulation of public resource emergency scheduling based on wireless sensor technology. Journal of Sensors, 2021(1), p.2450346. https://doi.org/10.1155/2021/2450346
Zhao, X. and Wang, G., 2023. Deep Q-networks-based optimization of emergency resource scheduling for urban public health events. Neural Computing and Applications, 35(12), pp.8823-8832. https://doi.org/10.1007/s00521-022-07696-2
Wang, Y., Chen, X., and Wang, L., 2023. Deep reinforcement learning-based rescue resource distribution scheduling of storm surge inundation emergency logistics. IEEE Transactions on Industrial Informatics, 19(10), pp.10004-10013. https://doi.org/10.1109/TII.2022.3230691
Upadhyay, A., Meena, Y.K., and Chauhan, G.S., 2024. SatCoBiLSTM: Self-attention-based hybrid deep learning framework for crisis event detection in social media. Expert Systems with Applications, 249, p.123604. https://doi.org/10.1016/j.eswa.2024.123604
Wang, C., Deng, D., Xu, L., and Wang, W., 2022. Resource scheduling based on deep reinforcement learning in UAV-assisted emergency communication networks. IEEE Transactions on Communications, 70(6), pp.3834-3848. https://doi.org/10.1109/TCOMM.2022.3170458
Powers, C.J., Devaraj, A., Ashqeen, K., Dontula, A., Joshi, A., Shenoy, J., and Murthy, D., 2023. Using artificial intelligence to identify emergency messages on social media during a natural disaster: A deep learning approach. International Journal of Information Management Data Insights, 3(1), p.100164. https://doi.org/10.1016/j.jjimei.2023.100164
Seid, A.M., Boateng, G.O., Anokye, S., Kwantwi, T., Sun, G. and Liu, G., 2021. Collaborative computation offloading and resource allocation in multi-UAV-assisted IoT networks: A deep reinforcement learning approach. IEEE Internet of Things Journal,8(15), pp.12203-12218. https://doi.org/10.1109/JIOT.2021.3063188
Zhang, Y., 2025. Media framing and public risk communication: Deep Learning-based crisis narrative analysis and optimization. Future Technology, 4(3), pp.227-238. https://doi.org/10.55670/fpll.futech.4.3.21
Yan, L., Ren, Z., Zhang, Y., Tao, Z. and Zhao, Y., 2024. Constructing the public opinion crisis prediction model using CNN and LSTM techniques based on social network mining. http://dx.doi.org/10.9781/ijimai.2024.07.005
Chen, M. and Du, W., 2023. Predicting public sentiment evolution on public emergencies under deep learning and the Internet of Things. The Journal of Supercomputing, 79(6), pp.6452-6470. https://doi.org/10.1007/s11227-022-04900-x
Shetty, N.P., Bijalwan, Y., Chaudhari, P., Shetty, J. and Muniyal, B., 2025. Disaster assessment from social media using multimodal deep learning. Multimedia Tools and Applications, 84(18), pp.18829-18854. https://doi.org/10.3390/ijgi13010029
Paul, N.R., Sahoo, D., and Balabantaray, R.C., 2023. Classification of crisis-related data on Twitter using a deep learning-based framework. Multimedia Tools and Applications, 82(6), pp.8921-8941. https://doi.org/10.1007/s11042-022-12183-w
Li, Z., & Fan, R. (2025). Crisis-Resilient Portfolio Management via Graph-based Spatio-Temporal Learning. arXiv preprint arXiv:2510.20868. https://doi.org/10.48550/arXiv.2510.20868
Mo, G., Jia, W., Tan, C., Zhang, W., & Rong, J. (2025). Risk Prediction of International Stock Markets with Complex Spatio-Temporal Correlations: A Spatio-Temporal Graph Convolutional Regression Model Integrating Uncertainty Quantification. Journal of Risk and Financial Management, 18(9), 488. https://doi.org/10.3390/jrfm18090488
https://www.kaggle.com/datasets/programmer3/public-crisis-spatiotemporal-response-dataset/data.
Shen, H., Ju, Y., and Zhu, Z., 2023. Extracting useful emergency information from social media: A method integrating machine learning and rule-based classification. International Journal of Environmental Research and Public Health, 20(3), p.1862. https://doi.org/10.3390/ijerph20031862
Powers, C. J., Devaraj, A., Ashqeen, K., Dontula, A., Joshi, A., Shenoy, J., & Murthy, D. (2023). Using artificial intelligence to identify emergency messages on social media during a natural disaster: A deep learning approach. International Journal of Information Management Data Insights, 3(1), 100164.https://doi.org/10.1016/j.jjimei.2023.100164
Airlangga, G. (2024). Comparative analysis of machine learning models for real-time disaster tweet classification: Enhancing emergency response with social media analytics. Brilliance: Research of Artificial Intelligence, 4(1), 25-31. https://doi.org/10.47709/brilliance.v4i1.3669
Khafaji, K. M., & Hamed, B. B. (2024). Employing deep learning in crisis management and decision making through prediction using time series data in Mosul Dam, Northern Iraq. PeerJ Computer Science, 10, e2416. https://doi.org/10.7717/peerj-cs.2416
Kabir, M. Y., & Madria, S. (2019). A Deep Learning Approach for Tweet Classification and Rescue Scheduling for Effective Disaster Management (Industrial). https://doi.org/10.1145/3347146.3359097
DOI:
https://doi.org/10.31449/inf.v49i36.10578Downloads
Published
How to Cite
Issue
Section
License
I assign to Informatica, An International Journal of Computing and Informatics ("Journal") the copyright in the manuscript identified above and any additional material (figures, tables, illustrations, software or other information intended for publication) submitted as part of or as a supplement to the manuscript ("Paper") in all forms and media throughout the world, in all languages, for the full term of copyright, effective when and if the article is accepted for publication. This transfer includes the right to reproduce and/or to distribute the Paper to other journals or digital libraries in electronic and online forms and systems.
I understand that I retain the rights to use the pre-prints, off-prints, accepted manuscript and published journal Paper for personal use, scholarly purposes and internal institutional use.
In certain cases, I can ask for retaining the publishing rights of the Paper. The Journal can permit or deny the request for publishing rights, to which I fully agree.
I declare that the submitted Paper is original, has been written by the stated authors and has not been published elsewhere nor is currently being considered for publication by any other journal and will not be submitted for such review while under review by this Journal. The Paper contains no material that violates proprietary rights of any other person or entity. I have obtained written permission from copyright owners for any excerpts from copyrighted works that are included and have credited the sources in my article. I have informed the co-author(s) of the terms of this publishing agreement.
Copyright © Slovenian Society Informatika
