Can We Predict the Unpredictable? Leveraging DisasterNet-LLM for Multimodal Disaster Classification
Preprint
Abstract
Effective disaster management requires timely and accurate insights, yet traditional methods struggle to integrate multimodal data such as images, weather records, and textual reports. To address this, we propose DisasterNet-LLM, a specialized Large Language Model (LLM) designed for comprehensive disaster analysis. By leveraging advanced pretraining, cross-modal attention mechanisms, and adaptive transformers, DisasterNet-LLM excels in disaster classification. Experimental results demonstrate its superiority over state-of-the-art models, achieving higher accuracy of 89.5%, an F1 score of 88.0%, AUC of 0.92%, and BERTScore of 0.88% in multimodal disaster classification tasks.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- CLLMate: A Multimodal Benchmark for Weather and Climate Events Forecasting2025
- Enhancing emergency decision-making with knowledge graphs and large language modelsInternational Journal of Disaster Risk Reduction, 2024
- Fine-tuning GPT-3 for legal rule classificationComputer Law & Security Review, 2023
- Health system-scale language models are all-purpose prediction enginesNature, 2023
- Parameter-efficient fine-tuning of large-scale pre-trained language modelsNature Machine Intelligence, 2023
- Social media for emergency rescue: An analysis of rescue requests on Twitter during Hurricane HarveyInternational Journal of Disaster Risk Reduction, 2022
- Venice Was Flooding ... One Tweet at a TimeProceedings of the ACM on Human-Computer Interaction, 2022
- MEDIC: a multi-task learning dataset for disaster image classificationNeural Computing and Applications, 2022
- Detecting Natural Hazard-Related Disaster Impacts with Social Media Analytics: The Case of Australian States and TerritoriesSustainability, 2022
- Disaster early warning and damage assessment analysis using social media data and geo-location informationDecision Support Systems, 2018