用大模型融合图文气象数据，提升灾情分类准确率
Can We Predict the Unpredictable? Leveraging DisasterNet-LLM for Multimodal Disaster Classification
- 构建专用大模型，通过跨模态注意力融合多源信息
- 在多个指标上超越现有方法，最高准确率达89.5%
- 适合灾害监测、应急响应等需要快速研判的场景
有效的灾害管理需要及时准确的洞察，但传统方法难以整合图像、气象记录和文本报告等多模态数据。为此，我们提出DisasterNet-LLM，一种专用于全面灾害分析的大语言模型。通过先进预训练、跨模态注意力机制和自适应变换器，DisasterNet-LLM在灾害分类任务中表现优异。实验表明，其在多模态灾害分类任务中达到89.5%的准确率、88.0%的F1分数、0.92的AUC值和0.88的BERTScore，显著优于现有最优模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。