mlsanityData to 7 Oct 2026

CrisiSense-RAG: Crisis Sensing Multimodal Retrieval-Augmented Generation for Rapid Disaster Impact Assessment

arXiv 2602.13239 ↗First posted 30 Jan 2026cs.CY cs.CV cs.IRcited by 3

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

Abstract (arXiv)

Timely and spatially resolved disaster impact assessment is essential for effective emergency response. However, automated methods typically struggle with temporal asynchrony. Real-time human reports capture peak hazard conditions while high-resolution satellite imagery is frequently acquired after peak conditions. This often reflects flood recession rather than maximum extent. Naive fusion of these misaligned streams can yield dangerous underestimates when post-event imagery overrides documented peak flooding. We present CrisiSense-RAG, which is a multimodal retrieval-augmented generation framework that reframes impact assessment as evidence synthesis over heterogeneous data sources without disaster-specific fine-tuning. The system employs hybrid dense-sparse retrieval for text sources and CLIP-based retrieval for aerial imagery. A split-pipeline architecture feeds into asynchronous fusion logic that prioritizes real-time social evidence for peak flood extent while treating imagery as persistent evidence of structural damage. Evaluated on Hurricane Harvey across 207 ZIP-code queries, the framework achieves a flood extent MAE of 10.94% to 28.40% and damage severity MAE of 16.47% to 21.65% in zero-shot settings. Prompt-level alignment proves critical for quantitative validity because metric grounding improves damage estimates by up to 4.75 percentage points. These results demonstrate a practical and deployable approach to rapid resilience intelligence under real-world data constraints.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 24 of its 54 references that are in the map. First posted on arXiv 30 Jan 2026.

Builds on

24 of 54 references.

References · 24

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  3. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 556
  4. 2022MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Textcited by 216
  5. 2020FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understandingcited by 181
  6. 2019xBD: A Dataset for Assessing Building Damage from Satellite Imagerycited by 138
  7. 2024MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Modelscited by 84
  8. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
  9. 2025Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generationcited by 42
  10. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directionscited by 30
  11. 2024CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informaticscited by 25
  12. 2022Large-scale Building Damage Assessment using a Novel Hierarchical Transformer Architecture on Satellite Imagescited by 24
12 more
  1. 2024REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Modelscited by 21
  2. 2022Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understandingcited by 18
  3. 2020A Hybrid Deep Learning Model for Predictive Flood Warning and Situation Awareness using Channel Network Sensors Datacited by 10
  4. 2024ELEV-VISION-SAM: Integrated Vision Language and Foundation Model for Automated Estimation of Building Lowest Floor Elevationcited by 9
  5. 2025DamageCAT: A Deep Learning Transformer Framework for Typology-Based Post-Disaster Building Damage Categorizationcited by 8
  6. 2025Empowering LLM Agents with Geospatial Awareness: Toward Grounded Reasoning for Wildfire Responsecited by 8
  7. 2024FloodDamageCast: Building Flood Damage Nowcasting with Machine Learning and Data Augmentationcited by 4
  8. 2025Disaster Management in the Era of Agentic AI Systems: A Vision for Collective Human-Machine Intelligence for Augmented Resiliencecited by 4
  9. 2025DisastIR: A Comprehensive Information Retrieval Benchmark for Disaster Managementcited by 3
  10. 2025Flood-DamageSense: Multimodal Mamba with Multitask Learning for Building Flood Damage Assessment using SAR Remote Sensing Imagerycited by 3
  11. 2025Recov-Vision: Linking Street View Imagery and Vision-Language Models for Post-Disaster Recoverycited by 2
  12. 2024Multi-step feature fusion for natural disaster damage assessment on satellite imagescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026DisasterLex: An Expert Concept-to-Schema Knowledge Graph for Geospatial Reasoning in Disaster Analyticscited by 0
  2. 2026Data-efficient flood depth prediction through domain-aware coreset selection and tabular foundation modelscited by 0
  3. 2026GeoArbiter: Verifiability-Guided Grounding for Remote-Sensing Multimodal LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Multimodal, Multilingual, and Multidimensional Pipeline for Fine-grained Crowdsourcing Earthquake Damage Evaluation
  2. 2026Obshazard-bench: Benchmarking Multimodal Foundation Models for Real-Time Disaster Intelligence from Raw Earth Observation Streams
  3. 2023FloodBrain: Flood Disaster Reporting by Web-based Retrieval Augmented Generation with an LLM
  4. 2025MONITRS: Multimodal Observations of Natural Incidents Through Remote Sensing
  5. 2026RAPTOR-AI for Disaster OODA Loop: Hierarchical Multimodal RAG with Experience-Driven Agentic Decision-Making
  6. 2025A Multimodal RAG Framework for Housing Damage Assessment: Collaborative Optimization of Image Encoding and Policy Vector Retrieval
  7. 2026DisastRAG: A Multi-Source Disaster Information Integration and Access System Based on Retrieval-Augmented Large Language Models
  8. 2026DisasterVQA: A Visual Question Answering Benchmark Dataset for Disaster Scenes