# UrbanResilience.AI Lab

> The UrbanResilience.AI Lab at Texas A&M University, directed by Dr. Ali Mostafavi, develops artificial intelligence — large language models, vision-language models, foundation models, and agentic AI systems — for disaster management and urban resilience. A world-leading research lab in Disaster AI.

## What we do

We build AI that reasons across the connected systems disasters unfold through — hazards, infrastructure, and people — with an emphasis on transferable representations of hazard and risk, auditable pictures of evolving conditions, agentic information seeking, and connecting intelligence to the decisions communities actually face.

## Director

- **Dr. Ali Mostafavi** — Zachry Endowed Professor, Zachry Department of Civil and Environmental Engineering, Texas A&M University. Director of Disaster AI at the Institute for a Disaster Resilient Texas (IDRT).
- Email: mostafavi@tamu.edu
- Google Scholar: https://scholar.google.com/citations?user=DFNvQPYAAAAJ
- X / Twitter: https://twitter.com/ResilienceTAMU

## Research directions

1. **Geospatial Reasoning** — AI that reasons over spatial data grounded in expert knowledge.
2. **Disaster Foundation Models** — transferable representations of hazard, risk, and resilience.
3. **World Models** — an auditable, evolving picture of community conditions.
4. **Agentic Reasoning & Information Seeking** — LLM agents that plan and use disaster-response tools.
5. **Cascading Impacts & Decision-Flow AI** — connecting intelligence to real decisions.
6. **Flood & Wildfire Intelligence** — hazard-specific AI methods and applications.

## Selected recent publications

- DisastQA: A Comprehensive Benchmark for Evaluating Question Answering in Disaster Management — https://arxiv.org/abs/2601.03670 (2026)
- DisasterBench: Benchmarking LLM Planning under Typed Tool Interface Constraints — https://arxiv.org/abs/2605.27957 (2026)
- DisasterLex: An Expert Concept-to-Schema Knowledge Graph for Geospatial Reasoning in Disaster Analytics — https://arxiv.org/abs/2605.30538 (2026)
- Data-Efficient Flood Depth Prediction through Domain-Aware Coreset Selection and Tabular Foundation Models — https://arxiv.org/abs/2606.05265 (2026)
- Automated Wildfire Damage Assessment from Multi-view Ground-level Imagery via Vision-Language Models — https://arxiv.org/abs/2509.01895 (2025)
- Disaster Management in the Era of Agentic AI Systems — https://arxiv.org/abs/2510.16034 (2025)
- Recov-Vision: Linking Street View Imagery and Vision-Language Models for Post-Disaster Recovery — https://arxiv.org/abs/2509.20628 (2025)
- CrisisSense-LLM: Instruction Fine-Tuned LLM for Multi-label Social Media Text Classification in Disaster Informatics — https://arxiv.org/abs/2406.15477 (2024)

## Recognition

- 2025 ASCE Walter L. Huber Civil Engineering Research Prize (Ali Mostafavi)
- 2023 ASCE Daniel W. Halpin Award for Scholarship in Construction
- NSF CAREER Award; Early-Career Research Fellowship, National Academies' Gulf Research Program
- Research featured by CNN, NSF, Scientific American, and ASCE Source

## How to join

- PhD students: fully-funded research assistantships each spring and fall. Email Dr. Mostafavi (mostafavi@tamu.edu) with CV + a statement of research experience and interests.
- Postdocs: open positions evaluated case by case, focused on AI methods for disaster resilience.
- Visiting scholars & interns: self-funded, evaluated case by case.
- TAMU undergraduate and master's students: research projects available — email Dr. Mostafavi.

## Site map

- Home: https://urbanresilience.ai/
- Research: https://urbanresilience.ai/research
- People: https://urbanresilience.ai/people
- News: https://urbanresilience.ai/news
- Publications: https://urbanresilience.ai/publications
- Director profile: https://urbanresilience.ai/people/ali-mostafavi
- Join Us: https://urbanresilience.ai/join-us
- Contact: https://urbanresilience.ai/contact

## Affiliation

Zachry Department of Civil and Environmental Engineering, Texas A&M University, 3136 TAMU, College Station, TX 77843, USA.