Humanitarian AI

This project develops cutting-edge methods at the intersection of computer vision, natural language processing, and remote sensing to tackle humanitarian challenges such as situational awareness, damage assessment, and urgent needs identification. Our work includes designing remote sensing pipelines that integrate satellite imagery, geospatial data, and AI models for rapid disaster mapping; building geospatially aware large language models and multi-agent systems for complex spatial reasoning; advancing LLMs and VLMs for disaster scene understanding through object detection and visual question answering; creating multimodal foundation models that fuse imagery, video, and text to enhance decision-making; and leveraging LLMs for anticipatory thinking to better prepare for climate-induced events. Through these efforts, we aim to push the boundaries of AI research while delivering practical tools with real-world humanitarian and societal impact.

Hamad Bin Khalifa University (HBKU)