The field of emergency response and data-driven decision making is rapidly evolving, with a focus on developing innovative solutions to mitigate the impact of disasters and improve public safety. Recent research has emphasized the importance of optimizing resource allocation, leveraging machine learning models, and integrating data-driven approaches to enhance emergency preparedness and response. Notably, the development of multi-objective optimization models and data-driven frameworks has shown promise in identifying high-risk areas and populations, and informing targeted interventions. Furthermore, the application of advanced visualization techniques and authoring tools has improved the effectiveness of data-driven storytelling and decision making.

Some noteworthy papers in this regard include: From Occurrence to Consequence, which presents a comprehensive data-driven analysis of building fire risk and identifies key risk factors influencing fire occurrence and consequences. DATAWEAVER, which introduces an integrated authoring framework and system for creating data-driven narratives through the composition of visualization and text. RefChartQA, which proposes a novel benchmark for chart question answering with visual grounding, enabling models to refer elements at multiple granularities within chart images.