Gabriela Gesualdo, postdoctoral researcher in the Department of Geosciences at Penn State, will give the talk "Beyond hazard forecasting: AI-driven insights into disaster impacts and humanitarian response," at 2 p.m. on Friday, Oct. 23, in 117 Earth and Engineering Sciences Building on the University Park campus. The talk will also be available via Zoom.
The event is part of a fall seminar series hosted by TRAnscendIng Natural hazards forecasting (TRAIN). The talk is free and open to the public.
Research on natural hazards often focuses on categorizing these hazards and improving prediction capabilities. However, the societal impact of natural hazards, and the humanitarian response, is a critical aspect of mitigating risk that is often more challenging to study.
"We have the data, but much of this information is embedded in large collections of unstructured reports, which are difficult to analyze systematically at regional to global scales." Gesualdo said. "Recent advances in natural language processing and large language models offer new opportunities to transform these textual sources into structured and actionable disaster information."
Gesualdo will present two studies that use text-based data to better understand disaster impacts and humanitarian response. One focuses on the asymmetries between disaster impacts and humanitarian response worldwide, and the other introduces a database of disaster impacts in the Global South to extract and structure information on disaster consequences.
"Together, these studies demonstrate how AI-assisted approaches can expand the evidence base for disaster research, particularly in regions where conventional impact databases remain incomplete," Gesualdo said. "These emerging datasets can complement hazard forecasting by improving our understanding of where, how and for whom disasters generate impacts."
Gesualdo's work focuses on water resources planning under compound climate events and systemic complexity. She holds a bachelor of science in environmental engineering and a master of science in environmental technologies from the Federal University of Mato Grosso do Sul, Brazil, and a doctorate in hydraulic engineering and sanitation from the University of São Paulo. Her research advances decision-making for sustainable water resources management in the context of intensifying hydrological extremes. She investigates how hydroclimatic hazards interact with human systems to shape water security, vulnerability, and adaptive capacity, with the goal of informing strategies that enhance resilience to droughts, floods, and cascading hydroclimatic risks across spatial and temporal scales.
About TRAIN
TRAIN is an initiative through the Earth and Environmental Systems Institute (EESI) that aims to transform complex geophysical and atmospheric data and bridge the gap between raw information and community resilience. TRAIN aims to build the community at Penn State to become nationally recognized for research innovation to respond proactively to funding opportunities and coordinate natural hazard responses.
