Researchers from the Department of Geography, Central University of South Bihar (CUSB), have developed an innovative GeoAI-based framework to assess school exposure to varying flood-depth scenarios in flood-prone regions of Bihar in collaboration with Arizona State University, USA. The research has been published in the internationally reputed Natural Hazards, Springer Nature (Q1, IF = 3.7). The paper, titled “Developing a framework for assessment of the school’s exposure to flood-depth scenarios: a case study of Darbhanga, Bihar, India,” has been authored by Chandrakanta Bishui, Somnath Bera, Shivam Priyadarshi, Pritha Ghosh, and Kshitij Dahal. According to the study, floods frequently disrupt educational infrastructure in Bihar, affecting student safety, attendance, and learning continuity. Schools often function as emergency shelters during disasters, making it crucial to assess their vulnerability under different flood conditions.Using Google Earth Engine (GEE) and a machine learning model, the research team generated flood depth susceptibility maps for three depth categories: below 1.5 meters, 1.5–3 meters, and above 3 meters. A spatial analysis of 2,010 schools in Darbhanga district was conducted. The findings reveal that nearly 20 percent of the district has a high probability of experiencing floods exceeding 3 meters in depth. Under extreme flood scenarios, 43 schools were identified within high-susceptibility zones. The study also highlights that rural schools are comparatively more vulnerable than urban schools. Leading the research, Dr. Somnath Bera, assistant professor of the Geography Department, said, “The proposed framework offers a scientific basis for disaster-resilient educational infrastructure planning. It can assist policymakers in prioritising flood-resilient school construction, retrofitting, and emergency preparedness. The framework is scalable and can be applied to other flood-prone regions across India”.