Deep Learning for Safer School Infrastructure: An Interdisciplinary and Cross-organizational Collaboration

Abstract

Interdisciplinary and cross-organizational collaborations can be educationally transformative. As part of such partnerships, students are expected to work innovatively across disciplinary boundaries, bringing their diverse perspectives to bear on complex, real-world problems. In this paper, we explore the outcomes of such a collaborative effort among teams of university students and the World Bank to develop a technical solution to the long-standing problem of identifying the most vulnerable school building infrastructures in hard-to-reach areas of developing countries. Worldwide, natural disasters like earthquakes and cyclones put more than a million school buildings at risk of collapse, and an estimated 875 million children and teachers at risk of harm. Together with the Global Program for Safer Schools of the World Bank, the student teams worked across classrooms and disciplines to design a tool that can save time and money in determining the structural type of school buildings to assess their vulnerability. Under this collaboration, students felt empowered working on such a highly impactful international development project involving real-world challenges, and considered it a transformative learning experience.