Syndicate content

Build Back better

Resilient housing joins the machine learning revolution

Sarah Elizabeth Antos's picture
Also available in: Español | Français  | 中文 

 World Bank

Machine learning algorithms are excellent at answering “yes” or “no” questions. For example, they can scan huge datasets and correctly tell us: Does this credit card transaction look fraudulent? Is there a cat in this photo?

But it’s not only the simple questions – they can also tackle nuanced and complex questions.

Today, machine learning algorithms can detect over 100 types of cancerous tumors more reliably than a trained human eye. Given this impressive accuracy, we started to wonder: what could machine learning tell us about where people live? In cities that are expanding at breathtaking rates and are at risk from natural disasters, could it warn us that a family’s wall might collapse during an earthquake or rooftop blow away during a hurricane?

Five ways to do better post-disaster assessments

Joe Leitmann's picture
2017 damage and loss assessment following landslides and floods in Sierra Leone. Photo: World Bank
2017 damage and loss assessment following landslides and floods in Sierra Leone. (Photo: World Bank)

Post-disaster assessments changed my life by starting my career in disaster risk management. Three months after arriving in Indonesia as the World Bank’s environment coordinator, the Indian Ocean tsunami and related earthquakes struck Aceh and Nias at the end of 2004. I was asked to pull together the economic evaluation of the disaster’s environmental impact as part of what was then known as a damage-and-loss assessment. Subsequently, the World Bank, United Nations and European Union agreed on a joint approach to crisis response in 2008, including a common methodology for post-disaster needs assessment (PDNA).

Now that we have a decade of experience with this approach, what have we learned and how can we do a better job in the future?