Rapid Building Damage Estimation through Data Integration

From remote sensing to crowdsourcing, an overwhelming amount of building damage data is produced after disasters. While this amount of data signifies impressive technological progress, it does not necessarily mean that all building damage data is usable for post-earthquake decision-making. In fact, too much information can be overwhelming to disaster responders who are making decisions in a fast-paced response environment.

We have applied geostatistical methods to integrate forecasts and remote sensing-derived estimates of damage with a limited sample of field surveys to rapidly estimate building damage after disasters. These methods were originally tested using real data from the 2015 Nepal Earthquake, and we have expanded testing to three additional events, including the 2010 Haiti Earthquake, February 2011 Christchurch, New Zealand Earthquake, and the 2016 Central Italy earthquakes. By developing and evaluating these methods using real data from earthquakes that occurred in a wide range of contexts, we are able to show that data integration can lead to more accurate building damage estimates that are flexible to different patterns of building damage and varying sources of data availability.