Infrastructure recovery curve estimation using Gaussian process regression on expert elicited data

Infrastructure recovery time estimation is critical to disaster management and planning. Inspired by recent resilience planning initiatives, we consider a situation where experts are asked estimate the for different infrastructure systems recover certain functionality levels after scenario hazard event. We propose methodological framework use expert-elicited data expected curve of particular system. This uses Gaussian process regression (GPR) capture experts' estimation-uncertainty satisfy known physical constraints processes. The designed find balance between collection cost expert elicitation prediction accuracy GPR. evaluate on realistically simulated concerning two case study events, 1995 Great Hanshin-Awaji Earthquake 2011 East Japan Earthquake.