摘要
Existing approaches to risk assessment in natural disasters usually suffer from information specificity and data density. For example, road vulnerability assessment requires disaster information on the neighbors of all road segments, but weather stations may be far from such locations. The widely used intensity–duration–frequency analysis is too rough to overcome the tradeoff between estimation accuracy and reliability for assessing road vulnerability. Therefore, this study proposes a machine learning method to replace the frequency-style vulnerability with an intelligent measure, which will enhance the assessment by predicting the missing weather information at all road segments. Compared with conventional interpolation methods, our Markov chain random field kriging can reliably estimate the ungauged information when available stations are distributed asymmetrically. Therefore, our model contributes to the assessment methods by providing accurate and reliable vulnerability information for the transportation network under contemporary changing weather conditions. Through elaborate proofs to demonstrate the theoretical validity of our mathematical results, empirical results are also presented for application to practical governance. The empirical accuracy of 0.3 normalized root mean square error for disasters of storms and earthquakes is sufficient to convince local authorities to change their existing methods. The resulting regionalization in road network vulnerability is also tailor-made for practical applicability.