It is vital that we develop appropriate statistical models to represent and extract valuable insights from these large datasets, since the bridges constitute critical infrastructure within modern transportation networks. The process of monitoring engineered systems via streaming data is typically referred to as Structural Health Monitoring (SHM) and while successful applications have been emerging in recent years, a number of challenges remain for practical implementation [5]. During model design, these concerns usually centre around low variance data: that is, measurements are not available for the entire range of expected operational, environmental, and damage conditions. Consider a bridge following construction, this will have a relatively small dataset that should only be associated with normal operation. On the other hand, a structure with historical data might still not experience low-probability events - such as extreme weather or landslides. An obvious solution considers sharing data (or information) between structures; this has been the focus of a large body of recent work [6-8].

Multilevel modelling is a technique for dealing with grouped or clustered data. Multilevel modelling can also be used to examine data with repeated measures. For example, if we are monitoring the blood pressure of a patient group on a regular basis, the subsequent measures might be thought of as being grouped within the individual subjects. It is capable of handling data with varying measurement times from one element to the next. In such instances, a multilevel model in ML can be used to simulate the parameters that change at more than one level.

Multilevel modeling can be used to handle clustered or grouped data. Data with repeated measures can also be analyzed using multilevel modelling. The MLM is used to examine individuals embedded within regions or countries. It allows regression equations at the level of the individual and the estimation of inter-individual differences in intra-individual change over time by modelling the variances and covariances. An MLM in machine learning can be applied to the parameters that vary at more than one level.