No abstract

This paper describes statistical procedures for developing earthquake damage fragility functions. Although fragility curves abound in earthquake engineering and risk assessment literature, the focus has generally been on the methods for obtaining the damage data (i.e., the analysis of structures), and little emphasis is placed on the process for fitting fragility curves to this data. This paper provides a synthesis of the most commonly used methods for fitting fragility curves and highlights some of their significant limitations. More novel methods are described for parametric fragility curve development (generalized linear models and cumulative link models) and non-parametric curves (generalized additive model and Gaussian kernel smoothing). An extensive discussion of the advantages and disadvantages of each method is provided, as well as examples using both empirical and analytical data. The paper further proposes methods for treating the uncertainty in intensity measure, an issue common with empirical data. Finally, the paper describes approaches for choosing among various fragility models, based on an evaluation of prediction error for a user-defined loss function.

This paper is NOT THE PUBLISHED VERSION; but the author's final, peer-reviewed manuscript. The published version may be accessed by following the link in th citation below.

The ability to rapidly assess the spatial distribution and severity of building damage is essential to post-event emergency response and recovery. Visually identifying and classifying individual building damage requires significant time and personnel resources and can last for months after the event. This article evaluates the feasibility of using machine learning techniques such as discriminant analysis, k-nearest neighbors, decision trees, and random forests, to rapidly predict earthquake-induced building damage. Data from the 2014 South Napa earthquake are used for the study where building damage is classified based on the assigned Applied Technology Council (ATC)-20 tag (red, yellow, and green). Spectral acceleration at a period of 0.3 s, fault distance, and several building specific characteristics (e.g. age, floor area, presence of plan irregularity) are used as features or predictor variables for the machine learning models. A portion of the damage data from the Napa earthquake is used to obtain the forecast model, and the performance of each machine learning technique is evaluated using the remaining (test) data. It is noted that the random forest algorithm can accurately predict the assigned tags for 66% of the buildings in the test dataset.

Predicting the dissolution rates of silicate glasses in aqueous conditions is a complex task as the underlying mechanism(s) remain poorly understood and the dissolution kinetics can depend on a large number of intrinsic and extrinsic factors. Here, we assess the potential of data-driven models based on machine learning to predict the dissolution rates of various aluminosilicate glasses exposed to a wide range of solution pH values, from acidic to caustic conditions. Four classes of machine learning methods are investigated, namely, linear regression, support vector machine regression, random forest, and artificial neural network. We observe that, although linear methods all fail to describe the dissolution kinetics, the artificial neural network approach offers excellent predictions, thanks to its inherent ability to handle non-linear data. Overall, we suggest that a more extensive use of machine learning approaches could significantly accelerate the design of novel glasses with tailored properties.