Estimation of seismic building structural types using multi-sensor remote sensing and machine learning techniques

Abstract

Detailed information about seismic building structural types (SBSTs) is crucial for accurate earthquake vulnerability and risk modeling as it reflects the main load-bearing structures of buildings and, thus, the behavior under seismic load. However, for numerous urban areas in earthquake prone regions this information is mostly outdated, unavailable, or simply not existent. To this purpose, we present an effective approach to estimate SBSTs by combining scarce in situ observations, multi-sensor remote sensing data and machine learning techniques. In particular, an approach is introduced, which deploys a sequential procedure comprising five main steps, namely calculation of features from remote sensing data, feature selection, outlier detection, generation of synthetic samples, and supervised classification under consideration of both Support Vector Machines and Random Forests. Experimental results obtained for a representative study area, including large parts of the city of Padang (Indonesia), assess the capabilities of the presented approach and confirm its great potential for a reliable area-wide estimation of SBSTs and an effective earthquake loss modeling based on remote sensing, which should be further explored in future research activities.

Feasibility of Machine Learning Methods for Separating Wood And Leaf Points From Terrestrial Laser Scanning Data

“…Moreover, feature selection may attenuate the over-fitting problem in multivariate classification methods (Geiß et al, 2015). Feature selection methods can be grouped into three categories; wrappers, embedded, and filters (Guyon et al, 2008).…”

“…The class determina- tion is based on a majority votes fashion. RF has proven to be an accurate and robust classification and regression approach, even on noisy data (Geiß et al, 2015).…”

One step back for a leap forward: toward operational measurements of elements at risk

“…For instance, Taubenböck (2015) characterize the built environment with remote sensing data and retrieve specific fragility functions or damage probability matrices, respectively, for designated building types. In contrast to that, e.g., Borfecchia et al (2010), and Geiß et al (2014Geiß et al ( , 2015 combine limited in situ ground truth building inventory data with features from remote sensing and use techniques of statistical inference for a complete labelling of the residual building inventory according to relevant vulnerability levels. Similar methodological principles were exploited by Wieland et al (2012), Pittore and Wieland (2013), and Geiß et al (2016) to assess seismic vulnerability on an aggregated spatial level to allow for covering larger areas.…”

Efficient DANNLO Classifier for Multi-class Imbalanced Data on Hadoop

“…Tobia Lakes et al [23] proposed an effectiveapproach to estimate SBSTs (seismic building structural types) by combining scarce in situ observations, multi-sensor remote sensingdata and machine learning techniques.Experimental outcomes obtained fora representative study area and evaluate the capacities of the exhibited approach.It confirm its great potential for a reliable area-wide estimation of SBSTs andan effective earthquake loss modeling based on remote sensing, which ought to be additionally investigated in future research exercises.The drawback is the high algorithmic complexity and extensive memory requirements of the required quadratic programming in large-scale tasks.…”