Prediction of potential seismic damage using classification and regression trees: a case study on earthquake damage data
- PDF / 1,094,881 Bytes
- 18 Pages / 439.37 x 666.142 pts Page_size
- 31 Downloads / 177 Views
Prediction of potential seismic damage using classification and regression trees: a case study on earthquake damage databases from Turkey Fatma Yerlikaya‑Özkurt1 · Aysegul Askan2 Received: 1 April 2020 / Accepted: 16 June 2020 © Springer Nature B.V. 2020
Abstract Seismic damage estimation is an important key ingredient of seismic loss modeling, risk mitigation and disaster management. It is a problem involving inherent uncertainties and complexities. Thus, it is important to employ robust approaches which will handle the problem accurately. In this study, classification and regression tree approach is applied on damage data sets collected from reinforced concrete frame buildings after major previous earthquakes in Turkey. Four damage states ranging from None to Severe are used, while five structural parameters are employed as damage identifiers. For validation, results of classification analyses are compared against observed damage states. Results in terms of well-known classification performance measures indicate that when the size of the database is larger, the correct classification rates are higher. Performance measures computed for Test data set indicate similar success to that of Train data set. The approach is found to be effective in classifying randomly selected damage data. Keywords Earthquakes · Seismic damage · Classification and regression tree · Damage prediction
1 Introduction Major earthquakes worldwide cause significant damages to built environment. Seismic damage estimation is an important ingredient of seismic loss models and risk reduction approaches. It is particularly important to assess seismic damages accurately as they are used in risk mitigation, disaster planning and management. Similarly, seismic damage and intensity estimations are also employed in insurance premiums which is becoming mandatory in seismic areas globally (e.g., Ünal et al. 2017). Despite its significance, seismic * Aysegul Askan [email protected] Fatma Yerlikaya‑Özkurt [email protected] 1
Department of Industrial Engineering, Atılım University, 06830 Ankara, Turkey
2
Department of Civil Engineering, Middle East Technical University, 06800 Ankara, Turkey
13
Vol.:(0123456789)
Natural Hazards
damage estimation is challenging due to limitations arising from the sparse nature of major earthquakes, insufficient data and complexity of building behavior. Another source of uncertainty is the subjective bias in assigning damage states to structures in the field after an earthquake. Thus, damage estimation must be performed with robust approaches which will handle these inherent complexities. There are several approaches in the literature concerning damage estimation and modeling. The complexity and scope of these methods vary; however, the common objective is to classify the structural damage into different damage levels with selected damage parameters. Past approaches include analytical methods which require detailed structural analyses or empirical approaches such as damage probability matrices (DPM
Data Loading...
