Data Integration for the Development of a Seismic Loss Prediction Model for Residential Buildings in New Zealand

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1168)


In 2010–2011, New Zealand experienced the most damaging earthquakes in its history. It led to extensive damage to Christchurch buildings, infrastructure and its surroundings; affecting commercial and residential buildings. The direct economic losses represented 20% of New Zealand’s GDP in 2011. Owing to New Zealand’s particular insurance structure, the insurance sector contributed to over 80% of losses for a total of more than NZ$31 billion. Amongst this, over NZ$11 billion of the losses arose from residential building claims and were covered either partially or entirely from the NZ government backed Earthquake Commission (EQC) cover insurance scheme. In the process of resolving the claims, EQC collected detailed financial loss data, post-event observations and building characteristics for each of the approximately 434,000 claims lodged following the Canterbury Earthquake sequence (CES). Added to this, the active NZ earthquake engineering community treated the event as a large scale outdoor experiment and collected extensive data on the ground shaking levels, soil conditions, and liquefaction occurrence throughout wider Christchurch. This paper discusses the necessary data preparation process preceding the development of a machine learning seismic loss model. The process draws heavily upon using Geographic Information System (GIS) techniques to aggregate relevant information from multiple databases interpolating data between categories and converting data between continuous and categorical forms. Subsequently, the database is processed, and a residential seismic loss prediction model is developed using machine learning. The aim is to develop a ‘grey-box’ model enabling human interpretability of the decision steps.


Seismic loss Christchurch earthquake sequence Data aggregation using GIS 



We acknowledge EQC for generously providing the claim data to realize this study. Many thanks to Geoffrey Spurr for his interpretation, assistance and review of the paper. We gratefully acknowledge the New Zealand Society for Earthquake Engineering (NZSEE) for the financial support. Thanks also goes to Dr. Sjoerd Van Ballegooy for his insightful advices.


  1. 1.
    Bevere, L., Balz, G.: Lessons from recent major earthquakes. Technical report, Swiss Reinsurance Company Ltd., Zurich, Switzerland (2012).
  2. 2.
    Deloitte Access Economics: Four years on: Insurance and the Canterbury Earthquakes. Technical report, February, Deloitte Access Economics (2015).
  3. 3.
    Drayton, M.J., Verdon, C.L.: Consequences of the Canterbury earthquake sequence for insurance loss modelling. In: 2013 New Zealand Society for Earthquake Engineering Conference, pp. 1–7 (2013).
  4. 4.
    Earthquake Commission (EQC): Budget Announcement: EQC levy to increase (2017).
  5. 5.
    Earthquake Commission (EQC): EQC Insurance (2019).
  6. 6.
    Earthquake Commission (EQC): EQC welcomes Act changes and gets ready to respond (2019).
  7. 7.
    Earthquake Commission (EQC): International reinsurers continue to provide cover to EQC (2019).
  8. 8.
    Earthquake Commission (EQC): The Natural Disaster Fund (2019).
  9. 9.
    Earthquake Commission (EQC), Ministry of Business Innovation and Employment (MBIE), New Zealand Government: New Zealand Geotechnical Database (NZGD) (2012).
  10. 10.
    Elwood, K.J., et al.: Preface earthquake spectra. Earthq. Spectra 30(1), fmi-fmix (2014).
  11. 11.
    Feltham, C.: Insurance and reinsurance issues after the Canterbury earthquakes (2011).
  12. 12.
    GeoNet: M 7.2 Darfield (Canterbury), 4 September 2010 (2010).
  13. 13.
    GeoNet: M 6.2 Christchurch, 22 February 2011 (2011).
  14. 14.
    GeoNet: GeoNet strong-motion FTP site (2012).
  15. 15.
    GNS (Geological and Nuclear Sciences Ltd.): RiskScape User Technical Documentation Wiki (2017).
  16. 16.
    Greater Christchurch Group - Department of the Prime Minister and Cabinet: Whole of Government Report: Lessons from the Canterbury Earthquake Sequence. Tech. rep., Greater Christchurch Group, Department of the Prime Minister and Cabinet, Christchurch, New Zealand (2017).
  17. 17.
    Insurance Council of New Zealand (ICNZ): Cantebury Earthquakes (2019).
  18. 18.
    Kam, W.Y., Pampanin, S., Elwood, K.: Seismic performance of reinforced concrete buildings in the 22 February Christchurch (Lyttelton) earthquake. Bull. N. Z. Soc. Earthq. Eng. 44(4), 239–278 (2011).
  19. 19.
    Kim, J.J., Elwood, K.J., Marquis, F., Chang, S.E.: Factors influencing post-earthquake decisions on buildings in Christchurch, New Zealand. Earthq. Spectra 33(2), 623–640 (2017). Scholar
  20. 20.
    King, A., Middleton, D., Brown, C., Johnston, D., Johal, S.: Insurance: its role in recovery from the 2010–2011 Canterbury earthquake sequence. Earthq. Spectra 30(1), 475–491 (2014). Scholar
  21. 21.
    Land Information New Zealand (LINZ): LINZ Data Services (2019).
  22. 22.
    Land Resource Information Systems (LRIS): Christchurch City Soil Map (2010).
  23. 23.
    Middleton, D.A.: EQC’s use of computer modelling in a catastrophe response. In: Proceedings of 2002 Annual Conference of the New Zealand Society for Earthquake Engineering (2002).
  24. 24.
    Munich RE: NatCatSERVICE (2019).
  25. 25.
    New Zealand Government: Canterbury maps - Liquefaction Susceptibility - Final (2017).
  26. 26.
  27. 27.
    Shephard, R.B., Spurr, D.D., Walker, G.R.: The Earthquake Commission’s earthquake insurance loss model. In: Proceedings of 2002 Annual Conference of the New Zealand Society for Earthquake Engineering (2002).
  28. 28.
    Tveite, H.: QGIS NNJoin plugin (2019).

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.The University of AucklandAucklandNew Zealand

Personalised recommendations