Bulletin of Earthquake Engineering

, Volume 17, Issue 9, pp 4825–4853 | Cite as

A transferable remote sensing approach to classify building structural types for seismic risk analyses: the case of Val d'Agri area (Italy)

  • Mariangela LiuzziEmail author
  • Patrick Aravena Pelizari
  • Christian Geiß
  • Angelo Masi
  • Valerio Tramutoli
  • Hannes Taubenböck
Original Research


This study proposes a methodology based on machine learning (ML) algorithms for rapid and robust classification of building structural types (STs) in multispectral remote sensing imagery aiming to assess buildings’ seismic vulnerability. The seismic behavior of buildings is strongly affected by the ST, including material, age, height, and other main structural features. Previous works deployed in situ data integrated with remote sensing information to statistically infer STs through supervised ML methods. We propose a transferable methodology with specific focus on situations with imbalanced in situ data (i.e., the number of available labeled samples for model learning differs largely between different STs). We learn a transferable model by selecting features from an exhaustive set. The transferability relies on deploying geometric features characterizing individual buildings; thus, the model is less sensitive to domain adaption problems frequently induced by e.g., changes in acquisition parameters of remotely sensed imagery. Thereby, we show that few geometry features enable generalization capabilities similar to models learned with a large number of features describing spectral, geometrical or contextual building properties. We rely on an extensive geodatabase containing almost 18,000 building footprints. We follow a Random Forest (RF)-based feature selection strategy to objectively identify most valuable features for prediction. Furthermore, the problem of unbalanced classes is addressed by adopting two approaches: downsampling the majority class and modifying the classifier internally (weighted RF). The implemented model is transferred on the challenging urban morphology of the Val d’Agri area (Italy). Results confirm the statistical robustness of the model and the importance of the geometry features, allowing for reliable identification of STs.


Machine learning Remote sensing Seismic vulnerability Building structural type Building inventory Class imbalance 



  1. Allouche O, Tsoar A, Kadmon R (2006) Assessing the accuracy of species distribution models: prevalence, kappa and the true skill statistic (TSS). J Appl Ecol 43(6):1223–1232CrossRefGoogle Scholar
  2. Aravena Pelizari P, Spröhnle K, Geiß C, Schoepfer E, Plank S, Taubenböck H (2018) Multi-sensor feature fusion for very high spatial resolution built-up area extraction in temporary settlements. Remote Sens Environ 209:793–807CrossRefGoogle Scholar
  3. Balkaya C, Casciati F, Casciati S, Faravelli L, Vece M (2015) Real-time identification of disaster areas by an open-access vision-based tool. Adv Eng Softw 88:83–90CrossRefGoogle Scholar
  4. Belgiu M, Tomljenovic I, Lampoltshammer T, Blaschke T, Höfle B (2014) Ontology-based classification of building types detected from airborne laser scanning data. Remote Sens 6(2):1347–1366CrossRefGoogle Scholar
  5. Berger C, Voltersen M, Eckardt R, Eberle J, Heyer T, Salepci N, Hese S, Schmullius C, Tao J, Auer S, Bamler R (2013) Multi-modal and multi-temporal data fusion: outcome of the 2012 GRSS data fusion contest. IEEE J Sel Top Appl Earth Obs Remote Sens 6(3):1324–1340CrossRefGoogle Scholar
  6. Blaschke T (2010) Object based image analysis for remote sensing. ISPRS J Photogramm Remote Sens 65(1):2–16CrossRefGoogle Scholar
  7. Breiman L (2001) Random forests. Mach Learn 45(1):5–32CrossRefGoogle Scholar
  8. Bruzzone L, Carlin L (2006) A multilevel context-based system for classification of very high spatial resolution images. IEEE Trans Geosci Remote Sens 44(9):2587–2600CrossRefGoogle Scholar
  9. Calvi GM, Pinho R, Magenes G, Bommer JJ, Restrepo-Vélez LF, Crowley H (2006) Development of seismic vulnerability assessment methodologies over the past 30 years. ISET J Earthq Technol 43(3):75–104Google Scholar
  10. Casciati S, Chen ZC, Faravelli L, Vece M (2016) Synergy of monitoring and security. Smart Struct Syst 17(5):743–751CrossRefGoogle Scholar
  11. Chawla NV, Japkowicz N, Kotcz A (2004) Special issue on learning from imbalanced data sets. ACM SIGKDD Explor Newsl 6(1):1–6CrossRefGoogle Scholar
  12. Chen C, Liaw A, Breiman L (2004) Using random forest to learn imbalanced data. Univ Calif Berkeley 110:1–12Google Scholar
  13. Cheriyadat AM (2014) Unsupervised feature learning for aerial scene classification. IEEE Trans Geosci Remote Sens 52(1):439–451CrossRefGoogle Scholar
  14. Chiauzzi L, Masi A, Mucciarelli M, Vona M, Pacor F, Cultrera G, Gallovič F, Emolo A (2012) Building damage scenarios based on exploitation of Housner intensity derived from finite faults ground motion simulations. Bull Earthq Eng 10(2):517–545CrossRefGoogle Scholar
  15. Congalton RG, Green K (2008) Assessing the accuracy of remotely sensed data: principles and practices. CRC Press, Boca RatonCrossRefGoogle Scholar
  16. Dolce M, Masi A, Marino M, Vona M (2003) Earthquake damage scenarios of the building stock of Potenza (Southern Italy) including site effects. Bull Earthq Eng 1(1):115–140CrossRefGoogle Scholar
  17. Fardis MN (2009) Seismic design, assessment and retrofitting of concrete buildings: based on EN-Eurocode, vol 8. Springer, BerlinCrossRefGoogle Scholar
  18. Feller W (1968) The strong law of large numbers. In: Feller W (ed) An introduction to probability theory and its applications, vol 1(3). Wiley, New York, pp 243–245Google Scholar
  19. Ganganwar V (2012) An overview of classification algorithms for imbalanced datasets. Int J Emerg Technol Adv Eng 2(4):42–47Google Scholar
  20. Geiß C, Taubenböck H, Tyagunov S, Tisch A, Post J, Lakes T (2014) Assessment of seismic building vulnerability from space. Earthq Spectra 30(4):1553–1583CrossRefGoogle Scholar
  21. Geiß C, Aravena Pelizari P, Marconcini M, Sengara W, Edwards M, Lakes T, Taubenböck H (2015) Estimation of seismic building structural types using multi-sensor remote sensing and machine learning techniques. ISPRS J Photogramm Remote Sens 104:175–188CrossRefGoogle Scholar
  22. Geiß C, Jilge M, Lakes T, Taubenböck H (2016) Estimation of seismic vulnerability levels of urban structures with multisensor remote sensing. IEEE J Sel Top Appl Earth Obs Remote Sens 9(5):1913–1936CrossRefGoogle Scholar
  23. Geiß C, Aravena Pelizari P, Schrade H, Brenning A, Taubenböck H (2017) On the effect of spatially non-disjoint training and test samples on estimated model generalization capabilities in supervised classification with spatial features. IEEE Geosci Remote Sens Lett 14(11):2008–2012CrossRefGoogle Scholar
  24. Genuer R, Poggi JM, Tuleau C (2008) Random forests: some methodological insights. arXiv preprint arXiv:0811.3619
  25. Géron A (2017) Hands-on machine learning with Scikit-Learn and TensorFlow: concepts, tools, and techniques to build intelligent systems. O’Reilly Media Inc, NewtonGoogle Scholar
  26. Gil J, Beirão JN, Montenegro N, Duarte JP (2012) On the discovery of urban typologies: data mining the many dimensions of urban form. Urban Morphol 16(1):27Google Scholar
  27. Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3(March):1157–1182Google Scholar
  28. Haralick RM, Shanmugam K (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 6:610–621CrossRefGoogle Scholar
  29. Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference and prediction. Springer, New York, 763 ppCrossRefGoogle Scholar
  30. He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 9:1263–1284Google Scholar
  31. Hermosilla T, Palomar-Vázquez J, Balaguer-Beser Á, Balsa-Barreiro J, Ruiz LA (2014) Using street based metrics to characterize urban typologies. Comput Environ Urban Syst 44:68–79CrossRefGoogle Scholar
  32. INGV – Instituto Nazionale di Geofisica e Vulcanologia (2018) Database of individual seismogenic source. DISS version 3. Accessed 23 Feb 2017
  33. Jeni LA, Cohn JF, De La Torre F (2013) Facing imbalanced data-recommendations for the use of performance metrics. In 2013 humaine association conference on affective computing and intelligent interaction. IEEE, pp 245–251Google Scholar
  34. Khalilia M, Chakraborty S, Popescu M (2011) Predicting disease risks from highly imbalanced data using random forest. BMC Med Inform Decis Mak 11(1):51CrossRefGoogle Scholar
  35. Klotz M, Kemper T, Geiß C, Esch T, Taubenböck H (2016) How good is the map? A multi-scale cross-comparison framework for global settlement layers: evidence from Central Europe. Remote Sens Environ 178:191–212CrossRefGoogle Scholar
  36. KrishnaVeni CV, Sobha Rani T (2011) On the classification of imbalanced datasets. IJCST 2(SP1):145–148Google Scholar
  37. Leichtle T, Geiß C, Wurm M, Lakes T, Taubenböck H (2017) Unsupervised change detection in VHR remote sensing imagery: an object-based clustering approach in a dynamic urban environment. Int J Appl Earth Obs Geoinf 54:15–27CrossRefGoogle Scholar
  38. Leinenkugel P, Esch T, Kuenzer C (2011) Settlement detection and impervious surface estimation in the Mekong Delta using optical and SAR remote sensing data. Remote Sens Environ 115(12):3007–3019CrossRefGoogle Scholar
  39. Masi A (2003) Seismic vulnerability assessment of gravity load designed R/C frames. Bull Earthq Eng 1(3):371–395CrossRefGoogle Scholar
  40. Masi A, Vona M (2012) Vulnerability assessment of gravity-load designed RC buildings: evaluation of seismic capacity through non-linear dynamic analyses. Eng Struct 45:257–269CrossRefGoogle Scholar
  41. Masi A, Santarsiero G, Nigro D (2013) Cyclic tests on external RC beam-column joints: role of seismic design level and axial load value on the ultimate capacity. J Earthq Eng 17(1):110–136CrossRefGoogle Scholar
  42. Masi A, Chiauzzi L, Samela C, Tosco L, Vona M (2014) Survey of dwelling buildings for seismic loss assessment at urban scale: the case study of 18 villages in Val D’agri, Italy. Environ Eng Manag J (EEMJ) 13(2):471–486CrossRefGoogle Scholar
  43. Masi A, Digrisolo A, Manfredi V (2015) Fragility curves of gravity-load designed RC buildings with regularity in plan. Earthq Struct 9(1):1–27CrossRefGoogle Scholar
  44. McHugh ML (2012) Interrater reliability: the kappa statistic. Biochem Med Biochem Med 22(3):276–282CrossRefGoogle Scholar
  45. Mueller M, Segl K, Heiden U, Kaufmann H (2006) Potential of high-resolution satellite data in the context of vulnerability of buildings. Nat Hazards 38(1–2):247–258CrossRefGoogle Scholar
  46. Nguyen GH, Bouzerdoum A, Phung SL (2008) A supervised learning approach for imbalanced data sets. In 2008 19th international conference on pattern recognition. IEEE, pp 1–4Google Scholar
  47. Pacifici F, Chini M, Emery WJ (2009) A neural network approach using multi-scale textural metrics from very high-resolution panchromatic imagery for urban land-use classification. Remote Sens Environ 113(6):1276–1292CrossRefGoogle Scholar
  48. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12(October):2825–2830Google Scholar
  49. Penazzi D, Valluzzi MR, Cardani G, Binda L, Baronio G, Modena C (2000) Behaviour of historic masonry buildings in seismic areas: lessons learned from the Umbria-Marche earthquake. In 12th international brick-block masonry conference, pp 217–235Google Scholar
  50. Rottensteiner F, Briese C (2002) A new method for building extraction in urban areas from high-resolution LIDAR data. In International archives of photogrammetry remote sensing and spatial information sciences, vol 34, no 3/A, pp 295–301. Natural Resources CanadaGoogle Scholar
  51. RNDT – Repertorio Nazionale dei Dati Territoriali (2018) Geoportal. Accessed 23 Feb 2017
  52. Sarabandi P, Kiremidjian A, Eguchi RT, Adams BJ (2008) Building inventory compilation for disaster management: application of remote sensing and statistical modeling. Technical Report Series MCEER-08-0025, Buffalo, MCEERGoogle Scholar
  53. Steiniger S, Lange T, Burghardt D, Weibel R (2008) An approach for the classification of urban building structures based on discriminant analysis techniques. Trans GIS 12(1):31–59CrossRefGoogle Scholar
  54. Taubenböck H, Post J, Roth A, Zosseder K, Strunz G, Dech S (2008) A conceptual vulnerability and risk framework as outline to identify capabilities of remote sensing. Nat Hazards Earth Syst Sci 8(3):409–420CrossRefGoogle Scholar
  55. Taubenböck H, Roth A, Dech S, Mehl H, Münich JC, Stempniewski L, Zschau J (2009) Assessing building vulnerability using synergistically remote sensing and civil engineering. In: Krek A, Rumor M, Zlatanova S, Fendel E (eds) Urban and regional data management. Taylor & Francis Group, London, pp 287–300Google Scholar
  56. Tuia D, Persello C, Bruzzone L (2016) Domain adaptation for the classification of remote sensing data: an overview of recent advances. IEEE Geosci Remote Sens Mag 4(2):41–57CrossRefGoogle Scholar
  57. Voltersen M, Berger C, Hese S, Schmullius C (2014) Object-based land cover mapping and comprehensive feature calculation for an automated derivation of urban structure types at block level. Remote Sens Environ 154:192–201CrossRefGoogle Scholar
  58. Winham SJ, Freimuth RR, Biernacka JM (2013) A weighted random forests approach to improve predictive performance. Stat Anal Data Min ASA Data Sci J 6(6):496–505CrossRefGoogle Scholar
  59. Wurm M, Taubenböck H, Schardt M, Esch T, Dech S (2011) Object-based image information fusion using multisensor earth observation data over urban areas. Int J Image Data Fusion 2(2):121–147CrossRefGoogle Scholar
  60. Wurm M, Schmitt A, Taubenböck H (2016) Building types’ classification using shape-based features and linear discriminant functions. IEEE J Sel Top Appl Earth Obs Remote Sens 9(5):1901–1912CrossRefGoogle Scholar
  61. Xie Y, Weng A, Weng Q (2015) Population estimation of urban residential communities using remotely sensed morphologic data. IEEE Geosci Remote Sens Lett 12(5):1111–1115CrossRefGoogle Scholar
  62. Yu B, Liu H, Wu J, Hu Y, Zhang L (2010) Automated derivation of urban building density information using airborne LiDAR data and object-based method. Landsc Urban Plan 98(3–4):210–219CrossRefGoogle Scholar
  63. Zhang L, Huang X, Huang B, Li P (2006) A pixel shape index coupled with spectral information for classification of high spatial resolution remotely sensed imagery. IEEE Trans Geosci Remote Sens 44(10):2950–2961CrossRefGoogle Scholar

Copyright information

© Springer Nature B.V. 2019

Authors and Affiliations

  1. 1.School of EngineeringUniversità degli Studi della BasilicataPotenzaItaly
  2. 2.German Aerospace Center (DLR), German Remote Sensing Data Center (DFD)WeßlingGermany

Personalised recommendations