GNN-Based Building Structure Characterization Framework for Seismic Risk Assessment

Abstract

Building structure characteristics are essential for seismic risk assessment and management. However, accurately classifying building structural types at the city scale remains challenging due to limited data availability, spatial heterogeneity, and the difficulty in capturing contextual dependencies. In this study, a novel graph neural network (GNN)-based framework, BSPGNN (Building Structural Type Prediction using Graph Neural Networks), was proposed, integrating spatial relationships and building geometric features to improve structural type classification. A Delaunay triangulation (DT) graph was constructed from building footprint centroids to represent spatial proximity, and node features included footprint area, height, and construction year. Experiments using a real-world building dataset from Tianjin, China demonstrated that BSPGNN significantly outperformed traditional machine learning models, such as random forest (RF) and support vector machine (SVM), particularly in capturing spatially coherent patterns. The proposed model achieved a classification accuracy of 90.25% and 85.51% on the training set and validation set respectively, showing robust performance under missing data conditions. The results highlight the potential of spatial graph-based models in advancing building structural type classification for seismic risk assessment and management.

Keywords

Building structural type classification / Exposure modeling / Graph neural network / Seismic risk assessment / Spatial graph-based model

References

[1] Aravena Pelizari P, Geiß C, Aguirre P, María HS, Peña YM, Taubenböck H. Automated building characterization for seismic risk assessment using street-level imagery and deep learning. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 180: 370-386

[2] Dabbeek, J., V. Silva, C. Galasso, and A. Smith. 2020. Probabilistic earthquake and flood loss assessment in the Middle East. International Journal of Disaster Risk Reduction 49: 101662.

[3] De Los Santos, M.J.D., and J.A. Principe. 2021. GIS-based rapid earthquake exposure and vulnerability mapping using Lidar DEM and machine learning algorithms: Case of Porac, Pampanga. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLVI-4/W6-2021: 125–132.

[4] Fernando KRM, Tsokos CP. Dynamically weighted balanced loss: Class imbalanced learning and confidence calibration of deep neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2021, 33(7): 2940-2951

[5] Geiß C, Taubenböck H. Remote sensing contributing to assess earthquake risk: From a literature review towards a roadmap. Natural Hazards, 2013, 68(1): 7-48

[6] Geiß C, Aravena Pelizari P, Marconcini M, Sengara W, Edwards M, Lakes T, Taubenböck H. Estimation of seismic building structural types using multi-sensor remote sensing and machine learning techniques. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 104: 175-188

[7] Geiß C, Taubenböck H, Tyagunov S, Tisch A, Post J, Lakes T. Assessment of seismic building vulnerability from space. Earthquake Spectra, 2014, 30(4): 1553-1583

[8] Ghione, F., S. Mæland, A. Meslem, and V. Oye. 2022. Building stock classification using machine learning: A case study for Oslo, Norway. Frontiers in Earth Science 10. https://doi.org/10.3389/feart.2022.886145.

[9] Hamilton, W., R. Ying, and J. Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), 4–9 December 2017, Long Beach, CA, USA.

[10] Kipf, T.N., and M. Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907. Accessed 15 Aug 2024.

[11] Lee DT, Schachter BJ. Two algorithms for constructing a Delaunay triangulation. International Journal of Computer & Information Sciences, 1980, 9(3): 219-242

[12] Lei B, Liu P, Milojevic-Dupont N, Biljecki F. Predicting building characteristics at urban scale using graph neural networks and street-level context. Computers, Environment and Urban Systems, 2024, 111: 102-129

[13] Ma J, Rao A, Silva V, Liu K, Wang M. A township-level exposure model of residential buildings for mainland China. Natural Hazards, 2021, 108(1): 389-423

[14] Polese M, Di Ludovico M, d’Aragona MG, Prota A, Manfredi G. Regional vulnerability and risk assessment accounting for local building typologies. International Journal of Disaster Risk Reduction, 2020, 43: 101-400

[15] Radovanović M, Nanopoulos A, Ivanović M. Hubs in space: Popular nearest neighbors in high-dimensional data. Journal of Machine Learning Research, 2010, 11: 2487-2531

[16] Rivera, F., T. Rossetto, and J. Twigg. 2020. An interdisciplinary study of the seismic exposure dynamics of Santiago de Chile. International Journal of Disaster Risk Reduction 48: Article 101581.

[17] Rossi, E., H. Kenlay, M.I. Gorinova, B.P. Chamberlain, X. Dong, and M. Bronstein. 2022. On the unreasonable effectiveness of feature propagation in learning on graphs with missing node features. In Proceedings of the First Learning on Graphs Conference (LoG 2022), Virtual Event, 9–12 December 2022.

[18] Torres Y, Arranz JJ, Gaspar-Escribano JM, Haghi A, Martínez-Cuevas S, Benito B, Ojeda JC. Integration of LiDAR and multispectral images for rapid exposure and earthquake vulnerability estimation. Application in Lorca, Spain. International Journal of Applied Earth Observation and Geoinformation, 2019, 81: 161-175

[19] Von Luxburg U. A tutorial on spectral clustering. Statistics and Computing, 2007, 17(4): 395-416

[20] Wang, C., Q. Yu, K.H. Law, F. McKenna, S.X. Yu, E. Taciroglu, A. Zsarnóczay, W. Elhaddad, and B. Cetiner. 2021. Machine learning-based regional scale intelligent modeling of building information for natural hazard risk management. Automation in Construction 122: Article 103474.

[21] Wang Y, Zhang Y, Dong Q, Guo H, Tao Y, Zhang F. A multi-view graph neural network for building age prediction. ISPRS Journal of Photogrammetry and Remote Sensing, 2024, 218: 294-311

[22] Xing, Z., S. Yang, X. Zan, X. Dong, Y. Yao, Z. Liu, and X. Zhang. 2023. Flood vulnerability assessment of urban buildings based on integrating high-resolution remote sensing and street view images. Sustainable Cities and Society 92: Article 104467.

[23] Xu Y, He Z, Xie X, Xie Z, Luo J, Xie H. Building function classification in Nanjing, China, using deep learning. Transactions in GIS, 2022, 26(5): 2145-2165

[24] Xu, Z., Y. Wu, M. Qi, M. Zheng, C. Xiong, and X. Lu. 2020. Prediction of structural type for city-scale seismic damage simulation based on machine learning. Applied Sciences 10(5): Article 1795.

[25] Xu Z, Zhang F, Wu Y, Yang Y, Wu Y. Building height calculation for an urban area based on street view images and deep learning. Computer-Aided Civil and Infrastructure Engineering, 2022

[26] Yan X, Ai T, Yang M, Tong X, Liu Q. A graph deep learning approach for urban building grouping. Geocarto International, 2022, 37(10): 2944-2966

[27] Yan X, Ai T, Yang M, Yin H. A graph convolutional neural network for classification of building patterns using spatial vector data. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 150: 259-273

[28] Yepes-Estrada C, Calderon A, Costa C, Crowley H, Dabbeek J, Hoyos MC, Martins L, Paul Net al.. Global building exposure model for earthquake risk assessment. Earthquake Spectra, 2023, 39(4): 2212-2235

RIGHTS & PERMISSIONS

The Author(s)