Deep learning-based classification of earthquake-impacted buildings using textual damage descriptions

Abstract To make informed decisions and have a well-coordinated response to a major hazard event, a rapid assessment of the spatial distribution and severity of building damage is needed. To this end, the long short-term memory (LSTM) deep learning method is applied to classify building damage based on textual descriptions of damage. The damaged state of an individual building is classified using the ATC-20 tags (red, yellow and green). The application of the LSTM approach is demonstrated using building damage descriptions recorded following the 2014 South Napa, California earthquake. The dataset, which consists of 3423 buildings (1552 green tagged, 1674 yellow tagged, 197 red tagged), is randomly divided into training and testing subsets. A predictive model is established using the training set and the performance of this model is evaluated with the test set. An overall accuracy of 86% is achieved when the deep learning model is used to identify the ATC-20 tags for the test set. Despite some noted limitations, the study highlights the overall potential of using the LSTM method to rapidly assess building cluster damage using textual information, which can be generated by building professionals, stakeholders or social media platforms.

[1]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[2]  Rui Liu,et al.  Feasibility study of using crowdsourcing to identify critical affected areas for rapid damage assessment: Hurricane Matthew case study , 2018, International Journal of Disaster Risk Reduction.

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[5]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[6]  David J. Wald,et al.  ShakeMap manual: technical manual, user's guide, and software guide , 2005 .

[7]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[8]  Jong-Su Jeon,et al.  Classification of failure mode and prediction of shear strength for reinforced concrete beam-column joints using machine learning techniques , 2018 .

[9]  Kuo-Wan Lin,et al.  ShakeCast: Automating and Improving the Use of ShakeMap for Post-Earthquake Decision-Making and Response , 2008 .

[10]  Xiangyang Guan,et al.  Using social media data to understand and assess disasters , 2014, Natural Hazards.

[11]  Marjorie Greene,et al.  Crowdsourcing earthquake damage assessment using remote sensing imagery , 2012 .

[12]  Hojjat Adeli,et al.  A New Neural Dynamic Classification Algorithm , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Mihailo D. Trifunac,et al.  Northridge, California, earthquake of 1994: density of red-tagged buildings versus peak horizontal velocity and intensity of shaking , 1997 .