Earthquake intensity estimation via an artificial neural network: Examination of different network designs and training algorithms

Saglam A. S., ÇAVDUR F.

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, cilt.37, sa.4, ss.2133-2145, 2022 (SCI-Expanded) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 37 Sayı: 4
  • Basım Tarihi: 2022
  • Doi Numarası: 10.17341/gazimmfd.791337
  • Dergi Adı: JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Art Source, Compendex, TR DİZİN (ULAKBİM)
  • Sayfa Sayıları: ss.2133-2145
  • Anahtar Kelimeler: Disaster operations management, Disaster relief operations, Machine learning, Artificial neural networks, Earthquake intensity estimation, MAGNITUDE PREDICTION, DAMAGE, CASUALTIES, LOGISTICS, MODEL
  • Bursa Uludağ Üniversitesi Adresli: Evet

Özet

Purpose: We aim to estimate the earthquake intensity via an artificial neural network. Theory and Methods: We obtain significant earthquakes data from the database of the United States Geological Survey. An artificial neural network is developed using the MATLAB Neural Network Toolbox. We first determine an appropriate network design by estimating earthquake intensity with different artificial neural network designs and then the best training algorithm for the appropriate network design by evaluating different algorithms for the corresponding network design. Results: In terms of the average performance parameters, the network structure with two hidden layers and five and ten hidden neurons in each respective layer is determined as the most appropriate design. We observe the best results in terms of performance parameters by using the Levenberg-Marquardt training algorithm with Bayesian Regularization for the corresponding network structure. Conclusion: Earthquake intensity estimation is critical in predicting the impact that will occur after a disaster. In this study, we estimate earthquake intensity via an artificial neural network. In future studies, associated with earthquake intensity, we can estimate the number of casualties, damages to the buildings, economic loss and so on. Integrating earthquake intensity estimation into other disaster operation management studies may be another future study direction.