Predicting Damage to Buildings Caused by Earthquakes Using Machine Learning Techniques

Chaurasia, Kuldeep; Kanse, Samiksha; Yewale, Aishwarya; Singh, V. P.; Sharma, Bhavnish; Dattu, B. R.

doi:10.1109/iacc48062.2019.8971453

Cited by 13 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bu bölümde literatürde yer alan çeşitli tahmin çalışmaları Tablo 1'de görüldüğü gibi özetlenmiştir. 32], Rassal ormanlar [19,22,32], Regresyon modelleri [27], Yapay sinir ağları [13-15, 16-20, 30-32], Diğer [19,22,23,28] Afet sonrası oluşan hasar Derin öğrenme [50,51], Destek vektör makineleri [52], Karar ağaçları [48,52], Rassal ormanlar [41,47,48], Regresyon modelleri [41,49,52], Yapay sinir ağları [34, 36-38, 41, 45, 47], Diğer [35,39,40,42,43,46,48] olasılığı ve sınırlı büyüklük aralığında bir depremin meydana gelme olasılığı olmak üzere iki tip tahmin yapılmaktadır. Corbi vd.…”

Section: Li̇teratür Araştirmasi (Literature Review)unclassified

“…Bina hasarı tahmini yapan çalışmalarda coğrafi bilgi sistemlerinden [42], literatürde yer alan ampirik ifadelerden [43], yapay sinir ağlarından [45] veya binaların iki boyutlu doğrusal olmayan sonlu eleman modellerinden [46] yararlanılmaktadır. Farklı makine öğrenme yöntemleri kullanılarak bu yöntemlerin performansının analiz edildiği çalışmalar da bulunmaktadır [47,48]. Oluşacak maddi hasarın tahmini de bir diğer önemli konudur.…”

Section: Li̇teratür Araştirmasi (Literature Review)unclassified

See 1 more Smart Citation

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

SAĞLAM

Çavdur

2022

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

 Development of an artificial neural network for earthquake intensity estimation  Network structure optimization by considering different network designs  Determining an appropriate training algorithm for the determined network designIn this study, using a multi-layer feed-forward artificial neural network, we estimate earthquake intensity based on the magnitude and the depth of an earthquake and the distance of the disaster victims from the epicenter of the earthquake. In this context, we use significant earthquakes database of the United States Geological Survey as the inputs of the artificial neural network. 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. Figure A. Artificial neural network designPurpose: 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.

show abstract

Section: Li̇teratür Araştirmasi (Literature Review)unclassified

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

SAĞLAM

Çavdur

2022

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

show abstract

“…K Chaurasia et al(2019) [9] predicted the level of damage caused by the earthquake that hit Nepal in the year 2015. The researchers have used Neural Networks and Random Forest classifier techniques to achieve the goal.…”

Section: Literature Survey/related Workmentioning

confidence: 99%

“…The United Kingdom also assisted by supplying 30 tons of humanitarian assistance and 8 tons of supplies. In this research, we have used dataset given by driven data [19], performed EDA using Tableau [12], and finally developed a machine learning model that is capable of predicting the damage grade severity to the buildings caused by the earthquake [1,2,4,9,16,17]. The models can also be used for forecasting the damage level to the buildings to a certain extent [6,8,20].…”

Section: Introductionmentioning

confidence: 99%

Earthquake Damage Prediction Using Random Forest and Gradient Boosting Classifier

Adi¹,

Adishesha²,

Bharadwaj³

et al. 2020

AJBES

View full text Add to dashboard Cite

“…Chaurasia et al performed predictions using a neural network and the random forest model, and the best-performing model's F1 score was 0.743. [13]. Chen and Zhang used a cloud model and Bayesian networks to predict the DG in three levels with an accuracy of 0.888 based on a dataset of 9920 buildings [14].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Assessment of Damage Grade for Post-Earthquake Buildings: A Three-Stage Approach Directly Handling Categorical Features

Li,

Jia,

Chen

et al. 2023

Sustainability

View full text Add to dashboard Cite

The rapid assessment of post-earthquake building damage for rescue and reconstruction is a crucial strategy to reduce the enormous number of human casualties and economic losses caused by earthquakes. Conventional machine learning (ML) approaches for this problem usually employ one-hot encoding to cope with categorical features, and their overall procedure is neither sufficient nor comprehensive. Therefore, this study proposed a three-stage approach, which can directly handle categorical features and enhance the entire methodology of ML applications. In stage I, an integrated data preprocessing framework involving subjective–objective feature selection was proposed and performed on a dataset of buildings after the 2015 Gorkha earthquake. In stage II, four machine learning models, KNN, XGBoost, CatBoost, and LightGBM, were trained and tested on the dataset. The best model was judged by comprehensive metrics, including the proposed risk coefficient. In stage III, the feature importance, the relationships between the features and the model’s output, and the feature interaction effects were investigated by Shapley additive explanations. The results indicate that the LightGBM model has the best overall performance with the highest accuracy of 0.897, the lowest risk coefficient of 0.042, and the shortest training time of 12.68 s due to its relevant algorithms for directly tackling categorical features. As for its interpretability, the most important features are determined, and information on these features’ impacts and interactions is obtained to improve the reliability of and promote practical engineering applications for the ML models. The proposed three-stage approach can provide a reference for the overall ML implementation process on raw datasets for similar problems.

show abstract

Predicting Damage to Buildings Caused by Earthquakes Using Machine Learning Techniques

Cited by 13 publications

References 19 publications

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

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

Earthquake Damage Prediction Using Random Forest and Gradient Boosting Classifier

Machine Learning Assessment of Damage Grade for Post-Earthquake Buildings: A Three-Stage Approach Directly Handling Categorical Features

Contact Info

Product

Resources

About