Journals / Acta Infologica / 2022 / Cilt: 6 Sayı: 2

Comparison of Different Heuristics Integrated with Neural Networks: A Case Study for Earthquake Damage Estimation

Yapay Sinir Ağı ile Entegre Farklı Sezgisel Yöntemlerin Karşılaştırılması: Deprem Hasar Tahmini için bir Vaka Çalışması

Pages
265–281
Publication Date
2022-12-31
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Based on the obtained results, it is believed that this model can be used in different earthquake damage prediction studies and as a guide in emergency planning.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Earthquakes are among the most challenging natural phenomena to predict.
📊
Key Findings & Data:If the effects of possible earthquakes can be predicted, quick and accurate decisions can be made.
💡
Conclusion & Impact:Based on the obtained results, it is believed that this model can be used in different earthquake damage prediction studies and as a guide in emergency planning.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Deprem · Hasar tahmini · Makine öğrenmesi

Abstract

Earthquakes are among the most challenging natural phenomena to predict. Most of these unpredictable earthquakes result in the loss of human lives and property. Seismologists can estimate the probable location and magnitude of such earthquakes. However, the actual time and extent of their impact remain unknown. If the effects of possible earthquakes can be predicted, quick and accurate decisions can be made. For this purpose, developing predictive models about earthquakes is a prevalent and vital issue in the literature. In this study, various Machine Learning (ML) algorithms were compared on a public dataset of earthquakes, which had occurred worldwide and had a local magnitude Ml ≥ 3, and the algorithm with the highest performance was selected and optimized with various other algorithms. The performances of the models were compared using different performance evaluation metrics such as accuracy, Mean Square Error, Root-Mean Square Error, precision, recall, and f1 score. As a result, it was observed that the Artificial Neural Network (ANN) algorithm optimized with the Particle Swarm Optimization (PSO) algorithm produced the most successful result with an accuracy value of 0.82. Based on the obtained results, it is believed that this model can be used in different earthquake damage prediction studies and as a guide in emergency planning.

Özet

Depremler, tahmin edilmesi en zor doğa olayları arasında yer almaktadır. Bu öngörülemeyen deprem-lerin ardından çoğu zaman can ve mal kayıpları meydana gelmektedir. Depremler önceden kesin olarak belirlenemese bile deprem bilimciler tarafından olası konumları ve büyüklükleri yaklaşık olarak tahmin edilebilmektedir. Ancak, bu depremlerin zamanı ve bırakacağı etkinin boyutu bilinme-mektedir. Eğer olası depremlerin etkileri önceden tahmin edilebilirse, arama kurtarma çalışmaları sırasında ekiplerin hızlı ve doğru kararlar alması sağlanabilir ve bu sayede özellikle can kayıplarının önüne geçilebilir. Bu amaç doğrultusunda depremlerle ilgili tahmin modelleri geliştirmek günümüzde oldukça yaygın ve hayati bir konudur. Bu çalışmada ise dünya genelinde gerçekleşmiş yerel büyük-lüğü Ml≥3 olan açık kaynaklı deprem verileri kullanılarak farklı Makine Öğrenmesi algoritmaları karşılaştırılmış ve en yüksek performansa sahip olan algoritma seçilerek çeşitli algoritmalar ile opti-mize edilmiştir. Modellerin performansı doğruluk, Ortalama Kare Hata, Kök-Ortalama Kare Hata, kesinlik, geri çağırma ve f1 puanı gibi farklı performans değerlendirme metrikleri kullanılarak karşı-laştırılmıştır. Sonuç olarak PSO algoritması ile optimize edilmiş ANN algoritmasının 0.82 oranında doğruluk değeri ile en başarılı sonucu ürettiği gözlemlenmiştir. Elde edilen sonuçlara bakıldığında bu modelin farklı deprem hasar tahmin çalışmalarında ve acil durum planlamasında yol gösterici olarak kullanılabileceği düşünülmektedir.

🔖

Cite This Article

MALKOÇOĞLU, A. B. V., ORMAN, Z., ŞAMLI, R. (2022). Comparison of Different Heuristics Integrated with Neural Networks: A Case Study for Earthquake Damage Estimation. Acta Infologica, Cilt: 6 Sayı: 2, 265–281. https://ajindex.com/articles/948329

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (1)

  1. Abraham A., Rohini V. (2019). A Particle Swarm Optimization-Backpropagation (PSO-BP) Model for the Prediction of Earthquake in Japan. In Emerging Research in Computing, Information, Communication and Applications, 882:435-441. google scholar Adjei C., Tian W., Onzo B., Kedjanyi E. A. G. & Darteh O. F., Chen S (2021). Rainfall Forecasting in Sub-Sahara Africa-Ghana using LSTM Deep Learning Approach. International Journal of Engineering Research & Technology, 10(3):464-470 google scholar Aghamohammadi H., Mesgari M. S., Mansourian A. & Molaei D. (2013). Seismic human loss estimation for an earthquake disaster using neural network. International Journal of Environmental Science and Technology, 10:931-939. https://doi.org/10.1007/s13762-013-0281-5 google scholar Ahmad N. (2019). Fragility Functions and Loss Curves for Deficient and Haunch-Strengthened RC Frames. Journal of Earthquake Engineering, accepted. https://doi.org/10.1080/13632469.2019.1698478 google scholar Ahmad N., Ali Q., Ashraf M., Alam B. & Naem A. (2012). Seismic vulnerability of the Himalayan half-dressed rubble stone masonry structures, experimental and analytical studies, Natural Hazards and Earth System Sciences, 12:3441-3454. https://doi.org/10.5194/nhess-12-3441-2012 google scholar Ahmad N., Ali Q., Crowley H. & Pinho R. (2014). Earthquake loss estimation of residential buildings in Pakistan, Natural Hazards, 73: 1889-1955. https:// doi.org/10.1007/s11069-014-1174-8 google scholar Alizadeh M., Alizadeh E., Kotenaee S. A., Shahabi H., Pour A. B., Panahi M., Ahmad B. B. & Saro L. (2018). Social Vulnerability Assessment Using Artificial Neural Network (ANN) Model for Earthquake Hazard in Tabriz City, Iran, Sustainability, 10, ID: 3376. https://doi.org/10.3390/su10103376 google scholar Alizadeh M., Ngah I., Hashim M., Pradhan B. & Pour A. B. (2018). A Hybrid Analytic Network Process and Artificial Neural Network (ANP-ANN) Model for Urban Earthquake Vulnerability Assessment, Remote Sensing, 10, ID: 975. https://doi.org/10.3390/rs10060975 google scholar Anupam S. and Pani P. (2020). Flood forecasting using a hybrid extreme learning machine particle swarm optimization algorithm (ELM PSO) model, Modeling Earth Systems and Environment, 6:341-347. https://doi.org/10.1007/s40808-019-00682-z280 google scholar Asim K. M., Idris A., Iqbal. T & Martínez-Álvarez F. (2018). Seismic indicators-based earthquake predictor system using Genetic Programming and AdaBoost classification. Soil Dynamics and Earthqua