Document Type : Research Paper

Authors

1 Student of master sensing, University of Tehran

2 Assistant professore of remote sensing, University of Tehran

Abstract

Discussion about earthquake to reduce its casualties and damages is very important, especially in a seismic area like Iran where the occurrence of this natural phenomenon is seen annually. Anomaly detection prior to earthquake plays an important role in earthquake prediction. Ionosphere changes which are recognizable by remote measurements (such as using Global Positioning System) are known as earthquake ionospheric precursors. In this study, two data sets from the ionospheric Total Electron Content (TEC) derived from the GPS data processing by Bernese software were used for two studies, Ahar earthquake, East Azerbaijan (2012/08/11) and Kaki earthquake,Bushehr (2013/4/9), and the results were compared with data obtained from the  global stations. Because of the nonlinear behavior of TEC changes, in order to predict and detect its changes, integration of neural network (using multilayer Perceptron (MLP)) with particle swarm optimization algorithm (PSO) was used. Particle Swarm Optimization algorithm with a performance based on the population can be effective in improving estimatedweight by artificial neural network. By analyzing the causes of ionospheric anomalies including the geomagnetic fields and solar activities and their removal from the processes, the results indicate that some of this anomalies caused by the earthquake and using intelligent algorithms were able to have appropriate efficiency for the prediction of nonlinear time series. The output resulted from the integration of artificial neural network and PSO shows that both positive and negative anomalies occur. The anomalies before earthquakes often occur close to the epicenter of the earthquake and are visible 3 days before the Ahar earthquake and 2 to 6 days before the Kaki earthquake are.

Keywords

1- المد‌رسی، تابان، عبدی؛ سید‌محمد‌تقی، محمد‌رضا،  جواد‌. (1383). «استفاد‌ه از شبکه عصبی د‌ر افزایش د‌قت گیرند‌ه‌های GPS تک فرکانسه پس از حذف اثر SA». نهمین کنفرانس شبکه‌های توزیع نیروی برق
2- صاد‌قی، فرهاد‌.(1386). «مد‌ل‌سازی اثر یونسفر با استفاد‌ه از آنالیز مشاهد‌ات د‌وفرکانسه شبکه‌های د‌ائمی GPS و کاربرد‌ آن د‌ر علوم مهند‌سی و فیزیک». اولین همایش پیش نشانگرهای زلزله
3- عبد‌ی، نانکلی؛ ناصر، حمید‌رضا.(1393). «بررسی تغییرات زمانی و مکانی TEC د‌ر ایران با استفاد‌ه از مشاهد‌ات GPS».نشریه علمی پژوهشی علوم و فنون نقشه‌برد‌اری، ص. 113-121
4- کاشفی کاویانی، پورموسوی کانی؛ علی، علی. (1386). «آموزش شبکه عصبی چند‌لایه با به‌کارگیری الگوریتم PSO.». اولین کنگره مشترک سیستم‌های فازی و سیستم‌های هوشمند‌
5- Akhoondzadeh, M.(2013).A MLP neural network as an investigator of TEC time series to detectseismo-ionospheric anomalies. Advances in Space Research 51, 2048-2057.
6- Akhoondzadeh ,M. (2013). An Adaptive Network-based Fuzzy Inference System for thedetection of thermal and TEC anomalies around the time of the Varzeghan, Iran, (Mw = 6.4) earthquake of 11 August 2012. Advances in Space Research 52,837-852
7-  Akhoondzadeh, M.(2013).Genetic algorithm for TEC seismo-ionospheric anomalies detection around the time of the Solomon (Mw=8.0) earthquake of 06 February 2013. Advances in Space Research 52,581 – 590.
 8- Akhoondzadeh, M. (2012). Anomalous TEC variations associated with the powerful Tohoku earthquake of 11 March 2011. Nat. Hazards Earth Syst. Sci.12, 1453 – 1462. 
9- Akhoondzadeh, M.(2013).Support vector machine for TEC seismo-ionospheric anomalies detection. Ann. Geophys. 31, 173- 186
10- Akhoondzadeh, M.(2013).Novelty detection in time series of ULF magnetic and electric components obtained from DEMETER satellite experiments above Samoa (29 September 2009) earthquake region. Nat. Hazards Earth Syst. Sci. 13, 15. 2103-25.
11- Akhoondzadeh, M.(2013). A comparison of classical and intelligent methods to detect potential thermal anomalies before the 11 August 2012 Varzeghan, Iran, earthquake (Mw =6.4). Nat. Hazards Earth Syst. Sci. 13, 1077-1083.
12- Akhoondzadeh, M. Saradjian, M R.(2010). TEC variations analysis concerning Haiti (January 12, 2010) and Samoa (September29,2009) earthquakes. Advances in Space Research 47,  94-104.
13- Akhoondzadeh, M. Parrot, M. Saradjian, M R. (2010).Electron and ion density variations before strong earthquakes(M>6.0) using DEMETER and GPS data”. Nat. Hazards Earth Syst.Sci. 10, 7-18.
14- Akhoondzadeh, M. Parrott, M. Saradjian, M R. (2010). Investigation of VLF and HF waves showing seismo-ionospheric anomalies induced by the 29 September 2009 Samoa earthquake (Mw=8.1). Nat. Hazards Earth Syst. ScI. 1061-1067, 10.
15- Da Costa,A, Vilas Boas,J. Da Fonseca Junior,E. (2004).GPS Total Electron Content measurements at low latitudes in Brazil for low solar activity. Geofísica Internacional.43,129-137.
16- Garner,T W. Gaussiran, T L.. Tolman, B W. Harris, R B. Calfas, R S.Gallagher,H. (2008) . Total electron content measurements in ionospheric physics. Advances in Space Research 42,720-726 .
17- Mahnam ,M.  .Fatemi Ghomi, S.M.T .(2012).A Particle Swarm Optimization Algorithm for Forecasting Based on Time Variant fuzzy Time Series. International Journal of Industrial Engineering & Production Research 269-270, 230.
18- Mann, M. Lognonne, P, Rolland, L.(2011) Ionospheric TEC Calculation from GPS Data and a Non-linear Frequency-Domain Approach for Approximation and Spectral Representation ofIonospheric Perturbances. World Academy of Science, Engineering and Technology 59 .
19- Meza, A. Brunini, C. Kleusberg, A. (2000).Global ionospheric models in three dimensions from GPS measurements: Numerical simulation. Geofísica Internacional .39. 21-27.
20- naggar, Aly M El. (2013).Artificial neural network as a model for ionospheric TEC map to serve the single frequency receiver. Alexandria Engineering Journal 52, 425-432.
21- Saroso, S . Liu,L.  Hattori, K . Chen,C .(2008). Ionospheric GPS TEC Anomalies and M> 5.9 Earthquakes in Indonesia during 1993 - 2002. Terr. Atmos. Ocean. Sci.19, 481-488.
22- Seradjian, M R Akhoondzadeh,M.(2010). Prediction of the date, magnitude and affected area of impending strong earthquakes using integration of multi precursors earthquake parameters. Nat. Hazards Earth Syst. Sci., 11, 1109-1119.
23- Telbany, Mohammed El, Karmi, Fawwaz El.(2007).Short-term forecasting of Jordanian electricity demand using particle swarm optimization. Electric Power Systems Research 78,425-433.
24- Xia, C. Yang, S. Xu, G. Zhao, B. Yu, T.(2011). Ionospheric Anomalies Observed by GPS TEC Prior to the Qinghai-Tibet Region Earthquakes. Terr. Atmos. Ocean. Sci.22,177-185.
25- Yao,Y B. Chen, P. Zhang ,S. Chen, J. Yan ,F. Peng, W F.(2012). Analysis of pre-earthquake ionospheric anomalies before the globalM = 7.0+ earthquakes in 2010” . Nat. Hazards Earth Syst. Sci. 12, 575-585.
26- Zhao, L .Yang, Y .(2009). PSO-based single multiplicative neuron model for time series prediction. Expert Systems with Applications 36,2805-2812.