Aqila, Muhammad Haekhal (2025) Estimasi Parameter Distribusi Generalized Pareto, Weibull, dan q-Weibull pada Moment Magnitude Gempa Mainshock Megathrust di Indonesia. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5006211032-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5006211032-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (6MB) | Request a copy |
Abstract
Indonesia menghadapi risiko gempa di zona megathrust Selat Sunda dan Mentawai Siberut, dengan gempa ekstrem terakhir pada 2004 yang memicu tsunami Aceh. Penelitian ini membandingkan distribusi Generalized Pareto, Weibull, dan q-Weibull dalam memodelkan moment magnitude gempa megathrust menggunakan data 1973–2023 dengan metode Maximum Likelihood Estimation, Nelder-Mead, dan Adaptive Hybrid Artificial Bee Colony Algorithm (AHABC) dan mengaplikasikannya pada CAT modelling. Uji Cramér-von Mises menunjukkan Weibull hanya sesuai pada 1 dari 16 lempeng, sedangkan Generalized Pareto dan q-Weibull sesuai pada seluruh lempeng. Plot PDF distribusi q-Weibull dan Generalized Pareto dengan berhasil membentuk distribusi yang menyerupai data empiris dibandingkan Weibull yang memiliki keterbatasan dalam pembentukan. Sedangkan, AIC Generalized Pareto unggul secara statistik dengan AIC terkecil, menghasilkan return level tinggi dengan return period kecil, sementara q-Weibull lebih stabil dengan hasil yang lebih moderat. Kedua distribusi efektif dalam membangkitkan data kejadian gempa, dengan Generalized Pareto cenderung lebih sering menangkap kejadian ekstrem pada pembuatan event loss table. Estimasi risiko menunjukkan Generalized Pareto menghasilkan perhitungan VaR dan TVaR yang lebih tinggi pada risiko ekstrem, sedangkan q-Weibull menawarkan stabilitas lebih baik. Penggunaan kernel Gaussian meningkatkan hasil perhitungan risiko, sedangkan Epanechnikov menurunkanya.
=================================================================================================================================
Indonesia faces earthquake risks in the Sunda Strait and Mentawai Siberut megathrust zones, with the last extreme earthquake in 2004 triggering the Aceh tsunami. This study compares the Generalized Pareto, Weibull, and q-Weibull distributions in modeling the moment magnitude of megathrust earthquakes using 1973-2023 data with Maximum Likelihood Estimation, Nelder-Mead, and Adaptive Hybrid Artificial Bee Colony Algorithm (AHABC) methods and applies them to CAT modeling. The Cramér-von Mises test shows that Weibull fits only 1 of the 16 plates, while Generalized Pareto and q-Weibull fit all plates. PDF plots of q-Weibull and Generalized Pareto distributions successfully form distributions that resemble empirical data compared to Weibull which has limitations in shaping. Meanwhile, the AIC of Generalized Pareto is statistically superior with the smallest AIC, producing high return levels with small return periods, while q-Weibull is more stable with more moderate results. Both distributions are effective in generating earthquake event data, with Generalized Pareto tending to capture extreme events more often in the event loss table generation. Risk estimation shows that Generalized Pareto produces higher VaR and TVaR calculations at extreme risks, while q-Weibull offers more stability. The use of Gaussian kernel improves the risk calculation results, while Epanechnikov decreases it.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Estimasi Parameter, Generalized Pareto, Megathrust, q-Weibull, Weibull, Generalized Pareto Distribution, Megathrust, Parameter Estimation |
| Subjects: | Q Science > Q Science (General) > Q180.55.M38 Mathematical models Q Science > Q Science (General) > Q337.3 Swarm intelligence Q Science > QA Mathematics > QA273.6 Weibull distribution. Logistic distribution. Q Science > QA Mathematics > QA353.K47 Kernel functions (analysis) Q Science > QA Mathematics > QA401 Mathematical models. Q Science > QA Mathematics > QA614.58 Catastrophes Q Science > QE Geology > QE538.8 Earthquakes. Seismology Q Science > QE Geology > QE539.2.S4 Seismic models |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Actuaria > 94203-(S1) Undergraduate Thesis |
| Depositing User: | Muhammad Haekhal Aqila |
| Date Deposited: | 07 Jan 2025 00:56 |
| Last Modified: | 07 Jan 2025 00:56 |
| URI: | http://repository.its.ac.id/id/eprint/116171 |
Actions (login required)
 |
View Item |