Model simulasi peluang kejadian gempa bumi di pulau Jawa dengan Poisson Hidden Markov Model (PHMM) menggunakan metode Bayesian

Andrea, Andrea (2020) Model simulasi peluang kejadian gempa bumi di pulau Jawa dengan Poisson Hidden Markov Model (PHMM) menggunakan metode Bayesian. Bachelor thesis, Universitas Pelita Harapan.

[img] Text (Title)
Title.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[img]
Preview
Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (163kB) | Preview
[img]
Preview
Text (ToC)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (164kB) | Preview
[img]
Preview
Text (Chapter1)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (568kB) | Preview
[img] Text (Chapter2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (864kB)
[img] Text (Chapter3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (254kB)
[img] Text (Chapter4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (520kB)
[img] Text (Chapter5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (148kB)
[img]
Preview
Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (158kB) | Preview
[img] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (187kB)

Abstract

Indonesia terletak pada pertemuan tiga lempeng tektonik besar yaitu lempeng tektonik Indo-Australia, lempeng Eureasia, dan lempeng Pasifik, serta satu lempeng tektonik kecil yaitu Filipina yang menyebabkan Indonesia rentan akan gempa tektonik. Maka dari itu gempa bumi sudah tidak asing lagi didengar oleh masyarakat Indonesia. Bahkan efek gempa bumi juga dapat mengganggu kehidupan manusia hingga jika gempa bumi tersebut berkekuatan besar juga dapat merusak lingkungan sekitar maupun memakan korban jiwa. Memperoleh parameter peluang gempa bumi sebagai mitigasi bencana bagi masyarakat di Pulau Jawa menjadi hal yang penting. Ada beberapa metode yang dapat dilakukan untuk memprediksi peluang terjadinya gempa bumi. Pada skripsi ini, akan digunakan Poisson Hidden Markov Model untuk memodelkan kejadian gempa bumi di Pulau Jawa. Data yang digunakan adalah data gempa bumi dari USGS periode 01 Januari 1998 hingga 31 Desember 2018 dengan syarat berkekuatan ≥ 5 Mw dan dengan kedalaman ≤ 70 km dari permukaan. Setelah itu dengan Gibbs Sampler menggunakan Bayesian Posterior Mean Estimates, untuk memprediksi peluang terjadinya gempa bumi dengan periode waktu 15 hari. Model yang memprediksi kejadian gempa bumi di Pulau Jawa adalah model two-state bernilai 1.881633, three-state bernilai 1.861224, dan four-state PHMM dengan MAE terkecil yaitu 1.769388. Hasil dari penelitian ini dapat digunakan sebagai salah satu langkah dalam mitigasi bencana bagi masyarakat Indonesia khususnya di Pulau Jawa. / Indonesia is located at the collision of three large tectonic plates namely the Indo-Australianplate, theEureasiaplate, andthePacificplatealongwithonesmall tectonic plate namely the Philippines which makes Indonesia vulnerable to tectonic earthquakes. Therefore Indonesian people is familiar with earthquake. The effect of the earthquakes can interfere the life of human and a large magnitude of earthquakes might also damage the surrounding environment and loss of life. Obtaining the parameters of earthquake probabilities as disaster mitigation for the people of Java is important. There are several methods that can be done to predict the chances of an earthquake. In this thesis, Poisson Hidden Markov Model will be used to model the earthquake events in Java. The data used are earthquake data from the USGS period 01 January 1998 to 31 December 2018 with a condition of ≥ 5 SR and a depth of ≤ 70 km from the surface. After that the Gibbs Sampler uses Bayesian Posterior Mean Estimates, to predict the probability of an earthquake occurring with a period of 15 days. The model that predicts earthquake events in Java are two-state is worth 1.881633, three-state is worth 1.861224, and four-state PHMM with a smallest value is 1.769388. The results of this study can be used as a step in disaster mitigation for the people of Indonesia, especially in Java.

Item Type: Thesis (Bachelor)
Creators:
CreatorsNIMEmail
Andrea, AndreaNIM00000021395andrea.tanujaya0202@yahoo.com
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorSembiring, Ukur AriantoNIDN0311056901ukur.sembiring@uph.edu
Thesis advisorFerdinand, Ferry VincenttiusNIDN0323059001ferry.vincenttius@uph.edu
Uncontrolled Keywords: gempa bumi; Pulau Jawa; poisson hidden markov model; Bayesian posterior mean estimates; mean absolut error
Subjects: Q Science > QA Mathematics
Divisions: University Subject > Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics
Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics
Depositing User: Users 5936 not found.
Date Deposited: 21 Jul 2020 07:17
Last Modified: 21 Jul 2020 07:17
URI: http://repository.uph.edu/id/eprint/9299

Actions (login required)

View Item View Item