Simatupang, Kevin Alessandro Frederick (2024) Pendekatan Bayesian Hierarki Dalam Analisis Ketersediaan Listrik Tiap Kecamatan di Provinsi Kepulauan Riau Melalui Pemodelan Intensitas Cahaya Malam. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5003201176-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5003201176-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (8MB) | Request a copy |
Abstract
Energi listrik memainkan peran penting dalam memajukan pembangunan dan tingkat kesejahteraan masyarakat di suatu daerah. Distribusi energi listrik yang tidak merata masih menjadi masalah nyata di Indonesia, terutama di wilayah terpencil seperti Provinsi Kepulauan Riau. Salah satu sumber data alternatif yang dapat dimanfaatkan adalah citra satelit malam VIIRS, yang mencatat perubahan intensitas penerangan di permukaan bumi pada malam hari. Data yang dianalisis dalam penelitian ini merupakan data berstruktur hierarki. Sehingga, metode Bayesian satu tingkat dan Bayesian hieraki digunakan untuk melakukan estimasi parameter. Proses estimasi parameter model Bayesian Hierarki dilakukan dengan menggunakan distribusi gamma serta algoritma sampling Hamiltonian Monte Carlo. Hasil pemodelan terbaik didapatkan menggunakan Bayesian hierarki dengan variabel mikro yang berpengaruh signifikan di sebagian besar kabupaten adalah jumlah koperasi aktif, akomodasi, dan restoran/tempat makan. Adapun pada tingkat makro, variabel yang berpengaruh terhadap variasi radiasi cahaya malam adalah IPM, PDRB ADHB, dan jumlah pelanggan listrik kabupaten/kota. Model Bayesian hierarki memiliki nilai DIC sebesar 5,08, lebih rendah dibandingkan model Bayesian satu tingkat dengan DIC 12,354, menunjukkan kebaikan model yang lebih tinggi. Peta tematik yang didapatkan dari hasil estimasi model menggunakan Bayesian hierarki dapat lebih menggambarkan radiasi cahaya malam tiap kecamatan sebagai indikator kondisi ketersediaan listrik di Kepulauan Riau.
========================================================================================================================
Electricity plays a crucial role in enhancing the pace of development and the well-being of communities in a region. Unfortunately, uneven distribution of electricity remains a significant issue across various regions in Indonesia, especially in remote areas such as Riau Islands Province. One alternative data source that can be utilized is VIIRS night satellite imagery, which records changes in the intensity of illumination on the earth's surface at night. The data analyzed in this study is hierarchically structured. Thus, one-level Bayesian and hierarchical Bayesian methods are used to perform parameter estimation. The parameter estimation process of the Bayesian Hierarchy model was conducted using the gamma distribution and Hamiltonian Monte Carlo sampling algorithm. The best modeling results were obtained using Bayesian hierarchy with micro variables that have a significant effect in most districts are the number of active cooperatives, accommodation, and restaurants/eating places. As for the macro level, the variables that influence the variation of night light radiation are HDI, GRDP, and the number of district electricity customers. The hierarchical Bayesian model has a DIC value of 5,08, lower than the one-level Bayesian model with a DIC of 12,354, indicating a higher goodness of fit. The thematic map obtained from the model estimation results using Bayesian hierarchy can better describe the night light radiation of each sub-district as an indicator of the condition of electricity availability in Riau Islands.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Bayesian Hierarki, Kepulauan Riau, Listrik, Hamiltonian Monte Carlo, VIIRS, Electricity, Hamiltonian Monte Carlo, Hierarchical Bayesian, Riau Archipelago, VIIRS |
| Subjects: | G Geography. Anthropology. Recreation > GA Mathematical geography. Cartography > GA102.4.R44 Cartography--Remote sensing H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA31.3 Regression. Correlation H Social Sciences > HA Statistics > HA31.7 Estimation |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Kevin Alessandro Frederick S |
| Date Deposited: | 08 Aug 2024 12:01 |
| Last Modified: | 08 Aug 2024 12:01 |
| URI: | http://repository.its.ac.id/id/eprint/114909 |
Actions (login required)
 |
View Item |