Model Multivariate Generalized Space Time Autoregressive untuk Monitoring Kualitas Udara di Surabaya

Nahdliyah, Nurun (2019) Model Multivariate Generalized Space Time Autoregressive untuk Monitoring Kualitas Udara di Surabaya. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 06211540000027-Undergraduate_Theses.pdf] Text
06211540000027-Undergraduate_Theses.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2022.

Download (36MB) | Request a copy

Abstract

Jumlah penduduk di Kota Surabaya mengalami peningkatan dari tahun ke tahun. Hal ini juga diiringi dengan peningkatan jumlah kendaraan bermotor yang dapat menyebabkan pencemaran udara. Parameter pencemar udara yang dihasilkan oleh kendaraan bermotor adalah CO dan PM10. Kualitas udara di Kota Surabaya dipantau dengan AQMS yang dipasang di stasiun SUF. Sebagai tindakan preventif terhadap pencemaran udara, perlu dilakukan monitoring kualitas udara dengan peramalan (forecasting). Penelitian ini bertujuan untuk mendapatkan pemodelan dan peramalan CO dan PM10 di Kota Surabaya dengan menggunakan Multivariate Generalized Space Time Autoregressive (MGSTAR). Data yang digunakan dalam penelitian ini adalah CO dan PM10 di SUF 1, SUF 6, dan SUF 7 Kota Surabaya. Penelitian ini terdiri dari kajian teori, kajian simulasi, dan kajian terapan. Pada kajian teori didapatkan model MGSTAR yang dapat digunakan untuk memodelkan data dengan dua variabel di tiga lokasi yang berbeda. Estimasi parameter untuk model tersebut dapat diperoleh dengan menggunakan OLS yang merupakan hasil dari kajian simulasi. Sedangkan pada kajian terapan, peramalan dengan ARIMA memberikan hasil lebih baik dibandingkan peramalan dengan MGSTAR.
================================================================================================
Population in Surabaya has been increased year to year. This is also followed by the increase in the number of vehicles that caused air polution. The air polution paramater that caused by vehicles are CO and PM10. Air quality in Surabaya being monitored with AQMS that installed in SUF station. As a preventive action to air polution, there is necessary to monitoring air quality with forecasting. The aim of this research is to get model and forecast of CO and PM10 -in Surabaya using Multivariate Generalized Space Time Autoregressive (MGSTAR). Data that be used in this research are CO and PM10 on SUF 1, SUF 6, and SUF 7 in Surabaya. This research consist of theoretical study, simulation study, and applied study. From theoretical study, MGSTAR model for forecasting two variables in three different location has been proposed and developed. Moreover, the simulation study showed that parameter estimation for MGSTAR model could be obtained by using Ordinary Least Square (OLS). Additionally, the result of applied study showed that ARIMA model yielded more accurate forecast than MGSTAR model. It lines with the result of M3 competition that simple method did not necessary give better tha the singular one.

Item Type: Thesis (Undergraduate)
Additional Information: RSSt 519.535 Nah m-1 2019
Uncontrolled Keywords: CO, MGSTAR, Pencemaran Udara, PM10
Subjects: Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry)
Q Science > QA Mathematics > QA278 Cluster Analysis. Multivariate analysis. Correspondence analysis (Statistics)
T Technology > TD Environmental technology. Sanitary engineering > TD883.5 Air--Pollution
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Nurun Nahdliyah
Date Deposited: 30 Dec 2021 08:13
Last Modified: 30 Dec 2021 08:13
URI: http://repository.its.ac.id/id/eprint/61901

Actions (login required)

View Item View Item