Yuliarto, Niam Zuhdi (2020) Penggunaan Metode Support Vector Regression untuk Prediksi Emisi Karbon Kebakaran Berdasarkan Indikator Iklim di Kabupaten Ogan Komering Ilir. Other thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
06211640000061-UNDERGRADUATE_THESIS.pdf Download (4MB) | Preview |
Abstract
Kabupaten Ogan Komering Ilir merupakan salah satu daerah di Indonesia yang sering mengalami kebakaran hutan dan lahan. Selain merugikan masyarakat, emisi kebakaran berupa asap yang ditimbulkan menyebabkan banyak kerugian bagi pemerintah karena banyaknya aktifitas yang harus diberhentikan. Emisi karbon kebakaran yang dihasilkan membuat Indonesia menjadi negara terbesar penyumbang gas pendukung pemanasan global dunia. Emisi karbon kebakaran memiliki hubungan non-linier dengan indikator iklim. Prediksi emisi karbon kebakaran dilakukan menggunakan metode regresi linier dan support vector regression. Data yang digunakan bersumber dari GFED, TRMM, GLDAS dan MEI ENSO Index. Metode support vector regression berdasarkan curah hujan dan Elnino-Indeks memiliki prediksi yang lebih baik dari pada skenario pemodelan lainnya baik menggunakan metode support vector regression maupun regresi linier. Emisi karbon kebakaran banyak muncul di Kabupaten Ogan Komering Ilir bagian tengah, timur dan utara dimana daerah tersebut merupakan kawasan hutan produksi kelapa sawit.
=================================================================================================================================
Ogan Komering Ilir Regency is one of the regions in Indonesia which is often experiences forest and land fires. In addition to harming the community, fire emissions in the form of smoke caused a lot of harm to the government because of the many activities that must be stopped. The resulting carbon emissions from fires make Indonesia become the largest gas contributor to supporting global warming. Fire carbon emissions have a nonlinear relationship with climate indicators. Fire carbon emissions prediction is done by using linear regression and support vector regression methods. The data used were sourced from GFED, TRMM, GLDAS and MEI ENSO Index. The support vector regression method based on rainfall and Elnino-Index has a better prediction than other modeling scenarios using either the support vector regression method or linear regression. Fire carbon emissions have arisen in the central, eastern and northern Ogan Komering Ilir districts where the area is a palm oil production forest area.
Item Type: | Thesis (Other) |
---|---|
Additional Information: | RSSt 519.536 Yul p-1 2020 |
Uncontrolled Keywords: | Emisi Karbon Kebakaran, Iklim, Ogan Komering Ilir, Remote-Sensing Data, SVR. |
Subjects: | H Social Sciences > HA Statistics > HA30.3 Time-series analysis H Social Sciences > HA Statistics > HA31.3 Regression. Correlation |
Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
Depositing User: | Niam Zuhdi Yuliarto |
Date Deposited: | 30 Apr 2024 06:49 |
Last Modified: | 30 Apr 2024 06:49 |
URI: | http://repository.its.ac.id/id/eprint/74031 |
Actions (login required)
![]() |
View Item |