FATURRAHMAN, FEBI TAUFIK (2024) UNVEILING THE DYNAMICS OF NO2 POLLUTION: INSIGHTS FROM SENTINEL-5P TROPOMI MONITORING WITH KNN (K-Nearest Neighbour) AND SVM (Support Vector Machine) WITH RBF (Radial Basic Function) KERNEL ANALYSIS. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (540kB) | Preview |
|
|
Text (ABSTRAK)
02 ABSTRAK.pdf Download (204kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
03 BAB 1.pdf Restricted to Registered users only Download (240kB) |
|
|
Text (BAB II)
04 BAB 2.pdf Restricted to Registered users only Download (537kB) |
|
|
Text (BAB III)
05 BAB 3.pdf Restricted to Registered users only Download (395kB) |
|
|
Text (BAB IV)
06 BAB 4.pdf Restricted to Registered users only Download (398kB) |
|
|
Text (BAB V)
07 BAB 5.pdf Restricted to Registered users only Download (202kB) |
|
|
Text (DAFTAR PUSTAKA)
8 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (274kB) |
|
|
Text (LAMPIRAN)
09 LAMPIRAN.pdf Restricted to Registered users only Download (286kB) |
Abstract
This journal unveils the dynamics of NO2 pollution in Jakarta through monitoring using Sentinel5P TROPOMI technology and analysis of KNN and SVM algorithms with RBF kernel. In the evaluation of data from July to September 2019, both SVM and KNN models consistently provided reliable results. SVM achieved a Kappa of 0.93, accuracy of 0.96, and an F1-Score of 0.61, maintaining resilience during the period of February to July 2023. KNN demonstrated remarkable performance in July-September 2019, with increased accuracy and precision in February-July. The study emphasizes the crucial role of satellite monitoring technology and machine learning algorithms in understanding and addressing urban air pollution issues. The findings contribute valuable insights to the scientific community and advocate for the adoption of such technologies to enhance environmental monitoring and management strategies in urban areas. Keywords: KNN, SVM, RBF, Pollution, Jakarta, Remote Sensing, GEE Jurnal ini mengungkap dinamika pencemaran NO2 di Jakarta melalui pemantauan menggunakan teknologi Sentinel-5P TROPOMI dan analisis algoritma KNN dan SVM dengan kernel RBF. Dalam evaluasi data pada bulan Juli hingga September 2019, baik model SVM maupun KNN secara konsisten memberikan hasil yang dapat diandalkan. SVM mencapai Kappa 0,93, akurasi 0,96, dan F1-Score 0,61, menjaga ketahanan selama periode Februari hingga Juli 2023. KNN menunjukkan kinerja luar biasa pada Juli-September 2019, dengan peningkatan akurasi dan presisi pada Februari-Juli. Studi ini menekankan peran penting teknologi pemantauan satelit dan algoritma pembelajaran mesin dalam memahami dan mengatasi masalah polusi udara perkotaan. Temuan ini memberikan kontribusi wawasan berharga bagi komunitas ilmiah dan mengadvokasi penerapan teknologi tersebut untuk meningkatkan pemantauan lingkungan dan strategi pengelolaan di wilayah perkotaan. Keywords: KNN, SVM, RBF, Polusi, Jakarta, Remote Sensing, GEE
| Item Type: | Thesis (S1) |
|---|---|
| Call Number CD: | FIK/INFO. 24 087 |
| Call Number: | SIK/15/24/064 |
| NIM/NIDN Creators: | 41518010032 |
| Uncontrolled Keywords: | KNN, SVM, RBF, Polusi, Jakarta, Remote Sensing, GEE |
| Subjects: | 600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 628 Sanitary Engineering and Environmental Protection Engineering/Rekayasa Sanitasi dan Teknik Perlindungan Lingkungan, Teknik Lingkungan 600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 628 Sanitary Engineering and Environmental Protection Engineering/Rekayasa Sanitasi dan Teknik Perlindungan Lingkungan, Teknik Lingkungan > 628.5 Pollution Control and Industrial Sanitation Engineering/Pengawasan Polusi dan Teknik Sanitasi Industri |
| Divisions: | Fakultas Ilmu Komputer > Informatika |
| Depositing User: | khalimah |
| Date Deposited: | 25 Apr 2024 02:24 |
| Last Modified: | 25 Apr 2024 02:24 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/88187 |
Actions (login required)
 |
View Item |
