PRATIWI, AMALIA (2024) KLASIFIKASI TINGKAT AEROSOL TERHADAP SINAR ULTRAVIOLET PLTU SURALAYA MENGGUNAKAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK INSTRUMEN TROPOMI PADA SENTINEL-5P. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (569kB) | Preview |
|
|
Text (ABSTRAK)
02 Abstrak.pdf Download (31kB) | 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 (271kB) |
|
|
Text (BAB II)
04 Bab 2.pdf Restricted to Registered users only Download (385kB) |
|
|
Text (BAB III)
05 Bab 3.pdf Restricted to Registered users only Download (82kB) |
|
|
Text (BAB IV)
06 Bab 4.pdf Restricted to Registered users only Download (612kB) |
|
|
Text (BAB V)
07 Bab 5.pdf Restricted to Registered users only Download (28kB) |
|
|
Text (DAFTAR PUSTAKA)
08 Daftar Pustaka.pdf Restricted to Registered users only Download (135kB) |
|
|
Text (LAMPIRAN)
09 Lampiran.pdf Restricted to Registered users only Download (520kB) |
Abstract
This study aims to classify aerosol levels in relation to ultraviolet radiation at the Suralaya coal-fired power plant (PLTU) using the Convolutional Neural Network (CNN) algorithm with data from the TROPOMI instrument on the Sentinel-5P satellite. The increase in air pollution in the regions of Banten, West Java, and DKI Jakarta, primarily caused by emissions from coal-fired power plants, underscores the need for improved monitoring systems. In this research, aerosol data were collected from TROPOMI and processed using remote sensing techniques and CNN analysis to identify pollution levels. The study successfully classified aerosol levels in the Suralaya PLTU area using Sentinel-5P satellite data from June 1 to December 31, 2023. The Convolutional Neural Network (CNN) algorithm demonstrated high performance with an accuracy of 96.40%, precision of 96.68%, recall of 96.40%, and an F1-Score of 96.47%, indicating a high agreement between predictions and actual results. Aerosol content in this area tends to be high, with concentrations predominantly at level 2 (unhealthy). The model also achieved a MAPE of 2.75, indicating a low prediction error rate. Overall, the CNN algorithm proved reliable in classifying aerosol levels and air quality. Keyword: Aerosol, Suralaya Coal-Fired Power Plant, Convolutional Neural Network, TROPOMI, Sentinel-5P Penelitian ini bertujuan untuk mengklasifikasikan tingkat aerosol terhadap sinar ultraviolet di PLTU Suralaya menggunakan algoritma Convolutional Neural Network (CNN) dengan data dari instrumen TROPOMI pada satelit Sentinel-5P. Peningkatan polusi udara di wilayah Banten, Jawa Barat, dan DKI Jakarta, terutama disebabkan oleh emisi dari PLTU batu bara, mendorong perlunya sistem pemantauan yang lebih baik. Dalam penelitian ini, data aerosol dikumpulkan dari TROPOMI dan diproses menggunakan teknik penginderaan jauh serta analisis CNN untuk mengidentifikasikan tingkat polusi. Penelitian ini berhasil mengklasifikasikan tingkat aerosol di wilayah PLTU Suralaya menggunakan data satelit Sentinel-5P dari 1 Juni hingga 31 Desember 2023. Algoritma Convolutional Neural Network (CNN) menunjukkan performa tinggi dengan akurasi 96,40%, presisi 96,68%, recall 96,40%, dan F1-Score 96,47%, menunjukkan kesepakatan tinggi antara prediksi dan hasil aktual. Kandungan aerosol di wilayah ini cenderung tinggi dengan konsentrasi dominan pada tingkat 2 (tidak sehat). Model ini juga mencapai MAPE 2,75, menunjukkan tingkat kesalahan prediksi yang rendah. Secara keseluruhan, algoritma CNN terbukti andal dalam klasifikasi tingkat aerosol dan kualitas udara. Kata kunci: Aerosol, PLTU Suralaya, Convolutional Neural Network, TROPOMI, Sentinel-5P
Actions (login required)
 |
View Item |
