NURFAUZI, PRIMA (2024) ALGORITMA CONVEX HULL-BASED CLASSIFIER UNTUK DETEKSI TRAILING ALBEDO AWAN MENGGUNAKAN SENTINEL-5P NEAR REAL-TIME (Studi Kasus: Kota Bandung). S1 thesis, Universitas Mercu Buana Jakarta.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (HAL COVER)
01 COVER.pdf Download (469kB) |
|
Text (ABSTRAK)
02 ABSTRAK.pdf Download (30kB) |
|
Text (BAB I)
03 BAB 1.pdf Restricted to Registered users only Download (86kB) |
|
Text (BAB II)
04 BAB 2.pdf Restricted to Registered users only Download (389kB) |
|
Text (BAB III)
05 BAB 3.pdf Restricted to Registered users only Download (222kB) |
|
Text (BAB IV)
06 BAB 4.pdf Restricted to Registered users only Download (663kB) |
|
Text (BAB V)
07 BAB 5.pdf Restricted to Registered users only Download (30kB) |
|
Text (DAFTAR PUSTAKA)
08 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (150kB) |
|
Text (LAMPIRAN)
09 LAMPIRAN.pdf Restricted to Registered users only Download (459kB) |
Abstract
This research addresses the challenge of detecting albedo clouds in Sentinel-5P Near Real-Time (NRT) satellite imagery. Albedo clouds significantly impact climate modeling and weather predictions, necessitating accurate detection methods. Therefore, we developed a Convex Hull-based Classifier algorithm that integrates Convex Hull with classification to separate trailing albedo clouds from other elements in the imagery. This method utilizes spatial and spectral features of Sentinel-5P NRT imagery to enhance detection accuracy. Performance evaluation indicates an accuracy of 94.9%, precision of 90.1%, recall of 94.9%, and an F1- Score of 92.4%. These results reflect the success of the method in improving efficiency and reliability in albedo cloud detection. This research contributes to a better understanding of climate change and improved weather predictions through the utilization of satellite technology. Keywords for this study include Sentinel-5P NRT, albedo clouds, Convex Hull, classification, and trailing detection, emphasizing the utilization of satellite technology for a better understanding of climate change and enhanced weather predictions. Keywords: Albedo Clouds, Classification, Convex Hull, Sentinel-5P NRT, Trailing Detection Penelitian ini bertujuan menanggulangi tantangan dalam deteksi Albedo Awan pada citra satelit Sentinel-5P Near Real-Time (NRT). Albedo Awan memiliki dampak signifikan terhadap pemodelan iklim dan prediksi cuaca, memerlukan metode deteksi yang akurat. Oleh karena itu, kami mengembangkan algoritma Convex Hull-based Classifier yang mengintegrasikan pendekatan Convex Hull dengan klasifikasi untuk memisahkan trailing Albedo Awan dari elemen lain pada citra. Metode ini memanfaatkan fitur spasial dan spektral dari citra Sentinel-5P NRT untuk meningkatkan ketepatan deteksi. Evaluasi kinerja menunjukkan tingkat akurasi sebesar 94.9%, presisi 90.1%, recall 94.9%, dan F1-Score 92.4%. Hasil ini mencerminkan keberhasilan metode dalam meningkatkan efisiensi dan keandalan deteksi Albedo Awan. Penelitian ini berkontribusi pada pemahaman lebih baik terhadap perubahan iklim dan peningkatan prediksi cuaca dengan memanfaatkan teknologi satelit. Kata kunci untuk penelitian ini mencakup Sentinel-5P NRT, Albedo Awan, Convex Hull, klasifikasi, dan deteksi trailing, mencerminkan fokus pada pemanfaatan teknologi satelit untuk pemahaman lebih baik terhadap perubahan iklim dan peningkatan prediksi cuaca. Kata Kunci : Albedo Awan, Convex Hull, Deteksi Trailing, Klasifikasi, Sentinel-5P NRT
Actions (login required)
 |
View Item |
