PERBANDINGAN ALGORITMA GRAPH NEURAL NETWORK DAN ALGORITMA MAXIMUM LIKELIHOOD DALAM MENDETEKSI TINGKAT KEKERINGAN PADA TANAMAN KOPI BERDASARKAN EKSTRAKSI FITUR NORMALIZED DIFFERENCE DROUGHT INDEX: STUDI KASUS DI PERKEBUNAN KOPI MEKAR TANI)

NASUTION, WARDAH FAKHRIYYAH D (2024) PERBANDINGAN ALGORITMA GRAPH NEURAL NETWORK DAN ALGORITMA MAXIMUM LIKELIHOOD DALAM MENDETEKSI TINGKAT KEKERINGAN PADA TANAMAN KOPI BERDASARKAN EKSTRAKSI FITUR NORMALIZED DIFFERENCE DROUGHT INDEX: STUDI KASUS DI PERKEBUNAN KOPI MEKAR TANI). S1 thesis, Universitas Mercu Buana Jakarta.

	Text (HAL COVER) 01 COVER.pdf Download (408kB)
	Text (ABSTRAK) 02 ABSTRAK.pdf Download (34kB)
	Text (BAB I) 03 BAB 1.pdf Restricted to Registered users only Download (112kB)
	Text (BAB II) 04 BAB 2.pdf Restricted to Registered users only Download (556kB)
	Text (BAB III) 05 BAB 3.pdf Restricted to Registered users only Download (178kB)
	Text (BAB IV) 06 BAB 4.pdf Restricted to Registered users only Download (404kB)
	Text (BAB V) 07 BAB 5.pdf Restricted to Registered users only Download (32kB)
	Text (DAFTAR PUSTAKA) 08 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (138kB)
	Text (LAMPIRAN) 09 LAMPIRAN.pdf Restricted to Registered users only Download (394kB)

Abstract

Coffee plantations in Betara Regency, Jambi Province, Indonesia are vulnerable to drought because it can have a significant impact on crop yield and quality. Drought can disrupt the growth of coffee plants and result in a significant reduction in production, so it is important to be aware of the potential risk of drought on coffee plantations. This research proposes an innovative approach that aims to develop a robust and precise method for identifying drought in coffee plantations. This method uses Normalized Difference Drought Index (NDDI) extraction as a drought index and compares the Maximum Likelihood Algorithm and the GNN Algorithm to determine the performance of the best algorithm model for detecting the level of drought in coffee plantations. The proposed method utilizes Google Earth Engine to obtain Sentinel-2A satellite imagery from the Mekar Tani Coffee Plantation in Betara District. The research results show that the Maximum Likelihood Algorithm is superior and more suitable for detecting the level of drought in coffee plantations compared to GNN by achieving an accuracy of 0.98, precision 0.98, recall 0.97, and F1-Score 0.99 based on confusion matrix calculations. Therefore, this research can help contribute to coffee farmers and researchers in identifying the level of drought and potential risk of drought in a region. Keywords: Coffee Plantations, Drought detection, Maximum Likelihood, Graph Neural Network, NDDI Perkebunan kopi di Kabupaten Betara, Provinsi Jambi, Indonesia rentan terhadap kekeringan karena dapat berdampak signifikan terhadap hasil dan kualitas tanaman. Kekeringan dapat mengganggu pertumbuhan tanaman kopi dan mengakibatkan penurunan produksi secara signifikan sehingga penting untuk mewaspadai potensi risiko kekeringan pada perkebunan kopi. Penelitian ini mengusulkan pendekatan inovatif yang bertujuan untuk membangun metode yang kuat dan tepat untuk mengidentifikasi kekeringan di perkebunan kopi. Metode ini menggunakan ekstraksi Normalized Difference Drought Index (NDDI) sebagai indeks kekeringan dan melakukan perbandingan Algoritma Maximum Likelihood dan Algoritma GNN untuk mengetahui performa model algoritma terbaik untuk mendeteksi tingkat kekeringan di perkebunan kopi. Metode yang diusulkan memanfaatkan Google Earth Engine untuk memperoleh citra satelit Sentinel-2A dari Perkebunan Kopi Mekar Tani di Kecamatan Betara. Hasil penelitian menunjukkan bahwa Algoritma Maximum Likelihood lebih unggul dan lebih cocok untuk mendeteksi tingkat kekeringan perkebunan kopi dibandingkan GNN dengan mencapai akurasi 0.98, presisi 0.98, recall 0.97, dan F1-Score 0.99 berdasarkan perhitungan matriks konfusi. Oleh karena itu, penelitian ini dapat membantu memberikan kontribusi bagi petani kopi dan peneliti untuk mengidentifikasi tingkat kekeringan dan potensi risiko kekeringan di suatu wilayah. Keywords: Perkebunan kopi, Deteksi kekeringan, Maximum Likelihood, Graph Neural Network, NDDI

Item Type:	Thesis (S1)
Call Number CD:	FIK/INFO. 24 035
Call Number:	SIK/15/24/028
NIM/NIDN Creators:	41520010085
Uncontrolled Keywords:	Perkebunan kopi, Deteksi kekeringan, Maximum Likelihood, Graph Neural Network, NDDI
Subjects:	000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.3 Artificial Intelligence/Kecerdasan Buatan > 006.32 Neural Nets (Neural Network)/Jaringan Saraf Buatan 100 Philosophy and Psychology/Filsafat dan Psikologi > 130 Paranormals/Paranormal > 133 Parapsychology and Occultism/Parapsikologi dan Ilmu Ghaib > 133.3 Divinatory Arts/Kepercayaan Kepada Tahayul > 133.32 Fortune-Telling by Crystals and Stones; Dowsing; Fortune-Telling by Cards, Tea Leaves and Coffee Grounds, Oracles and Sibyls/Mencari Peruntungan Lewat Kristal dan Batu; Pencelupan; Mencari Peruntungan Lewat Kartu, Daun Teh and Kopi, Oracle and Siby 500 Natural Science and Mathematics/Ilmu-ilmu Alam dan Matematika > 510 Mathematics/Matematika > 518 Numerical Analysis/Analisis Numerik, Analisa Numerik > 518.1 Algorithms/Algoritma 600 Technology/Teknologi > 630 Agriculture and Related Technologies/Pertanian dan Teknologi Terkait > 633 Field and Plantation Crops/Tanaman Lapangan dan Perkebunan
Divisions:	Fakultas Ilmu Komputer > Informatika
Depositing User:	khalimah
Date Deposited:	15 Feb 2024 07:06
Last Modified:	15 Feb 2024 07:06
URI:	http://repository.mercubuana.ac.id/id/eprint/86100

Actions (login required)

View Item