dc.contributor.advisor | Jaya, I Nengah Surati Jaya | |
dc.contributor.author | Ranti, Aulia | |
dc.date.accessioned | 2023-09-26T08:24:39Z | |
dc.date.available | 2023-09-26T08:24:39Z | |
dc.date.issued | 2023-09-26 | |
dc.identifier.uri | http://repository.ipb.ac.id/handle/123456789/125498 | |
dc.description.abstract | Kajian ini mengulas tentang pembangunan teknik algoritma pohon keputusan dari pembelajar mesin (decision tree of machine learning) dengan fokus utama mengidentifikasi tanaman kakao agroforestri dan kakao monokultur. Tujuan utama dari penelitian ini adalah menemukan algoritma pohon keputusan terbaik untuk mendapatkan informasi sebaran spasial kakao agroforestri dan kakao monokultur. Penelitian ini menguji tiga kriteria pengambilan keputusan yaitu Information Gain, Gain Ratio, dan Gini Indeks menggunakan peubah-peubah spektral yang diturunkan dari SPOT 7 dan peubah-peubah geo-sosio biofisik. Kajian ini menemukan bahwa integrasi antara empat peubah spektral dan lima peubah geo-sosio biofisik menghasilkan performa model terbaik dengan overall accuracy (OA) 93,54%. Kajian ini menemukan bahwa kriteria terbaik dalam mendeteksi kakao adalah information gain dan citra sintetis NDVI menjadi peubah paling berpengaruh terhadap model. Kajian ini menemukan bahwa minimal producer’s dan user’s accuracy dari algoritma yang dihasilkan adalah 94,20% dan 93,76%. | id |
dc.description.abstract | This study describes the development of the "decision tree of machine learning" algorithm development technique with the main focus on identifying agroforestry cocoa and monoculture cocoa plants. The main objective of this study is to find the best decision tree algorithm to obtain accurate spatial distribution of agroforestry and monoculture cacao. This study examined three criteria of the decision tree, namely the Information gain, the Gain ratio, and the Gini index algorithms, using spectral variables derived from SPOT 7 and bio-socio geophysics variables. This study found that integrating four spectral variables and five bio-socio-geophysics attributes resulted in the best model performance with an overall accuracy (OA) of 93,54%. This study found that the best criterion for detecting cocoa is information gain, and the NDVI was identified as the most influential attribute of the model. This study found that the minimum producer's and user's accuracy of the resulting algorithm is 94,20% and 93,76%. | id |
dc.language.iso | id | id |
dc.publisher | IPB University | id |
dc.title | Deteksi Agroforestri Kakao dengan Algoritma Pohon Keputusan Pembelajar Mesin Menggunakan Citra Spot 7: Studi Kasus Kecamatan Malangke dan Malangke Barat, Luwu Utara | id |
dc.title.alternative | Detecting Cocoa Agroforestry using Decision Tree of Machine Learning Algorithm Through SPOT 7 Imagery: A Case Study of Malangke and West Malangke Districts, North Luwu | id |
dc.type | Undergraduate Thesis | id |
dc.subject.keyword | agroforestri | id |
dc.subject.keyword | indeks vegetasi | id |
dc.subject.keyword | kakao | id |
dc.subject.keyword | pembelajar mesin | id |
dc.subject.keyword | pohon keputusan | id |
dc.subject.keyword | agroforestry | id |
dc.subject.keyword | cacao | id |
dc.subject.keyword | decision tree | id |
dc.subject.keyword | machine learning | id |
dc.subject.keyword | vegetation index | id |