Analisis Tree Counting Kelapa Sawit Menggunakan Metode Object-Based Image Analysis (OBIA) dan Random Forest Machine Learning (Studi Kasus: Kecamatan Cempaga Hulu, Kabupaten Kotawaringin Timur)

Abstract

Sebagai upaya mempercepat perhitungan jumlah pohon kelapa sawit guna asseting dalam produksi komoditas sawit, dapat menggunakan teknologi di bidang geomatika dengan mengaplikasikan pemanfaatan teknologi machine learning. Salah satu metode yang dapat digunakan untuk perhitungan jumlah pohon kelapa sawit dengan tepat, dan cepat adalah dengan klasifikasi berbasis objek menggunakan data mozaik orthophoto. Data tersebut dapat diolah menggunakan metode klasifikasi berupa Object Based Image Analysis (OBIA) dan Random Forest Machine Learning. Dalam pengolahan menggunakan masing masing sample pada sawit, tanah dan non sawit diwakili 80 sampel. Didapatkan hasil berupa raster lalu diolah menggunakan metode multiresolution. Hasil dari pengolahan otomatisasi sebesar 3098 titik pohon sawit dan hasil uji validasi digitasi manual sebesar 3034 titik pohon sawit sehingga didapat deviasi sebesar 64 titik pohon. Melalui pengujian performa pemodelan machine learning, yakni confusion matrix dengan nilai sebesar 0,89 dan kappa sebesar 0,78.

CC Licencing

Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).