Optimalisasi model prediksi kesesuaian lahan kelapa sawit menggunakan algoritme pohon keputusan spasial

Andi Nurkholis (Department of Informatics, Universitas Teknokrat Indonesia)
Imas Sukaesih Sitanggang (Department of Computer Science, Institut Pertanian Bogor)

Jurnal Teknologi dan Sistem Komputer
Volume 8, Issue 3, Year 2020 (July 2020)

Land suitability evaluation has a vital role in land use planning aimed to increase food production effectiveness. Palm oil is a leading and strategic commodity for Indonesian people, which is predicted consumption will exceed production in the future. This study aims to evaluate palm oil land suitability using a spatial decision tree algorithm that is conventional decision tree modification for spatial data classification with adding spatial join relation. The spatial dataset consists of eight explanatory layers (soil nature and characteristics), and a target layer (palm oil land suitability) in Bogor District, Indonesia. This study produced three models, where the best model was obtained based on optimizing accuracy (98.18 %) and modeling time (1.291 seconds). The best model has 23 rules, soil texture as the root node, two variables (drainage and cation exchange capacity) are uninvolved, with land suitability visualization obtains percentage S2 (29.94 %), S3 (53.16 %), N (16.57 %), and water body (0.33 %).