Classification of the Geochemical Composition of Metorite of Punggur (Astomulyo) by K-Nearest Neighbor Algorithm
Triyana Muliawati (a*)

a) Department of Mathematics, Institut Teknologi Sumatera
Jalan Terusan Ryacudu, Lampung 35365, Indonesia
*triyana.muliawati[at]ma.itera.ac.id

Abstract

The fall of a meteorite in Astomulyo Village, Punggur, Lampung Province in early 2021 is an interesting topic for further study. This rare object has been suggested to have a unique geochemical composition and a special connection with other meterorites. We aimed to trace its classification by comparing it with other well-known meteorites that have been studied previously. We approach the classification process using the k-nearest neighbor algorithm. The database used represents the geochemical data for each known meteorite group. As a result, we clearly identified that with a k-value = 5 and the proportion of test data 5/95 (in %), the geochemical composition of this meteorite is relatively close to that of the H-type chondrite group with a value accuracy of 91.67%. These results are consistent with the fact that the meteorite of Punggur has a high total iron and metallic composition.

Keywords: Meteorite- K-Nearest Neighbor- Geochemistry- Astomulyo

Topic: MATHEMATICS AND STATISTICS