Classification of terrestrial impact craters based on morphometric parameters using remote sensing data: a case study of Jeokjung-Chogye impact crater, South Korea

Abstract

This study aims to develop an automated impact crater classification machine learning (ML) method based on the morphometric parameters extracted from SRTM DEM. The training and testing dataset comprises data from 52 confirmed, well preserved, and moderately eroded impact craters and a recently discovered impact crater in Korea, Jeokjung Chogye Basin (JCB). The morphometric parameters including rim diameter, floor diameter, and wall width of complex craters and simple craters were tested by Mann Whitney U test and One Sample Wilcoxon signed rank test. The tests showed that those parameters can statistically separate the two types of craters. The Random Forest model classified them with an accuracy of 88.6% and a Kappa coefficient of 0.67, where rim diameter, floor diameter, and wall width were identified as variables with the highest Gini indices. Complex craters are characterized by a large flat diameter and wide wall width compared to simple craters with parabolic bases. The difference is caused by the impact energy when the craters were formed. The study confirmed that using machine learning, the complex craters and simple craters can be separated by checking the SRTM elevation model with machine learning methods. The morphometric parameters of JCB impact crater indicated that the crater is highly a complex crater concluded by both statistical tests and machine learning algorithm.