Share Email Print

Proceedings Paper • Open Access

MaxEnt (Maximum Entropy) model for predicting prehistoric cave sites in Karst area of Gunung Sewu, Gunung Kidul, Yogyakarta

Paper Abstract

The Gunungsewu area is one of karstic regions in the southern part of the island of Java whose a variety of archaeological remains. Archaeological data were scattered around the Gunungsewu region starting from remains of humans fossil and animals, bone artifacts, clamshell artifacts, Pacitanian cultural stone artifacts, and prehistoric caves that show evidence of occupation caves as well as sustain of prehistoric human communities. This research used the model MaxEnt as a method for estimating prehistoric occupation cave sites in the karst area of Gunung Sewu, Gunung Kidul. The objectives of this research were: (1) assessed the ability of DEM Alos Palsar, Sentinel-2a images and GIS data to extract environmental parameters related to prehistoric occupation cave sites. (2) prepared a spatial model for estimating prehistoric occupation cave sites using DEM Alos Palsar image, Sentinel-2a imagery and GIS data for input model MaxEnt (maximum entropy). (3) test accuracy of model MaxEnt to estimated the location of prehistoric occupation caves. This research used 68 location cave as attendance data input in the model MaxEnt. Environmental variables extracted from the 12.5-meter resolution DEM Alos Palsar, Sentinel- 2A images with 10 meters resolution, and GIS data. There were 8 environmental variables used in this study, there are: OBIA valley-hill classification map, distance map of valley base, elevation map, slope map, aspect map, distance map of lineament, lineament density map and map distance from water sources. Modeling using location data input as many as 68 prehistoric occupations pointed caves with 8 environmental variables resulted in modeling performance with an AUC value of 0. 715 with good performance. Modeling produces the results of the jackknife test, analyzes the response curve of the environment variable and probability map in the researched area. Based on the probability map produced, this studied obtained prehistoric cave location data. Therefore, this modeling shows that MaxEnt could be used as a method for estimating archeological sites.

Paper Details

Date Published: 21 November 2019
PDF: 9 pages
Proc. SPIE 11311, Sixth Geoinformation Science Symposium, 113110B (21 November 2019); doi: 10.1117/12.2543522
Show Author Affiliations
Luthfi Alwi Muttaqin, Univ. Gadjah Mada (Indonesia)
Sigit Heru Murti, Univ. Gadjah Mada (Indonesia)
Bowo Susilo, Univ. Gadjah Mada (Indonesia)

Published in SPIE Proceedings Vol. 11311:
Sixth Geoinformation Science Symposium
Sandy Budi Wibowo; Andi B. Rimba; Stuart Phinn; Ammar A. Aziz; Josaphat Tetuko Sri Sumantyo; Hasti Widyasamratri; Sanjiwana Arjasakusuma, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?