ABSTRACT
Machine learning can offer an efficient method to identify and map caves, sinkholes, and other cave-like features (i.e. sinkholes, rockshelters, voids) using remotely sensed imagery. While there exists a body of work applying machine learning for sinkhole identification, little work exists for caves. In the densely forested and rugged Maya Lowlands, developing such a methodology can help archaeologists to identify previously unknown caves that may contain important archaeological materials. Here, we introduce a proof-of-concept project that uses random forest and lidar-derived landscape morphometrics to map caves and other cave-like features in northwest Belize. Several undocumented caves and cave-like features were identified in our study area based on model results. Next steps towards making a more robust version of this model include the addition of more training data and integration of a larger number of morphologic parameters. Based on the results described here as well as those in cited works focused on caves, we proposed machine learning as a first step in cave and cave-like feature identification, followed then by fieldwork and ground-truthing.
Acknowledgments
We would like to thank the Sewanee Landscape Analysis Lab and the Lab Manager, Dr. Christopher Van de Ven, for providing the Sewanee dataset. We would like to thank the Sewanee Outing Program and John Benson for sharing his knowledge of Sewanee caves.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Data availability statement
The code that supports the findings of this study is available from the corresponding author, Leila Character, upon reasonable request: since caves can contain artifacts and sometimes are protected in and of themselves, the authors have chosen to not to make the code freely available. The availability of the lidar data would require further conversations and appropriate permissions from all parties involved in data collection.