@article{ART003370705},
author={Gwang-Jin Park and Moon Su Park},
title={Machine Learning-Based Rock Class Prediction Using Eco-Geological Forest Growth Indicators for Forest Road Cut-Slope Design},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2026},
volume={31},
number={8},
pages={97-105}
TY - JOUR
AU - Gwang-Jin Park
AU - Moon Su Park
TI - Machine Learning-Based Rock Class Prediction Using Eco-Geological Forest Growth Indicators for Forest Road Cut-Slope Design
JO - Journal of The Korea Society of Computer and Information
PY - 2026
VL - 31
IS - 8
PB - The Korean Society Of Computer And Information
SP - 97
EP - 105
SN - 1598-849X
AB - This study developed an eco-geological approach for predicting rock classes in forest road cut slopes using forest spatial information and machine learning. A total of 330 cut slopes in eastern Jeollanam-do, South Korea, were classified as Hard Rock, Soft Rock, Weathered Rock, or Soil. Topographic and geological variables were combined with forest-derived growth indicators, including HIAge, HIAC, HIDBH, and DBHAge. Seven machine learning algorithms were compared, and Random Forest achieved the highest performance, with an accuracy of 93.88% and an AUC of 0.9895. HIAge and HIAC showed high effect sizes and variable importance, indicating that vegetation growth characteristics may reflect bedrock weathering conditions. The results suggest that forest-derived indicators can serve as eco-geological proxies for high-precision rock class prediction and provide a cost-effective, non-invasive method for assessing ground conditions in forested mountainous areas.
KW - Rock Class Prediction;Machine Learning;Forest Spatial Information;Eco-Geological Proxy;Forest-Derived Growth Indicators
DO -
UR -
ER -
Gwang-Jin Park and Moon Su Park. (2026). Machine Learning-Based Rock Class Prediction Using Eco-Geological Forest Growth Indicators for Forest Road Cut-Slope Design. Journal of The Korea Society of Computer and Information, 31(8), 97-105.
Gwang-Jin Park and Moon Su Park. 2026, "Machine Learning-Based Rock Class Prediction Using Eco-Geological Forest Growth Indicators for Forest Road Cut-Slope Design", Journal of The Korea Society of Computer and Information, vol.31, no.8 pp.97-105.
Gwang-Jin Park, Moon Su Park "Machine Learning-Based Rock Class Prediction Using Eco-Geological Forest Growth Indicators for Forest Road Cut-Slope Design" Journal of The Korea Society of Computer and Information 31.8 pp.97-105 (2026) : 97.
Gwang-Jin Park, Moon Su Park. Machine Learning-Based Rock Class Prediction Using Eco-Geological Forest Growth Indicators for Forest Road Cut-Slope Design. 2026; 31(8), 97-105.
Gwang-Jin Park and Moon Su Park. "Machine Learning-Based Rock Class Prediction Using Eco-Geological Forest Growth Indicators for Forest Road Cut-Slope Design" Journal of The Korea Society of Computer and Information 31, no.8 (2026) : 97-105.
Gwang-Jin Park; Moon Su Park. Machine Learning-Based Rock Class Prediction Using Eco-Geological Forest Growth Indicators for Forest Road Cut-Slope Design. Journal of The Korea Society of Computer and Information, 31(8), 97-105.
Gwang-Jin Park; Moon Su Park. Machine Learning-Based Rock Class Prediction Using Eco-Geological Forest Growth Indicators for Forest Road Cut-Slope Design. Journal of The Korea Society of Computer and Information. 2026; 31(8) 97-105.
Gwang-Jin Park, Moon Su Park. Machine Learning-Based Rock Class Prediction Using Eco-Geological Forest Growth Indicators for Forest Road Cut-Slope Design. 2026; 31(8), 97-105.
Gwang-Jin Park and Moon Su Park. "Machine Learning-Based Rock Class Prediction Using Eco-Geological Forest Growth Indicators for Forest Road Cut-Slope Design" Journal of The Korea Society of Computer and Information 31, no.8 (2026) : 97-105.
