No abstract

Warmer and drier conditions in temperate regions are increasing the length of the wildfire season. Given the greater fire frequency and extent of burned areas under climate warming, greater focus has been placed on predicting post-fire tree mortality as a crucial component of sustainable forest management. This study evaluates the potential of logistic regression models to predict post-fire tree mortality in Korean red pine (Pinus densiflora) stands, and we propose novel means of evaluating bark injury. In the Samcheok region of Korea, we measured topography (elevation, slope, and aspect), tree characteristics (tree/crown height and diameter at breast height (DBH)), and bark injuries (bark scorch height/proportion/index) at three sites subjected to a surface fire. We determined tree status (dead or live) over three years after the initial fire. The bark scorch index (BSI) produced the best univariate model, and by combining this index with the DBH produced the highest predictive capacity in multiple logistic regression models. A three-variable model (BSI, DBH, and slope) enhanced this predictive capacity to 87%. Our logistic regression analysis accurately predicted tree mortality three years post fire. Our three-variable model provides a useful and convenient decision-making tool for land managers to optimize salvage harvesting of post-fire stands.

No abstract

The Civilian Access Control Zone (CACZ), south of the Demilitarized Zone (DMZ) separating North and South Korea, has functioned as a unique bio-reserve owing to restrictions on human use. However, it is now increasingly threatened by damaged land and slope failures. In this study, a machine-learning-based method was used to assess slope stability by introducing the random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost), and logistic regression (LR) approaches. These classification models were trained and evaluated on 393 slope stability cases from 2009 to 2019 to assess slope stability in the northern area of the Civilian Control Line, South Korea. For comparison, the performance of these classification models was measured by considering the accuracy, Cohen’s kappa, F1-score, recall rate, precision, and area under the ROC curve (AUC). Furthermore, 14 influencing factors (slope, vegetation, structure conditions, etc.) were considered to explore feature importance. The evaluation and comparison of the results showed that the performance of all classifier models was satisfactory for assessing the stability of the slope, the ability of LR was validated (accuracy = 0.847; AUC = 0.838), and XGBoost proved to be the most efficient method for predicting slope stability (accuracy = 0.903; AUC = 0.900). Among the 14 influencing factors, the external condition was the most important. The proposed supervised learning method offers a promising method for assessing slope status, may be beneficial for government agencies in early-stage risk mitigation, and provides a database for efficient restoration management.

No abstract