In this study, ensemble learning was applied to develop a classification model capable of accurately estimating slope stability. Two prominent ensemble techniques—parallel learning and sequential learning—were applied to implement the ensemble classifiers. Additionally, for comparison, eight versatile machine learning algorithms were utilized to formulate the single-learning classification models. These classification models were trained and evaluated on the well-established global database of slope documented from 1930 to 2005. The performance of these classification models was measured by considering the F₁ score, accuracy, receiver operating characteristic (ROC) curve and area under the ROC curve (AUC). Furthermore, K-fold cross-validation was employed to fairly assess the generalization capacity of these models. The obtained results demonstrated the advantage of ensemble classifiers over single-learning classification models. When ensemble learning was used instead of the single learning, the average F₁ score, accuracy, and AUC of the models increased by 2.17%, 1.66%, and 6.27%, respectively. In particular, the ensemble classifiers with sequential learning exhibited better performance than those with parallel learning. The ensemble classifiers on the extreme gradient boosting (XGB-CM) framework clearly provided the best performance on the test set, with the highest F₁ score, accuracy, and AUC of 0.914, 0.903, and 0.95, respectively. The excellent performance on the spatially well-distributed database along with its capacity to distribute computing indicates the significant potential applicability of the presented ensemble classifiers, particularly the XGB-CM, for landslide risk assessment and management on a global scale.

在这项研究中，集成学习被用于开发能够精确估计边坡稳定性的分类模型。应用了两种杰出的集成技术（并行学习和顺序学习）来实现集成分类器。此外，为了进行比较，使用了八种通用机器学习算法来制定单学习分类模型。这些分类模型在1930年至2005年建立的完善的全球坡度数据库中进行了培训和评估。这些分类模型的性能是通过考虑F ₁得分，准确性，接收器工作特性（ROC）曲线和下坡面积来衡量的。ROC曲线（AUC）。此外，K折交叉验证被用来公平地评估这些模型的泛化能力。获得的结果证明了集成分类器优于单学习分类模型的优势。当使用集成学习而不是单一学习时，模型的平均F ₁得分，准确性和AUC分别增加了2.17％，1.66％和6.27％。特别地，具有顺序学习的集合分类器表现出比具有并行学习的集合分类器更好的性能。极端梯度增强（XGB-CM）框架上的集成分类器显然在测试集上提供了最佳性能，具有最高的F ₁分数，准确性和AUC分别为0.914、0.903和0.95。空间分布良好的数据库的出色性能及其分布计算的能力表明，提出的整体分类器，尤其是XGB-CM，在全球范围内的滑坡风险评估和管理中具有巨大的潜在适用性。