This study uses machine learning to analyze local seismic features' influence on damage from the 6 February 2023 Türkiye Earthquakes.The input features include Vs (the average shear wave velocity to a depth of 30 m), f (the predominant frequency of the site), A (HVSR ratio for the site), and EB (engineering bedrock depth), along with the target feature of damage status for 44 locations. Machine learning involves Random Forest (RF), K-nearest Neighbor (KNN), Logistic Regression (LR), Decision Trees (DT), Support Vector Machines (SVM), Stochastic Gradient Descent (SGD), and Multilayer Perceptron (MP) algorithms. Also, five-fold cross-validation is employed to acquire suitable hyperparameters, enhancing its efficacy in modeling small sample sets. RF emerged as the most effective in whole performance metrics, presenting recall scores for damage and no damage conditions respectively by a 94% and 92% ratio and achieving a damage status prediction accuracy of 93%. All remaining algorithms also exhibited remarkable performance, reaching a minimum accuracy of 89% by DT, and recall score for no damage condition with 80% by MP and damage condition with 88% by SVM and SGD. The outcomes definitively designate EB as the most crucial parameter, attributing 52% importance to its role in building damage occurrence within the study area. In contrast, significance values were determined as 24%, 18%, and 6% for f, Vs and A respectively. These findings underscore the importance of demonstrating that initial damage estimation in high seismic hazard zones can be effectively carried out using machine learning approaches through seismic-based local site parameters.

中文翻译：

---

使用机器学习预测当地场地对地震脆弱性的影响：对 2023 年 2 月 6 日土耳其地震的研究


本研究使用机器学习来分析当地地震特征对 2023 年 2 月 6 日土耳其地震损害的影响。输入特征包括 Vs（30 m 深度的平均剪切波速度）、f（该地点的主频率） 、A（场地的 HVSR 比率）和 EB（工程基岩深度），以及 44 个位置的损坏状态目标特征。机器学习涉及随机森林（RF）、K近邻（KNN）、逻辑回归（LR）、决策树（DT）、支持向量机（SVM）、随机梯度下降（SGD）和多层感知器（MP）算法。此外，还采用五重交叉验证来获取合适的超参数，增强其对小样本集建模的效率。 RF 成为整体性能指标中最有效的，损坏和无损坏情况的召回率分别为 94% 和 92%，损坏状态预测准确度达到 93%。所有其余算法也表现出出色的性能，DT 的最低准确率达到 89%，MP 的无损坏条件召回率达到 80%，SVM 和 SGD 的损坏条件召回率达到 88%。结果明确将 EB 指定为最关键的参数，其在研究区域内建筑物损坏发生中的作用占 52% 的重要性。相反，f、Vs 和 A 的显着性值分别确定为 24%、18% 和 6%。这些发现强调了证明可以通过基于地震的局部场地参数使用机器学习方法有效地进行高地震危险区的初始损害估计的重要性。