基于集成学习的风沙跃移轨迹自动识别模型

周虹吉, 梅凡民, 蒲梦洁, 林川, 苏进, 陈金广

Ensemble models for identifying automatically aeolian saltating tracks driven by datasets

Hongji Zhou, Fanmin Mei, Mengji Pu, Chuan Lin, Jin Su, Jinguang Chen

表2 通过Tree-structured Parzen Estimator优化后的各个模型的最终超参数设置

Table 2 Final hyperparameter settings for each model optimized by Tree-structured Parzen Estimator

算法 HP1 HP2 HP3 HP4 HP5 HP6 HP7 HP8 HP9 HP10 随机森林 True -1 True 180 18 True “sqrt” “gini” 梯度提升决策树 True -1 True 210 3 0.3 XGBoost True -1 70 6 0.3 0.5 极度随机树 True -1 True 186 21 0.1 True None “entropy”