基于非均衡数据的ADASYN-CatBoost测井岩性智能识别——以胶西北招贤金矿床为例

许方颖,邹艳红,易卓炜,杨福强,毛先成

ADASYN-CatBoost Method for Intelligent Identification of Logging Lithology Considering Unbalanced Data：A Case Study of Zhaoxian Gold Deposit in Northwestern Jiaodong Peninsula

Fangying XU,Yanhong ZOU,Zhuowei YI,Fuqiang YANG,Xiancheng MAO

表4 测试集上岩性识别精确率、召回率和F1分数（加权平均）

Table 4 Precision，recall rate and F1 score （weighted average） of lithology identification on the test set

分类器 精确率 召回率 F1分数 GBDT 0.9355 0.9349 0.9327 LightGBM 0.9561 0.9554 0.9552 CatBoost 0.9503 0.9600 0.9600 ADASYN-GBDT 0.9472 0.9469 0.9466 ADASYN-LightGBM 0.9695 0.9695 0.9695 ADASYN-CatBoost 0.9821 0.9820 0.9820