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2 实例测井数据中各岩性类别对应的样本统计

Table 2 Sample statistics for each lithological category in example logging data

岩性 类别 样本数/个 处理前 ADASYN处理后 总计 2 609 10 540 含角闪黑云英云闪长岩质片麻岩 1 83 1 047 钾化花岗质碎裂岩 2 173 1 038 中粒含黑云二长花岗岩 3 1 045 1 045 绢英岩化花岗质碎裂岩 4 570 1 094 钾化含黑云二长花岗岩 5 27 1 047 绢英岩化花岗岩 6 217 1 038 含黑云二长花岗岩 7 140 1 072 黄铁绢英岩化花岗质碎裂岩 8 149 1 073 黄铁绢英岩化碎裂岩 9 80 1 050 钾化绢英岩化花岗质碎裂岩 10 125 1 036