地球科学进展 ›› 2025, Vol. 40 ›› Issue (11): 1196 -1210. doi: 10.11867/j.issn.1001-8166.2025.084

研究论文 上一篇    

基于PCA-Stacking模型的砂岩型铀矿地层岩性识别方法研究
陈梦诗1,2(), 肖昆1,2(), 李红星1,2, 张华1,2, 杨亚新1,2, 胡旭东1,2, 徐艺宸1,2, 焦常伟1,2, 尹德宁1,2   
  1. 1.东华理工大学 铀资源探采与核遥感全国重点实验室,江西 南昌 330013
    2.东华理工大学 核资源与环境国家重点实验室,江西 南昌 330013
  • 收稿日期:2025-05-27 修回日期:2025-10-27 出版日期:2025-11-10
  • 通讯作者: 肖昆 E-mail:1785944559@qq.com;xiaokun0626@163.com
  • 基金资助:
    江西省自然科学基金项目(20232BAB203072);国家自然科学基金项目(42404150)

Research on Lithology Identification Method for Sandstone-Type Uranium Deposits Based on PCA-Stacking Model

Mengshi CHEN1,2(), Kun XIAO1,2(), Hongxing LI1,2, Hua ZHANG1,2, Yaxin YANG1,2, Xudong HU1,2, Yichen XU1,2, Changwei JIAO1,2, Dening YIN1,2   

  1. 1.National Key Laboratory of Uranium Resources Exploratory-Mining and Nuclear Remote Sensing, East China University of Technology, Nanchang 330013, China
    2.Key Laboratory of Nuclear Resources and Environment, East China University of Technology, Nanchang 330013, China
  • Received:2025-05-27 Revised:2025-10-27 Online:2025-11-10 Published:2025-12-31
  • Contact: Kun XIAO E-mail:1785944559@qq.com;xiaokun0626@163.com
  • About author:CHEN Mengshi, research areas include unconventional oil and gas logging evaluation. E-mail: 1785944559@qq.com
  • Supported by:
    the Jiangxi Provincial Natural Science Foundation(20232BAB203072);The National Natural Science Foundation of China(42404150)

为了提高铀矿钻孔地层岩性识别的准确性,解决传统集成学习模型识别地层岩性效果不佳的问题,提出了一种基于主成分分析优化的Stacking集成学习模型。首先,基于皮尔逊相关系数量化测井参数与目标岩性的线性关联强度,结合测井地球物理机理,筛选出与岩性关系较为密切的6个测井参数作为输入特征。同时,计算基学习器预测误差的皮尔逊相关系数,并使用Q统计量矩阵评估预测结果的相关性,从中筛选出误差互补性强(即低相关性)且预测模式差异显著(即低Q值)的基模型组合。通过主成分分析算法对基模型的预测结果进行加权融合,并将这些融合后的特征作为输入,构建第二层元模型的训练数据,从而实现一个高精度的多层次集成学习模型。实验结果表明,基于主成分分析优化的Stacking模型的识别精度达97.19%,明显优于传统Stacking模型以及所有个体模型的性能,这一结果验证了所提出方法的有效性,为砂岩型铀矿钻孔地层岩性识别研究提供了新的思路和方法。

To improve the accuracy of lithology identification in uranium mine borehole strata and address the limitations of traditional ensemble learning models in achieving satisfactory lithology recognition performance, this study proposes a PCA-optimized Stacking ensemble learning model. The methodology begins by quantitatively evaluating the linear correlation strength between various logging parameters and the target lithology using Pearson correlation coefficients. This statistical analysis is further refined by incorporating geophysical mechanisms of well logging, leading to the selection of six logging parameters that demonstrate strong lithological relevance as input features. These parameters effectively capture essential petrophysical characteristics while minimizing redundancy in the feature set. Simultaneously, the model employs a dual-faceted approach to base learner selection. The Pearson correlation coefficients of prediction errors among base learners are systematically calculated to assess their error interdependence. Additionally, the Q-statistic matrix is utilized to evaluate the correlation and diversity of prediction outcomes. From this, a combination of base models with strong error complementarity (i.e., low correlation) and significant prediction mode differences (i.e., low Q-value) is selected. To optimally consolidate the predictive information, the PCA algorithm is utilized to perform a weighted fusion of the prediction results derived from the diverse base models. The resulting principal components, which represent the most discriminative fused features, then form the refined input feature space for training the second-layer meta-model, thereby achieving a sophisticated and high-accuracy multi-level ensemble learning framework. Experimental results show that the PCA-optimized Stacking model achieves a recognition accuracy of 97.19%, significantly outperforming traditional Stacking models and all individual models. The experimental results indicate that the recognition accuracy of the PCA-optimized Stacking model reaches 97.19%, significantly outperforming both the traditional Stacking model and all individual models. Furthermore, the study provides valuable insights and a novel technical framework for lithology identification in sandstone-type uranium mine borehole strata, contributing to more reliable and efficient geological interpretation in uranium exploration and mining operations.

中图分类号: 

图1 松辽盆地南部地区位置(a)和构造单元区划图(b29
Fig. 1 Location of the Southern Songliao Basinaand zoning map of structuralb29
表1 不同岩性颜色及测井响应特征
Table 1 Lithology colors and logging response characteristics
图2 Stacking基础模型的具体训练方式
Fig. 2 Specific training methods for base models in Stacking
图3 松辽盆地南部地区测井参数与岩性相关性热力图
Fig. 3 Heatmap of the correlation between logging parameters and lithology in southern Songliao Basin
图4 SMOTE算法处理前后的岩性类别样本分布
Fig. 4 Lithology class sample distribution before and after processing with the SMOTE algorithm
图5 基模型相关性分析
(a)皮尔逊相关系数热力图;(b)Q统计量矩阵热力图。
Fig. 5 Correlation analysis of base models
(a) Pearson correlation coefficient heatmap; (b) Q-statistic matrix heatmap.
表2 不同主成分数量下的模型性能对比
Table 2 Model performance comparison with different numbers of principal components
图6 Stacking模型框架
Fig. 6 Stacking model framework
表3 不同组合的Stacking模型岩性识别结果比较
Table 3 Comparison of lithology identification results for different Stacking model combinations
表4 基学习器超参数设置
Table 4 Hyperparameter configuration of the base learner
表5 各机器学习模型的综合性能评估表 (%)
Table 5 Comprehensive performance evaluation table of various machine learning models
图7 不同铀矿地层岩性识别模型的混淆矩阵
横纵坐标数字代表了对应的岩性类型,1:粗砂岩,2:粉砂岩,3:泥岩,4:砂砾岩,5:细砂岩,6:黏土,7:中砂岩;行表示预测岩性类别,每个单元格的数字代表对应类别的样本数量。
Fig. 7 Confusion matrix of different uranium mine strata lithology identification models
The numbers on the vertical and horizontal axes correspond to the following lithology categories: 1: coarse sandstone, 2: siltstone, 3: mudstone, 4: sandy conglomerate, 5: fine sandstone, 6: clay, and 7: medium sandstone. The rows represent the predicted lithology classes, where the numerical value in each cell indicates the sample count for the corresponding category.
表6 松辽盆地两口钻孔预测精度对比结果 (%)
Table 6 Comparison of prediction accuracy for two boreholes in Songliao Basin
图8 钻孔B井岩性识别成果图
Fig. 8 Lithology identification results of borehole B
图9 不同模型的全井段岩性样本比例分布
Fig. 9 Lithology sample proportion distribution for the entire well section of different models
[1] SUN Kui. Logging identification method of complex lithology in buried hill based on the improved KNN algorithm[J]. Special Oil & Gas Reservoirs202229(3): 18-27.
孙岿. 基于改进KNN算法的潜山复杂岩性测井识别方法[J]. 特种油气藏202229(3): 18-27.
[2] GUO Yushan, WANG Wanyin. A method for identifying lithology based on a feature-weighted KNN model[J]. Geophysical and Geochemical Exploration202448(2): 428-436.
郭雨姗, 王万银. 基于特征加权的KNN模型岩性识别方法[J]. 物探与化探202448(2): 428-436.
[3] WANG X D, YANG S C, ZHAO Y F, et al. Lithology identification using an optimized KNN clustering method based on entropy-weighed cosine distance in Mesozoic strata of Gaoqing field, Jiyang depression[J]. Journal of Petroleum Science and Engineering2018166: 157-174.
[4] WU Siyuan, LI Shouding, CHEN Dong,et al. An intelligent-while-drilling steering method of global closed-loop servo control[J]. Chinese Journal of Geophysics202164(11): 4 215-4 226.
吴思源,李守定,陈冬,等. 大闭环伺服控制随钻智能导向钻井方法[J]. 地球物理学报202164(11): 4 215-4 226.
[5] ZHOU Jinyu, GUO Haopeng, ZHANG Shaohua,et al. Study on lithology identification for volcanic rock logging data in Songliao Basin[J]. Journal of Oil and Gas Technology201436(3):72-76.
周金昱,郭浩鹏,张少华,等. 松辽盆地火山岩岩性测井识别方法研究[J]. 石油天然气学报201436(3):72-76.
[6] XU Han, YAO Kongxuan, CHENG Danyi,et al. Stratigraphic lithology identification based on no-dig logging while drilling system and random forest[J]. Bulletin of Geological Science and Technology202140(5): 272-280.
徐晗,姚孔轩,程丹仪,等. 基于非开挖随钻检测系统与随机森林的地层岩性识别[J]. 地质科技通报202140(5): 272-280.
[7] LIU Kai, ZOU Zhengyin, WANG Zhizhang, et al. Intelligent identification and prediction of lithology of volcanic reservoirs based on machine learning[J]. Special Oil & Gas Reservoirs202229(1): 38-45.
刘凯, 邹正银, 王志章, 等. 基于机器学习的火山岩岩性智能识别及预测[J]. 特种油气藏202229(1): 38-45.
[8] BRESSAN T S, de KEHL S M, GIRELLI T J, et al. Evaluation of machine learning methods for lithology classification using geophysical data[J]. Computers & Geosciences2020, 139. DOI: 10.1016/j.cageo.2020.104475 .
[9] HUANG Yu, SHAO Yanlin, WEI Wei,et al. Study on the decision tree model for carbonate rock lithology identification based on hyperspectral data[J]. Laser & Optoelectronics Progress202562(8): 416-424.
黄宇,邵燕林,魏薇,等. 基于高光谱数据的碳酸盐岩岩性识别决策树模型研究[J]. 激光与光电子学进展202562(8): 416-424.
[10] XIE Y X, ZHU C Y, HU R S, et al. A coarse-to-fine approach for intelligent logging lithology identification with extremely randomized trees[J]. Mathematical Geosciences202153(5): 859-876.
[11] DUAN Zhongyi, XIAO Kun, YANG Yaxin, et al. Automatic lithology identification of sandstone-type uranium deposit in Songliao Basin based on ensemble learning[J]. Atomic Energy Science and Technology202357(12): 2 443-2 454.
段忠义, 肖昆, 杨亚新, 等. 基于集成学习的松辽盆地砂岩型铀矿地层岩性自动识别研究[J]. 原子能科学技术202357(12): 2 443-2 454.
[12] ZHAO Ranlei, YANG Liushuan, XU Xiao, et al. Lithology identification method and research of volcanic rock based on XGBoost algorithm[J]. Progress in Geophysics202540(2): 646-657.
赵然磊, 杨留栓, 徐晓, 等. 基于XGBoost算法的火山岩岩性识别方法与研究[J]. 地球物理学进展202540(2): 646-657.
[13] PAN Shaowei, WANG Chaoyang, ZHANG Yun,et al. Lithology identification based on LSTM neural networks completing log and hybrid optimized XGBoost[J]. Journal of China University of Petroleum (Edition of Natural Science)202246(3): 62-71.
潘少伟,王朝阳,张允,等. 基于长短期记忆神经网络补全测井曲线和混合优化XGBoost的岩性识别[J]. 中国石油大学学报(自然科学版)202246(3): 62-71.
[14] FENG Huan, ZHANG Guoqiang, CAO Jun, et al. Application of WOA optimized LightGBM in lithology identification of igneous logging[J]. Progress in Geophysics202540(1): 230-242.
冯欢, 张国强, 曹军, 等. WOA优化LightGBM在火成岩测井岩性识别中的应用[J]. 地球物理学进展202540(1): 230-242.
[15] GU Yufeng, ZHANG Daoyong, BAO Zhidong, et al. Lithology prediction of tight sandstone formation using GS-LightGBM hybrid machine learning model[J]. Bulletin of Geological Science and Technology202140(4): 224-234.
谷宇峰, 张道勇, 鲍志东, 等. 利用GS-LightGBM机器学习模型识别致密砂岩地层岩性[J]. 地质科技通报202140(4): 224-234.
[16] LI Qing, LONG Xunrong, WU Xiuhui, et al. One method to predict porosity in tight sandstone reservoirs based on SAO-LightBGM algorithm[J]. Natural Gas Technology and Economy202418(4): 9-14, 86.
李庆, 龙训荣, 吴秀慧, 等. 基于SAO-LightGBM算法的致密砂岩储层孔隙度预测方法[J]. 天然气技术与经济202418(4): 9-14, 86.
[17] GU J Y, LIU S G, ZHOU Z Z, et al. A Stacking ensemble learning model for monthly rainfall prediction in the Taihu Basin, China[J]. Water202214(3). DOI: 10.3390/w14030492 .
[18] ZHAN Y, ZHANG H J, LI J H, et al. Prediction method for ocean wave height based on Stacking ensemble learning model[J]. Journal of Marine Science and Engineering202210(8). DOI: 10.3390/jmse10081150 .
[19] HOU S K, LIU Y R, YANG Q. Real-time prediction of rock mass classification based on TBM operation big data and Stacking technique of ensemble learning[J]. Journal of Rock Mechanics and Geotechnical Engineering202214(1): 123-143.
[20] DING W Z, LI X H, YANG H, et al. A novel method for damage prediction of stuffed protective structure under hypervelocity impact by Stacking multiple models[J]. IEEE Access20208: 130 136-130 158.
[21] DING Ziwei, GAO Chengdeng, ZHANG Ling, et al. Prediction method for data-driven lithology identification of TBM tunneling strata[J]. Journal of Mining and Safety Engineering202542(1): 147-160.
丁自伟, 高成登, 张玲, 等. 基于数据驱动的TBM掘进地层岩性识别预测方法[J]. 采矿与安全工程学报202542(1): 147-160.
[22] CAO Maojun, GONG Weijia, GAO Zhiyong. Research on lithology identification based on Stacking integrated learning[J]. Computer Technology and Development202232(7): 161-166, 172.
曹茂俊, 巩维嘉, 高志勇. 基于Stacking集成学习的岩性识别研究[J]. 计算机技术与发展202232(7): 161-166, 172.
[23] ZOU Qi, HE Yueshun, YANG Xi, et al. Construction of lithology identification model by well logging based on ensemble learning[J]. Intelligent Computer and Applications202010(3): 91-94.
邹琪, 何月顺, 杨希, 等. 基于集成学习的测井岩性识别模型的构建[J]. 智能计算机与应用202010(3): 91-94.
[24] LIN X C, YIN S T. Lithology identification based on interpretability integration learning[J]. Earth Science Informatics202316(3): 2 211-2 222.
[25] ZHANG Chi, PAN Mao, HU Shuiqing, et al. A machine learning lithologic identification method combined with vertical reservoir information[J]. Bulletin of Geological Science and Technology202342(3): 289-299.
张驰, 潘懋, 胡水清, 等. 融合储层纵向信息的机器学习岩性识别方法[J]. 地质科技通报202342(3): 289-299.
[26] HUO Fengcai, LI Qingzhi, DONG Hongli, et al. Prediction method of reservoir evaluation parameters based on improved Stacking fusion model[J]. Progress in Geophysics202540(2): 691-704.
霍凤财, 李青志, 董宏丽, 等. 基于改进Stacking融合模型的储层参数预测方法[J]. 地球物理学进展202540(2): 691-704.
[27] LUO Shuiliang, QI Yingqiang, TANG Song, et al. Lithology logging identification method and application to carbonate reservoirs based on improved Stacking algorithm[J]. Special Oil & Gas Reservoirs202532(4): 58-67.
罗水亮, 漆影强, 唐松, 等. 基于改进Stacking算法的碳酸盐岩储层测井岩性识别方法与应用[J]. 特种油气藏202532(4): 58-67.
[28] ZHAO J, LIN Z P, LAI Q, et al. A fluid identification method for caved-fracture reservoirs based on the Stacking model[J]. Frontiers in Earth Science2023, 11. DOI: 10.3389/feart.2023.1216222 .
[29] LIU Xin, WANG Changdong, CAI Jianfang, et al. Characteristics of stratigraphic sequences and their controlling effect on uranium mineralization in southern Songliao Basin [J]. Uranium Geology202541(5): 757-772.
刘鑫, 王常东, 蔡建芳, 等. 松辽盆地南部层序地层特征及其对铀成矿的制约作用分析[J]. 铀矿地质202541(5): 757-772.
[30] ZHANG Hongjing, YU Haoyi, ZHANG Lingling, et al. Discussion on metallogenic conditions of sandstone-type uranium deposits in Upper Cretaceous Yaojia Formation in Changling area, central depression, Songliao Basin[J]. Uranium Geology202440(5): 850-863.
张红静, 于浩依, 张玲玲, 等. 松辽盆地中央坳陷区长岭地区上白垩统姚家组砂岩型铀矿成矿条件分析[J]. 铀矿地质202440(5): 850-863.
[31] YAN Zhanglei, GUO Qiang, XIAO Jing. Geochemical characteristics and provenance analysis of clastic rocks for sandstone-type uranium deposit in Yuliangbao area, southern Songliao Basin[J]. Uranium Geology202440(5): 864-880.
严张磊, 郭强, 肖菁. 松辽盆地南部余粮堡地区砂岩型铀矿含矿层碎屑岩地球化学特征及物源分析[J]. 铀矿地质202440(5): 864-880.
[32] LIU Yuhu, CAO Chunhui, LI Ruilei, et al. The control of the spatial and temporal differential evolution of boundary faults on faulted basins: taking the fulongquan fault depression in the southern Songliao Basin as an example[J]. Advances in Earth Science202035(1): 79-87.
刘玉虎, 曹春辉, 李瑞磊, 等. 边界断裂时空差异演化对断陷盆地的控制作用: 以松辽盆地南部伏龙泉断陷为例[J]. 地球科学进展202035(1): 79-87.
[33] ZHANG Hang, NIE Fengjun, LUO Min, et al. Discussion on metallogenic conditions and prospecting direction of sandstone-type uranium deposits in Yaojia Formation, Baiquan area, northeast Songliao Basin[J]. Uranium Geology202238(3): 425-435.
张航, 聂逢君, 罗敏, 等. 松辽盆地东北部拜泉地区姚家组砂岩型铀成矿条件与找矿方向探讨[J]. 铀矿地质202238(3): 425-435.
[34] SHANG Gaofeng, QIAO Haiming, SONG Zhe,et al. Geochemical characteristics of sandstone type uranium depositsin interlayer oxidation zone,Baxiankou area[J]. Advances in Earth Science201227():245-250.
尚高峰,乔海明,宋哲,等. 八仙口砂岩型铀矿层间氧化带的地球化学特征[J]. 地球科学进展201227():245-250.
[35] ZHAO Xingqi, CUI Shoukai, CAI Ya, et al. Metallogenic conditions and prospecting targeting of sandstone-type uranium mineralization in Mahai area, northern Qaidam Basin[J]. Acta Geoscientia Sinica202142(5): 593-604.
赵兴齐, 崔守凯, 蔡亚, 等. 柴达木盆地北缘马海地区砂岩型铀成矿条件及找矿方向[J]. 地球学报202142(5): 593-604.
[36] PENG Hu, JIAO Yangquan, RONG Hui, et al. Spatial-temporal coupling of key ore-controlling factors for sandstone-type uranium deposits in Tiefa area, Songliao Basin[J]. Earth Science202449(9): 3 182-3 198.
彭虎, 焦养泉, 荣辉, 等. 松辽盆地铁法地区砂岩型铀矿关键控矿因素的时空耦合[J]. 地球科学202449(9): 3 182-3 198.
[37] ZHAO Zhonghua, ZHANG Zhenqiang, YU Wenbin, et al. The major controlling factors and prospecting guide of sandstone-type uranium mineralization in southern Songliao Basin[J]. World Nuclear Geoscience201229(4): 199-202, 226.
赵忠华, 张振强, 于文斌, 等. 松辽盆地南部砂岩型铀矿成矿主控因素及找矿方向[J]. 世界核地质科学201229(4): 199-202, 226.
[38] WOLPERT D H. Stacked generalization[J]. Neural Networks19925(2): 241-259.
[39] SONG Yanjie, LIU Yingjie, TANG Xiaomin, et al. Evaluation method of total organic carbon content in shale based on Stacking algorithm ensemble learning[J]. Well Logging Technology202448(2): 163-178.
宋延杰, 刘英杰, 唐晓敏, 等. 基于Stacking算法集成学习的页岩油储层总有机碳含量评价方法[J]. 测井技术202448(2): 163-178.
[40] WANG Zhihan, WEN Tao. Prediction of rock brittleness index using two-layer Stacking model optimized by tree-structured Parzen estimator[J]. China Petroleum Exploration202530(2): 115-132.
王芷含, 温韬. 基于树结构Parzen估计器优化后两层Stacking模型的岩石脆性指数预测[J]. 中国石油勘探202530(2): 115-132.
[41] MA Liangyu, GENG Yanzhu, LIANG Shuyuan,et al. Anomaly warning of wind turbine gearbox oil pool temperature based on Stacking fusion of multiple models[J]. Proceedings of the CSEE202343(): 242-251.
马良玉,耿妍竹,梁书源,等. 基于Stacking多模型融合的风电机组齿轮箱油池温度异常预警[J]. 中国电机工程学报202343():242-251.
[42] ZHENG Yingying, LI Xin, CHEN Yanxu, et al. Short-term wind power forecasting method in extreme weather based on Stacking multi-model fusion[J]. High Voltage Engineering202450(9): 3 871-3 882.
郑颖颖, 李鑫, 陈延旭, 等. 基于Stacking多模型融合的极端天气短期风电功率预测方法[J]. 高电压技术202450(9): 3 871-3 882.
[43] SHI Jiaqi, ZHANG Jianhua. Load forecasting based on multi-model by Stacking ensemble learning[J]. Proceedings of the CSEE201939(14): 4 032-4 042.
史佳琪, 张建华. 基于多模型融合Stacking集成学习方式的负荷预测方法[J]. 中国电机工程学报201939(14): 4 032-4 042.
[44] WU Zhongqiang, MA Boyan. Real-time energy distribute strategy of PHEV hybrid energy storage system based on Stacking fusion model[J]. Acta Metrologica Sinica202445(1): 73-81.
吴忠强, 马博岩. 基于Stacking融合模型的PHEV复合储能系统实时能量分配策略[J]. 计量学报202445(1): 73-81.
[45] SHI Pengyu, XU Sihui, FENG Jiaming, et al. Log identification of fluid types in tight sandstone reservoirs using an improved Stacking algorithm[J]. Progress in Geophysics202439(1): 280-290.
史鹏宇, 徐思慧, 冯加明, 等. 基于改进Stacking算法的致密砂岩储层测井流体识别[J]. 地球物理学进展202439(1): 280-290.
[46] GUO Zhiqiang, ZHANG Botao, ZENG Yunliu. Study on sugar content detection of kiwifruit using near-infrared spectroscopy combined with Stacking ensemble learning[J]. Spectroscopy and Spectral Analysis202444(10): 2 932-2 940.
郭志强, 张博涛, 曾云流. 近红外光谱结合Stacking集成学习的猕猴桃糖度检测研究[J]. 光谱学与光谱分析202444(10): 2 932-2 940.
[47] LIANG Haibo, MA Rui. Porosity prediction method based on Stacking ensemble learning[J]. Journal of Electronic Measurement and Instrumentation202438(12): 202-210.
梁海波, 马睿. 基于Stacking集成学习的孔隙度预测方法[J]. 电子测量与仪器学报202438(12): 202-210.
[48] SADHASIVAM S K, KEERTHIVASAN M B, MUTTAN S. Implementation of max principle with PCA in image fusion for surveillance and navigation application[J]. ELCVIA Electronic Letters on Computer Vision and Image Analysis201110(1): 1-10.
[49] XU J J, ZHU M T, TANG P J, et al. Visualization enhancement by PCA-based image fusion for skin burns assessment in polarization-sensitive OCT[J]. Biomedical Optics Express202415(7): 4 190-4 205.
[50] DUAN Z J, LI H Q, LI C G, et al. A CNN model for early detection of pepper Phytophthora blight using multispectral imaging, integrating spectral and textural information[J]. Plant Methods202420(1). DOI: 10.1186/s13007-024-01239-7 .
[51] SHOJAEIAN A, SHAFIZADEH-MOGHADAM H, SHARAFATI A, et al. Extreme flash flood susceptibility mapping using a novel PCA-based model Stacking approach[J]. Advances in Space Research202474(11): 5 371-5 382.
[52] ABDI H, WILLIAMS L J. Principal component analysis[J]. WIREs Computational Statistics20102(4): 433-459.
[53] LI Chiyun, MIAO Jianming, SHEN Bingzhen. Operational effectiveness prediction of weapon equipment system based on improved Stacking ensemble learning method[J]. Acta Armamentarii202344(11): 3 455-3 464.
李驰运, 缪建明, 沈丙振. 基于改进Stacking集成学习方法的武器装备体系作战效能预测[J]. 兵工学报202344(11): 3 455-3 464.
[54] CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE: synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research200216: 321-357.
[55] HE Y L, LU X, FOURNIER-VIGER P, et al. A novel overlapping minimization SMOTE algorithm for imbalanced classification[J]. Frontiers of Information Technology & Electronic Engineering202425(9): 1 266-1 281.
[1] 陈亮, 段建平, 马柱国. 大气环流形势客观分型及其与中国降水的联系[J]. 地球科学进展, 2018, 33(4): 396-403.
[2] 王新娥, 许东晖, 孙之夫, 孙宗峰, 罗景美. 山东黄金资源钻探井测井资料分析方法与应用[J]. 地球科学进展, 2014, 29(3): 397-403.
[3] 李本纲,陶 澍,林健枝,程寿全. 地理信息系统与主成分分析在多年气象观测数据处理中的应用[J]. 地球科学进展, 2000, 15(5): 509-515.
[4] 崔茂常,练树民,纪立人. 中国周降雨量与相关海域周平均海面水温[J]. 地球科学进展, 2000, 15(1): 34-39.
[5] 潘汉军. 因子克立格分析的理论综述及应用展望[J]. 地球科学进展, 1992, 7(1): 50-.
阅读次数
全文


摘要