中国含铝岩系中稀土元素的赋存形式: 主量元素数据驱动的集成机器学习分析<sup>&#x0002A;</sup>

doi:10.7605/gdlxb.2025.045

古地理学报 ›› 2025, Vol. 27 ›› Issue (2): 307-320. doi: 10.7605/gdlxb.2025.045

中国含铝岩系中稀土元素的赋存形式: 主量元素数据驱动的集成机器学习分析^*

周锦涛¹^,²(), 余文超¹^,²(), 杜远生¹^,², 邓旭升²^,³, 翁申富²^,⁴, 雷志远²^,⁵

1 中国地质大学(武汉)地球科学学院,湖北武汉,430074
2 自然资源部基岩区矿产资源勘查工程技术创新中心,贵州贵阳 550081
3 贵州省地质调查院,贵州贵阳 550081
4 贵州省地质矿产勘查开发局106地质大队,贵州遵义 563003
5 贵州省地质矿产勘查开发局,贵州贵阳 520300

收稿日期:2024-08-24 修回日期:2024-11-19 出版日期:2025-04-01 发布日期:2025-04-01
作者简介:
周锦涛,男,1998年生,博士研究生,主要从事铝土矿沉积地质学研究。E-mail: jtzhou@cug.edu.cn。
基金资助:
*国家重点研发计划项目“植物登陆的环境资源效应”(编号:2022YFF0800200)和湖北省创新群体项目“地球生物学大数据与计算模拟”(编号:2023AFA006)联合资助

Occurrence forms of rare earth elements in aluminum-bearing rock series in China: ensemble machine learning analysis driven by major element data

ZHOU Jintao¹^,²(), YU Wenchao¹^,²(), DU Yuansheng¹^,², DENG Xusheng²^,³, WENG Shenfu²^,⁴, LEI Zhiyuan²^,⁵

1 School of Earth Sciences,China University of Geosciences(Wuhan),Wuhan 430074,China
2 Innovation Center of Ore Resources Exploration Technology in the Region of Bedrock,Ministry of Natural Resources of People’s Republic of China,Guiyang 550081,China
3 Guizhou Geological Survey,Guiyang 550081,China
4 Geological Brigade 106,Bureau of Geology and Mineral Exploration and Development of Guizhou Province, Guizhou Zunyi 563003,China
5 Bureau of Geology and Mineral Exploration and Development of Guizhou Province,Guiyang 520300,China

Received:2024-08-24 Revised:2024-11-19 Online:2025-04-01 Published:2025-04-01
About author:
ZHOU Jintao,born in 1998,is a Ph.D. candidate in the School of Earth Sciences at China University of Geosciences(Wuhan). His primary research focus is on sedimentary geology of bauxite. E-mail: jtzhou@cug.edu.cn.
Supported by:
Co-funded by the National Key R & D Program of China(No. 2022YFF0800200)and the Innovation Group of Hubei(No. 2023AFA006)

摘要/Abstract

摘要：

铝土矿及含铝岩系中的稀土元素是重要的潜在供应源,随着技术进步和市场需求增长,其勘探、开发和利用变得日益重要。目前,对含铝岩系中稀土元素的主要赋存形式和富集机制仍有争议,尤其是重稀土(HREE)。本研究汇编了中国含铝岩系的地球化学数据,利用机器学习方法预测轻稀土(LREE)和重稀土(HREE)含量,探讨其赋存形式。研究构建了随机森林(RF)、极限梯度提升(XGBoost)、支持向量机(SVM)和多层感知器(MLP)4种模型,并结合最优的2种模型构建集成模型,以提高预测性能。结果表明,集成模型在预测HREE和LREE含量方面表现更佳,能较好预测剖面尺度的稀土变化规律,并对高稀土含量剖面更敏感。特征重要性评估显示,P₂O₅和TFe₂O₃是预测HREE含量的关键变量,表明铁相矿物和磷酸盐矿物是HREE的主要载体。HREE可能通过类质同象替代和内环络合形式在磷酸盐矿物和铁相矿物中富集。含铝岩系中铁相矿物的存在是赋存HREE的基础,而磷酸盐矿物则是富集HREE的关键。对于LREE,P₂O₅的重要性显示含磷矿物是其重要赋存载体,即含磷稀土矿物为代表的独立稀土矿物是中国含铝岩系LREE的重要赋存形式。黏土矿物和铝矿物的离子吸附形式作为一种背景现象同样存在,但对稀土异常富集影响较小。研究建议,在找矿勘查中,针对LREE应关注P₂O₅含量较高的层位,含铝岩系的岩性应关注贫铁铝土矿和黏土质铝土矿。对于HREE,应首先关注TFe₂O₃含量较高的层位,若同时有较高的P₂O₅含量,则HREE富集可能性更大,建议关注的岩性包括富铁铝土矿和铝土质黏土岩。本研究建立的稀土含量预测模型在中国含铝岩系伴生稀土预测方面展现出潜力,需进一步验证、优化与应用。

关键词: 集成模型, 铁相矿物, 磷酸盐矿物, 稀土矿物

Abstract:

Bauxite and associated aluminum-bearing rock series,which host rare earth elements(REE),are considered significant potential sources of REE. With the advancement of new technologies and the increasing global market demand,the exploration,development,and utilization of REE associated with aluminum-bearing rock series have become increasingly critical. However,the dominant occurrence forms of REE in these rock series remain controversial. Moreover,most studies have primarily focused on Light Rare Earth Elements(LREE),while the occurrence forms and enrichment mechanisms of Heavy Rare Earth Elements(HREE)remain poorly understood. To address these issues,this study compiled geochemical data from Chinese aluminum-bearing rock series and attempted to utilize machine learning methods based on major elemental compositions to predict LREE and HREE contents,as well as to explore the occurrence forms of REE in these rock series. Four models were constructed for this purpose: Random Forest(RF),Extreme Gradient Boosting(XGBoost),Support Vector Machine(SVM),and Multi-Layer Perceptron(MLP). Additionally,two ensemble models were developed by combining the two best-performing models among the four. The results demonstrated that the ensemble models exhibited superior predictive performance for both HREE and LREE contents. The two ensemble models successfully predicted the variation of REE at the profile scale and delineated the REE enrichment horizons. These models demonstrated enhanced sensitivity to profiles with higher overall REE content,leading to improved predictive performance. Feature importance analysis revealed that P₂O₅ and TFe₂O₃ are critical variables for predicting HREE content,indicating that iron-bearing and phosphate minerals are primary carriers of HREE. The enrichment of HREE in phosphate minerals likely occurs via a substitution mechanism,while iron-bearing minerals enrich HREE through inner-sphere complexation. The presence of iron-bearing minerals in aluminum-bearing rock series is fundamental to HREE occurrence,and their absence may result in lower HREE content. Phosphate minerals play a crucial role in HREE enrichment,complementing iron-bearing minerals to facilitate high HREE content in aluminum-bearing rock series. The high importance of P₂O₅ in predicting LREE content suggests that phosphorus-bearing minerals are significant carriers of LREE. Independent REE minerals,particularly phosphorus-bearing REE minerals,represent an important form of LREE occurrence in Chinese aluminum-bearing rock series. While clay and aluminum minerals contribute to ion adsorption as a background phenomenon,they have minimal impact on abnormal REE enrichment. This study recommends focusing on strata with higher P₂O₅ content for potential LREE enrichment in practical mineral exploration. For aluminum-bearing rock series,attention should be given to low-iron bauxite and clayey bauxite. For HREE,strata with higher TFe₂O₃ content should be prioritized,especially when accompanied by elevated P₂O₅ levels. Lithologies suggested for attention include iron-rich bauxite and bauxitic claystone. In addition,the prediction model developed in this study shows potential in predicting REE associated with aluminum-bearing rock series in China,and is in urgent need of further optimization for validation and application.

Key words: ensemble model, iron-bearing mineral, phosphate mineral, REE mineral

周锦涛, 余文超, 杜远生, 邓旭升, 翁申富, 雷志远. 中国含铝岩系中稀土元素的赋存形式: 主量元素数据驱动的集成机器学习分析^*[J]. 古地理学报, 2025, 27(2): 307-320.

ZHOU Jintao, YU Wenchao, DU Yuansheng, DENG Xusheng, WENG Shenfu, LEI Zhiyuan. Occurrence forms of rare earth elements in aluminum-bearing rock series in China: ensemble machine learning analysis driven by major element data[J]. Journal of Palaeogeography（Chinese Edition）, 2025, 27(2): 307-320.

http://www.gdlxb.cn/CN/Y2025/V27/I2/307

图/表 11

图1 中国含铝岩系地球化学数据来源分布

Fig.1 Distribution map of geochemical data sources for aluminum-bearing rock series in China

表1 中国含铝岩系地球化学数据来源汇编

Table1 Compilation of source data for geochemical data of aluminum-bearing rock series in China

时代	地区	组名	岩性	数据量	参考文献
早石炭世	黔中	九架炉组	贫铁铝土矿和黏土质铝土矿为主	148	Ling et al., 2018;Weng et al., 2019;Long et al., 2020;吴林等,2021;Pang et al., 2023;Luo et al., 2023
晚石炭世	豫西晋中晋西北	本溪组	贫铁铝土矿和黏土质铝土矿为主	175	Liu et al., 2013,2020;Yang et al., 2019a,2019b;Zhu et al., 2019;Zhang et al., 2021;Zhao et al., 2023;Wang et al., 2024
早二叠世	黔北滇中	大竹园组倒石头组	黏土质铝土矿和铝土质黏土岩为主	25	Li et al., 2020;Zhang et al., 2022a;邓旭升等,2023
晚二叠世	黔北滇东南黔西桂西	龙潭组宣威组合山组	黏土质铝土矿、铝土质黏土岩和贫铁铝土矿为主	126	Wang et al., 2010;焦扬等,2014;侯莹玲等,2014;张启明等,2015;Yu et al., 2016;Hou et al., 2017;Liu et al., 2017b;Zhou et al., 2022
更新世	桂中桂西	/	铝土矿、富铁铝土矿和黏土质铝土矿为主	116	Wang et al., 2010;Liu et al., 2010,2017a;Chen et al., 2018

图2 中国含铝岩系岩性判别三端元图(依据Bárdossy,1982的分类方案)

Fig.2 Ternary diagram for lithological discrimination of aluminum-bearing rock series in China(according to Bárdossy(1982)’s classification scheme)

图3 9个特征变量的VIF值

Fig.3 VIF values of nine features

表2 4种机器学习算法的最优超参数组合

Table2 Optimal hyperparameter combinations for four machine learning algorithms

算法	超参数	预测HREE 的最优值	预测LREE 的最优值
RF	n_estimators max_depth max_features min_samples_leaf min_samples_split bootstrap	28 10 ‘log2’ 7 2 True	70 11 ‘sqrt’ 14 2 False
XGBoost	n_estimators learning_rate max_depth min_child_weight subsample colsample_bytree reg_alpha	25 0.1 17 7 0.4 0.75 0.2	20 0.1 14 9 0.5 0.7 0.2
SVM	C gamma epsilon kernel	25 0.3 0.35 ‘rbf’	120 0.78 0.85 ‘rbf’
MLP	hidden_layer_sizes learning_rate_init activation alpha max_iter	(55,47) 0.015 ‘tanh’ 0.04 99	(41,60) 0.06 ‘relu’ 0.025 100

表3 模型预测性能的各项评估指标

Table3 Assessment metrics of model prediction performance

目标变量	算法	R²	MAE/μg·g^-1	RMSE/μg·g^-1
HREE	RF	0.414	23.052	34.934
	XGBoost	0.469	21.473	33.267
	SVM	0.235	24.852	39.942
	MLP	0.287	26.230	38.552
	RF+XGBoost	0.506	21.799	32.073
LREE	RF	0.411	203.995	309.802
	XGBoost	0.441	196.087	301.705
	SVM	0.283	209.451	341.668
	MLP	0.463	206.432	295.633
	XGBoost+MLP	0.502	191.222	284.865

图4 不同模型的重、轻稀土预测值与实际测试值散点图
A—RF、XGBoost和集成模型的重稀土预测值与实际测试值散点图; B—XGBoost、MLP和集成模型的轻稀土预测值和测试值散点图

Fig.4 Scatter diagrams of predicted versus actual test values for HREE and LREE across different models

图5 集成模型在剖面尺度的预测值和实际测试值对比
A—黔北遵义钻孔ZK13-1样品的轻、重稀土预测值与实测值对比结果(实测数据来自Zhou et al., 2022);B—黔中修文钻孔ZK47-12样品的轻、重稀土预测值与实测值对比结果(实测数据来自Pang et al., 2023);C—黔北遵义钻孔ZK5600样品的轻、重稀土预测值与实测值对比结果(实测数据来自Weng et al., 2019);D—黔西威宁钻孔GDZK1的轻、重稀土预测值与实测值对比结果(数据由余文超提供)

Fig.5 Comparisons of predictive values and actual test values at profile scale for ensemble models

图6 不同模型的置换特征重要性评估结果和SHAP总览图
A—预测HREE的RF模型的置换特征重要性评估结果与SHAP总览图; B—预测HREE的XGBoost模型的置换特征重要性评估结果与SHAP总览图; C—预测HREE的集成模型的置换特征重要性评估结果与SHAP总览图; D—预测LREE的XGBoost模型的置换特征重要性评估结果与SHAP总览图; E—预测LREE的MLP模型的置换特征重要性评估结果与SHAP总览图; F—预测LREE的集成模型的置换特征重要性评估结果与SHAP总览图

Fig.6 Permutation feature importance assessment results and SHAP summary diagrams for different models

图7 中国含铝岩系不同HREE和LREE含量对应的主量元素含量的箱线图(稀土含量分为低值、中值和高值3种类型)
A—不同HREE含量对应的主量元素含量的箱线图; B—不同LREE含量对应的主量元素含量的箱线图

Fig.7 Box plots of major element contents corresponding to different HREE and LREE contents in aluminum-bearing rock series in China(REE content is divided into three types: low value,medium value,and high value)

图8 中国含铝岩系中不同岩性对应的稀土元素含量箱线图及不同岩性稀土元素高含量占比饼图(稀土元素高含量比例统计以LREE含量大于800 μg/g、HREE含量大于100 μg/g为标准)
A—含铝岩系不同岩性对应的LREE含量箱线图及高含量LREE占比饼图; B—含铝岩系不同岩性对应的HREE含量箱线图及高含量HREE占比饼图

Fig.8 Box plots of REE content and pie charts of the proportion of high REE content in different rock types in aluminum-bearing rock series in China(The standard for high REE content is LREE content greater than 800 μg/g and HREE content greater than 100 μg/g)

参考文献 70

[1]	邓旭升,余文超,杜远生,杜威,熊兴国,曾禹人,龙建喜,张晗彬,符宏斌,何犇,卢树藩,罗香建. 2023. 贵州狮溪铝土岩型锂资源的发现及意义. 地质论评,69(1): 133-147.
	[Deng X S,Yu W C,Du Y S,Du W,Xiong X G,Zeng Y R,Long J X,Zhang H B,Fu H B,He B,Lu S F,Luo X J. 2023. Discovery and significance of Shixi bauxitite-type lithium deposit in Guizhou Province. Geological Review,69(1): 133-147]
[2]	侯莹玲,何斌,钟玉婷. 2014. 桂西二叠系喀斯特型铝土矿成矿物质来源的新认识: 来自合山组碎屑岩地球化学证据. 大地构造与成矿学,38(1): 181-196.
	[Hou Y L,He B,Zhong Y T. 2014. New perspective on provenance of the Permian karstic bauxite in the western Guangxi: geochemical evidence of clastic rocks of the Heshan formation. Geotectonica et Metallogenia,38(1): 181-196]
[3]	焦扬,王训练,崔银亮,姜永果,周洪瑞,高金汉,王根厚. 2014. 云南文山县天生桥铝土矿地球化学特征与物源分析. 现代地质,28(4): 731-742.
	[Jiao Y,Wang X L,Cui Y L,Jiang Y G,Zhou H R,Gao J H,Wang G H. 2014. Geochemical characteristics and provenance analysis of the Tianshengqiao bauxite in Wenshan County,Yunnan Province. Geoscience,28(4): 731-742]
[4]	刘东义,韩鎏,郑骥飞,胡小辉. 2020. 淄博盆地A层硬质黏土—铝土矿矿床地质特征及分布规律. 山东国土资源,36(10): 22-27.
	[Liu D Y,Han L,Zheng J F,Hu X H. 2020. Geological characteristics and distribution regularity of a layer hard clay: bauxite deposit in Zibo City. Shandong Land and Resources,36(10): 22-27]
[5]	罗香建,覃英,卢树藩,符宏斌,刘国栋,陈武. 2023. 赫章辅处地区沉积型富稀土岩系地球化学特征及物源分析. 矿物学报,43(6): 758-770.
	[Luo X J,Qin Y,Lu S F,Fu H B,Liu G D,Chen W. 2023. Geochemical characteristics and provenance analysis of the sedimentary type REE-rich rock series in the Fuchu area,Hezhang County,Guizhou,China. Acta Mineralogica Sinica,43(6): 758-770]
[6]	唐波,付勇,龙克树,龙珍,王天顺,刘阳,杨颖. 2021. 中国铝土矿含铝岩系伴生稀土资源分布特征及富集机制. 地质学报,95(8): 2284-2305.
	[Tang B,Fu Y,Long K S,Long Z,Wang T S,Liu Y,Yang Y. 2021. Distribution characteristics and enrichment mechanism of associated rare earth elements resource in aluminum-bearing rock series in bauxite deposits of China. Acta Geologica Sinica,95(8): 2284-2305]
[7]	王翠芝,肖荣阁,贾琇明,周红春,刘军. 2005. 山东淄博铝土矿地质特征及成矿作用. 地质与勘探,41(5): 34-37.
	[Wang C Z,Xiao R G,Jia X M,Zhou H C,Liu J. 2005. Geological features and mineralization of Zibo bauxite deposits in Shandong Province. Geology and Prospecting,41(5): 34-37]
[8]	温静静,梁涛,卢仁,王莉. 2016. 河南省嵩箕地区铝土矿 Li、Ti、Zr、Ga、Nb和 LREE 的矿化分析. 矿产与地质,30(2): 216-222.
	[Wen J J,Liang T,Lu R,Wang L. 2016. Mineralization of Li,Ti,Zr,Ga,Nb and LREE of bauxite deposits in Songji area of Henan. Mineral Resources and Geology,30(2): 216-222]
[9]	吴林,黄智龙,王智琳,王宇非,陈健,吴涛. 2021. 黔中猫场铝土矿地球化学研究. 矿物学报,41(S1): 475-484.
	[Wu L,Huang Z L,Wang Z L,Wang Y F,Chen J,Wu T. 2021. Geochemistry of bauxite in the Maochang deposit,central Guizhou. Acta Mineralogica Sinica,41(S1): 475-484]
[10]	徐璐. 2020. 一种选择性浸出沉积型稀土矿的方法. 中国: ZL201811407361.2,2020-04-24.
	[Xu L. 2020. A method for selectively leaching sedimentary rare earth ores. China: ZL201811407361.2,2020-04-24]
[11]	薛洪富,向震中,吴林,肖宪国,叶霖,曾道国,黄威虎. 2022. 黔西北玉龙地区Nb-REE富集层中稀土赋存形式. 矿物学报,42(4): 555-556.
	[Xue H F,Xiang Z Z,Wu L,Xiao X G,Ye L,Zeng D G,Huang W H. 2022. The occurring states of REE in the enriched Nb-REE bed,Yulong area,north-western Guizhou Province. Acta Mineralogica Sinica,42(4): 555-556]
[12]	余文超,杜远生,周锦涛,成龙,邓旭升,戴贤铎,庞大卫,翁申富,雷志远,李沛刚,陈群. 2023. 中国铝土矿成矿作用的物质来源与深时环境因素: 进展与讨论. 地质学报,97(9): 3056-3074.
	[Yu W C,Du Y S,Zhou J T,Cheng L,Deng X S,Dai X D,Pang D W,Weng S F,Lei Z Y,Li P G,Chen Q. 2023. Provenance and deep-time environmental factors for bauxitization in China: progress and discussion. Acta Geologica Sinica,97(9): 3056-3074]
[13]	翟明国,吴福元,胡瑞忠,蒋少涌,李文昌,王汝成,王登红,齐涛,秦克章,温汉捷. 2019. 战略性关键金属矿产资源: 现状与问题. 中国科学基金,33(2): 106-111.
	[Zhai M G,Wu F Y,Hu R Z,Jiang S Y,Li W C,Wang R C,Wang D H,Qi T,Qin K Z,Wen H J. 2019. Critical metal mineral resources: current research status and scientific issues. Bulletin of National Natural Science Foundation of China,33(2): 106-111]
[14]	张启明,秦建华,廖震文,刘才泽. 2015. 滇东南晚二叠世铝土矿地球化学特征及物源分析. 现代地质,29(1): 32-44.
	[Zhang Q M,Qin J H,Liao Z W,Liu C Z. 2015. Geochemical characteristics and material source of the Late Permian bauxite deposits in southeastern Yunnan Province. Geoscience,29(1): 32-44]
[15]	张振杰,成秋明,杨玠,武国朋,葛云钊. 2021. 机器学习与成矿预测: 以闽西南铁多金属矿预测为例. 地学前缘,28(3): 221-235.
	[Zhang Z J,Cheng Q M,Yang J,Wu G P,Ge Y Z. 2021. Machine learning for mineral prospectivity: a case study of iron-polymetallic mineral prospectivity in southwestern Fujian. Earth Science Frontiers,28(3): 221-235]
[16]	Bárdossy G. 1982. Karst Bauxites. Amsterdam: Elsevier,4-6.
[17]	Bergen K J,Johnson P A,de Hoop M V,Beroza G C. 2019. Machine learning for data-driven discovery in solid Earth geoscience. Science,363: 100-115.
[18]	Breiman L. 2001. Random Forests. Machine Learning,45(1): 5-32.
[19]	Buccione R,Ameur-Zaimeche O,Ouladmansour A,Kechiched R,Mongelli G. 2024. Data-centric approach for predicting critical metals distribution: heavy rare earth elements in Cretaceous Mediterranean-type Karst bauxite deposits,southern Italy. Geochemistry,84: 126026.
[20]	Chen G X,Cheng Q M,Puetz S. 2023a. Special issue: Data-driven discovery in geosciences: opportunities and challenges. Mathematical Geosciences,55: 287-293.
[21]	Chen G X,Kusky T,Luo L,Li Q K,Cheng Q M. 2023b. Hadean tectonics: insights from machine learning. Geology,51(8): 718-722.
[22]	Chen J H,Wang Q F,Zhang Q Z,Carranza E J M,Wang J Q. 2018. Mineralogical and geochemical investigations on the iron-rich gibbsitic bauxite in Yongjiang basin,SW China. Journal of Geochemical Exploration,188: 413-426.
[23]	Chen T Q,Guestrin C,Chen T Q,Guestrin C. 2016. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. August 13-17,2016,San Francisco,California,USA. ACM,785-794.
[24]	Cortes C,Vapnik V. 1995. Support-vector networks. Machine Learning,20(3): 273-297.
[25]	Dormann C F,Elith J,Bacher S,Buchmann C,Carl G,Carré G,García Marquéz J R,Gruber B,Lafourcade B,Leitão P J,Münkemüller T,McClean C,Osborne P E,Reineking B,Schröder B,Skidmore A K,Zurell D,Lautenbach S. 2013. Collinearity: a review of methods to deal with it and a simulation study evaluating their performance. Ecography,36: 27-46.
[26]	Doucet L S,Tetley M G,Li Z X,Liu Y B,Gamaleldien H. 2022. Geochemical fingerprinting of continental and oceanic basalts: a machine learning approach. Earth-Science Reviews,233: 104192.
[27]	Ellahi S S,Taghipour B,Zarasvandi A,Bird M I,Somarin A K. 2016. Mineralogy,geochemistry and stable isotope studies of the dopolan bauxite deposit,Zagros Mountain,Iran. Minerals,6(1): 11.
[28]	Hou Y L,Zhong Y T,Xu Y G,He B. 2017. The provenance of Late Permian karstic bauxite deposits in SW China,constrained by the geochemistry of interbedded clastic rocks,and U-Pb-Hf-O isotopes of detrital zircons. Lithos,278: 240-254.
[29]	Hsu C W,Chang C C,Lin C J. 2003. A practical guide to Support Vector Classification. Department of Computer Science, National Taiwan University.
[30]	Kaneko H. 2022. Cross-validated permutation feature importance considering correlation between features. Analytical Science Advances,3: 278-287.
[31]	Li P G,Yu W C,Du Y S,Lai X L,Weng S F,Pang D W,Xiong G L,Lei Z Y,Zhao S,Yang S Q. 2020. Influence of geomorphology and leaching on the formation of Permian bauxite in northern Guizhou Province,South China. Journal of Geochemical Exploration,210: 106446.
[32]	Ling K Y,Zhu X Q,Tang H S,Du S J,Gu J. 2018. Geology and geochemistry of the xiaoshanba bauxite deposit,central Guizhou Province,SW China: implications for the behavior of trace and rare earth elements. Journal of Geochemical Exploration,190: 170-186.
[33]	Ling K Y,Long Y Z,Guo S X,Tang Y W,Dai Z H,Wen H J. 2024. Hydrothermal enrichment of rare earth elements in the Lower Permian Lijiatian bauxite deposit,Southern China. Journal of Geochemical Exploration,264: 107542.
[34]	Liu X F,Wang Q F,Deng J,Zhang Q Z,Sun S L,Meng J Y. 2010. Mineralogical and geochemical investigations of the Dajia Salento-type bauxite deposits,western Guangxi,China. Journal of Geochemical Exploration,105: 137-152.
[35]	Liu X F,Wang Q F,Zhang Q Z,Feng Y W,Cai S H. 2012. Mineralogical characteristics of the superlarge Quaternary bauxite deposits in Jingxi and Debao counties,western Guangxi,China. Journal of Asian Earth Sciences,52: 53-62.
[36]	Liu X F,Wang Q F,Feng Y W,Li Z M,Cai S H. 2013. Genesis of the Guangou karstic bauxite deposit in western Henan,China. Ore Geology Reviews,55: 162-175.
[37]	Liu X F,Wang Q F,Zhang Q Z,Zhang Y,Li Y. 2016. Genesis of REE minerals in the karstic bauxite in western Guangxi,China,and its constraints on the deposit formation conditions. Ore Geology Reviews,75: 100-115.
[38]	Liu X F,Wang Q F,Zhang Q Z,Yang S J,Liang Y Y,Zhang Y,Li Y,Guan T. 2017a. Genesis of the Permian karstic Pingguo bauxite deposit,western Guangxi,China. Mineralium Deposita,52(7): 1031-1048.
[39]	Liu X F,Wang Q F,Zhang Q Z,Yang S J,Zhang Y,Liang Y Y,Qing C. 2017b. Transformation from Permian to Quaternary bauxite in southwestern South China Block driven by superimposed orogeny: a case study from Sanhe ore deposit. Ore Geology Reviews,90: 998-1017.
[40]	Liu X F,Wang Q F,Zhao L H,Peng Y B,Ma Y,Zhou Z H. 2020. Metallogeny of the large-scale Carboniferous karstic bauxite in the Sanmenxia area,southern part of the North China Craton,China. Chemical Geology,556: 119851.
[41]	Long Y Z,Lu A H,Gu X P,Chi G X,Ye L,Jin Z G,Zhang D L. 2020. Cobalt enrichment in a paleo-karstic bauxite deposit at Yunfeng,Guizhou Province,SW China. Ore Geology Reviews,117: 103308.
[42]	Lundberg S,Lee S-I. 2017. A Unified Approach to Interpreting Model Predictions. arXiv: 1705.07874.
[43]	Luo C K,Liang P,Yang R D,Gao J B,Chen Q,Mo H C. 2023. Mineralogical and geochemical constraints on the occurrence forms of REEs in Carboniferous Karst bauxite,central Guizhou Province,southwest China: a case study of Lindai bauxite. Minerals,13(3): 320.
[44]	McCulloch W S,Pitts W. 1990. A logical Calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biology,52: 99-115.
[45]	Mongelli G,Boni M,Buccione R,Sinisi R. 2014. Geochemistry of the Apulian Karst bauxites(southern Italy): chemical fractionation and parental affinities. Ore Geology Reviews,63: 9-21.
[46]	Mongelli G,Mameli P,Sinisi R,Buccione R,Oggiano G. 2021. REEs and other critical raw materials in Cretaceous Mediterranean-type bauxite: the case of the Sardinian ore(Italy). Ore Geology Reviews,139: 104559.
[47]	Nathwani C L,Wilkinson J J,Fry G,Armstrong R N,Smith D J,Ihlenfeld C. 2022. Machine learning for geochemical exploration: classifying metallogenic fertility in arc magmas and insights into porphyry copper deposit formation. Mineralium Deposita,57(7): 1143-1166.
[48]	Pang D W,Yu W C,Chen Q,Du Y S,Dai X Y,Xiong G L,Deng K Y,Wu B,Deng X S,Zhou J T. 2023. Continental weathering led to the accumulation of Early Carboniferous bauxite deposits in the SW South China Craton. Journal of Asian Earth Sciences,256: 105801.
[49]	Quinn K A,Byrne R H,Schijf J. 2006. Sorption of yttrium and rare earth elements by amorphous ferric hydroxide: influence of pH and ionic strength. Marine Chemistry,99(1): 128-150.
[50]	Shrestha N. 2020. Detecting multicollinearity in regression analysis. American Journal of Applied Mathematics and Statistics,8(2): 39-42.
[51]	Tetley M G,Li Z X,Matthews K J,Williams S E,Müller R D. 2020. Decoding earth’s plate tectonic history using sparse geochemical data. Geoscience Frontiers,11(1): 265-276.
[52]	Wang N,Dai S F,Wang X B,Nechaev V P,French D,Graham I T,Zhao L,Song X L. 2022. New insights into the origin of Middle to Late Permian volcaniclastics(Nb-Zr-REY-Ga-rich horizons)from eastern Yunnan,SW China. Lithos,420-421: 106702.
[53]	Wang Q F,Deng J,Liu X F,Zhang Q Z,Sun S L,Jiang C Z,Zhou F. 2010. Discovery of the REE minerals and its geological significance in the Quyang bauxite deposit,West Guangxi,China. Journal of Asian Earth Sciences,39(6): 701-712.
[54]	Wang Z H,Fok K W,Thing V L L. 2022. Machine learning for encrypted malicious traffic detection: approaches,datasets and comparative study. Computers & Security,113: 102542.
[55]	Wang Z S,Li Y,Algeo T J,Yu W C,He X F. 2024. Critical metal enrichment in Upper Carboniferous Karst bauxite of North China Craton. Mineralium Deposita,59: 237-254.
[56]	Weng S F,Yu W C,Algeo T J,Du Y S,Li P G,Lei Z Y,Zhao S. 2019. Giant bauxite deposits of South China: multistage formation linked to Late Paleozoic ice age(LPIA)eustatic fluctuations. Ore Geology Reviews,104: 1-13.
[57]	Wolpert D H. 1992. Stacked generalization. Neural Networks,5(2): 241-259.
[58]	Yang S J,Huang Y X,Wang Q F,Deng J,Liu X F,Wang J Q. 2019a. Mineralogical and geochemical features of Karst bauxites from Poci(western Henan,China):implications for parental affinity and bauxitization. Ore Geology Reviews,105: 295-309.
[59]	Yang S J,Wang Q F,Deng J,Wang Y Z,Kang W,Liu X F,Li Z M. 2019b. Genesis of Karst bauxite-bearing sequences in Baofeng,Henan(China),and the distribution of critical metals. Ore Geology Reviews,115: 103161.
[60]	Yu W C,Algeo T J,Du Y S,Zhang Q L,Liang Y P. 2016. Mixed volcanogenic-lithogenic sources for Permian bauxite deposits in southwestern Youjiang Basin,South China,and their metallogenic significance. Sedimentary Geology,341: 276-288.
[61]	Zhang J Y,Wang Q F,Liu X F,Zhou G F,Xu H P,Zhu Y G. 2022a. Provenance and ore-forming process of Permian lithium-rich bauxite in central Yunnan,SW China. Ore Geology Reviews,145: 104862.
[62]	Zhang S Q,Liu X F,Zhao F H,Liu D N,Zou Y,Zhang W X,Liu X L,Li L,Zhao L H. 2021. Geological and geochemical characteristics of Karst bauxite-bearing sequences in Xiabu area,Central Shanxi Province,North China. Journal of Geochemical Exploration,230: 106849.
[63]	Zhang S Q,Zhao F H,Liu D N,Zhao L,Zhang X H,Lin J W,Dong H Y,Zhao S,Liu X F,Zan M J. 2022b. Modes of occurrence of critical metal elements(Li,REEs and other critical elements)in low-grade bauxite from southern Shanxi Province,China. Minerals,12(8): 990.
[64]	Zhang X M,Jing Y T,Zhao W F,Jiang Y J,Guan D X,Du H X,Qian Y,Ye F,Zhao W C. 2024. Rare earth elements in clay-sized fractions: implications for weathering fingerprint from parent materials to soils. Geoderma,445: 116879.
[65]	Zhang Z W,Zheng G D,Takahashi Y, Wu C Q, Zheng C F, Yao J H, Xiao C Y. 2016. Extreme enrichment of rare earth elements in hard clay rocks and its potential as a resource. Ore Geology Reviews, 72: 191-212.
[66]	Zhao L H,Wang W X,Liu X F,Sun X F,Liu L,Zhao J,Zhang S Q,Feng Y C. 2023. The formation environment of Carboniferous karstic bauxite deposits in the central North China Craton: insights from nitrogen isotopes and geochemical proxies. Ore Geology Reviews,159: 105559.
[67]	Zhong S H,Liu Y,Li S Z,Bindeman I N,Cawood P A,Seltmann R,Niu J H,Guo G H,Liu J Q. 2023. A machine learning method for distinguishing detrital zircon provenance. Contributions to Mineralogy and Petrology,178(6): 35.
[68]	Zhou J T,Yu W C,Du Y S,Liu X,Wang Y H,Xiong G L,Zhao Z Y,Pang D W,Shen D X,Weng S F,Liu Z C,Chen D. 2022. Provenance change and continental weathering of Late Permian bauxitic claystone in Guizhou Province,Southwest China. Journal of Geochemical Exploration,236: 106962.
[69]	Zhou J T,Yu W C,Wei W,Yang M Y,Du Y S. 2023. Provenance and tectonic evolution of bauxite deposits in the Tethys: perspective from random forest and logistic regression analyses. Geochemistry,Geophysics,Geosystems,24(6): e2022GC010745.
[70]	Zhu K Y,Su H M,Jiang S Y. 2019. Mineralogical control and characteristics of rare earth elements occurrence in Carboniferous bauxites from western Henan Province,North China: a XRD,SEM-EDS and LA-ICP-MS analysis. Ore Geology Reviews,114: 103144.

选择文件类型/文献管理软件名称

选择包含的内容

中国含铝岩系中稀土元素的赋存形式: 主量元素数据驱动的集成机器学习分析^*

Occurrence forms of rare earth elements in aluminum-bearing rock series in China: ensemble machine learning analysis driven by major element data

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 70

相关文章 0

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

中国含铝岩系中稀土元素的赋存形式: 主量元素数据驱动的集成机器学习分析*

Occurrence forms of rare earth elements in aluminum-bearing rock series in China: ensemble machine learning analysis driven by major element data

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 70

相关文章 0

编辑推荐

Metrics

本文评价

中国含铝岩系中稀土元素的赋存形式: 主量元素数据驱动的集成机器学习分析^*