基于高光谱与 LiDAR 融合的尾矿库 Pb 元素浓度反演

doi:10.3799/dqkx.2026.005

基于高光谱与 LiDAR 融合的尾矿库 Pb 元素浓度反演

doi: 10.3799/dqkx.2026.005

刘福江^1,3,
李博¹,
林伟华^1,3,
郭艳²,
朱哲¹,
王勉之¹

1. 中国地质大学（武汉）地理与信息工程学院，湖北武汉 430078
2. 中国地质大学（武汉）计算机学院，湖北武汉 430074
3. 中国地质大学区域生态过程与环境演变湖北省重点实验室，湖北武汉 430078

基金项目:

遥感科学国家重点实验室开放基金资助(编号:6142A01210404)

湖北智能地理信息处理重点实验室(项目编号:KLIGIP-2022-B03)

云南省元阳县大坪金矿床成矿模式与矿化预测研究(项目编号:2022026821)

中国科学院西南生态与环境研究所可持续发展研究项目(项目编号:CAS-ANSO-SDRP-2024-01)

中国地质大学(武汉)中央高校基本科研业务费资助项目(项目编号:2025XLA58)

国家自然基金火星大地基准与正常重力场研究项目(项目编号:42374051)

详细信息

作者简介:
刘福江（1973-），男，博士，中国地质大学（武汉）副教授，主要从事环境遥感方面的研究，E-mail:liufujiang@cug.edu.cn;李博（2002-），男，硕士，毕业于中国地质大学（武汉），研究方向为高植被覆盖遥感找矿模型研究。E-mail：Libobo@cug.edu.cn

中图分类号: X87
计量
- 文章访问数: 33
- HTML全文浏览量: 2
- PDF下载量: 6
- 被引次数: 0
出版历程
- 收稿日期: 2025-09-15
- 网络出版日期: 2026-01-28

Inversion of Heavy Metal Pb Concentration in Tailings Areas Based on Hyperspectral and LiDAR Multi-Source Data Fusion

1 School of Geography and Information Engineering, China University of Geosciences (Wuhan), Wuhan 430078, China
2 School of Computer Science, China University of Geosciences (Wuhan), Wuhan 430074, China
3 Hubei Key Laboratory of Regional Ecology and Environmental Change, China University of Geosciences, Wuhan 430078, China

摘要

摘要: 尾矿库是重金属迁移与富集的高风险区域，其受胁迫植被在光谱特征与冠层结构上表现出显著响应。本研究融合机载高光谱影像与 LiDAR 点云数据，构建多源特征体系，提取光谱与三维结构参数共 112 项，并通过相关性分析与 ReliefF 方法筛选出 10 个关键特征，建立多种反演模型进行对比。结果表明，多源特征融合能够从生理与结构两个层面刻画 Pb 胁迫特征，显著提升模型对复杂污染信号的表达能力，其中 ReliefF–RF 模型表现最优。空间反演结果显示，Pb 高值区主要分布于一、二号尾矿库内部及其东南缘低洼区域，与地形汇流路径高度一致。研究结果为尾矿区重金属污染监测与生态风险评估提供了可行的技术路径。
- 高光谱遥感 /
- 重金属污染 /
- 尾矿库监测 /
- 特征优化 /
- ReliefF-RF
Abstract: Tailings reservoirs are high-risk areas for the migration and accumulation of heavy metals, and vegetation under stress exhibits pronounced spectral and canopy structural responses.This study integrates airborne hyperspectral imagery and LiDAR point-cloud data to construct a multi-source feature set, extracting a total of 112 spectral and three-dimensional structural parameters. Key features were further reduced to 10 through correlation analysis and the ReliefF method, and multiple inversion models were established for comparison.The results indicate that multi-source feature fusion captures Pb stress characteristics from both physiological and structural perspectives and significantly enhances the model’s ability to represent complex pollution signals, with the ReliefF–RF model achieving the best performance. Spatial inversion results show that high Pb concentrations are mainly distributed within the first and second tailings reservoirs and in low-lying areas along their southeastern margins, which are highly consistent with terrain flow paths. The proposed approach provides a feasible technical pathway for heavy-metal pollution monitoring and ecological risk assessment in tailings areas.
- hyperspectral remote sensing /
- heavy metal pollution /
- tailings monitoring /
- feature optimization /
- ReliefF-RF

HTML全文

参考文献(36)

Akoto, O., Yakubu, S., Ofori, L.A., Bortey-sam, N., Boadi, N.O., Horgah, J., Sackey, L.N.A., 2023. Multivariate studies and heavy metal pollution in soil from gold mining area. Heliyon 9, e12661. https://doi.org/10.1016/j.heliyon.2022.e12661
Bai, S.H., Tahmasbian, I., Zhou, J., Nevenimo, T., Hannet, G., Walton, D., Randall, B., Gama, T., Wallace, H.M., 2018. A non-destructive determination of peroxide values, total nitrogen and mineral nutrients in an edible tree nut using hyperspectral imaging. Computers and Electronics in Agriculture 151, 492–500. https://doi.org/10.1016/j.compag.2018.06.029
Briffa, J., Sinagra, E., Blundell, R., 2020. Heavy metal pollution in the environment and their toxicological effects on humans. Heliyon 6, e04691. https://doi.org/10.1016/j.heliyon.2020.e04691
Chen, W., Li, Z., Wang, H., He, W., Chen, Z., Li, J., 2025. HTransNet: A Hierarchical Transformer Network with Dual Attention for Large-Scale Mining Scene Classification Using Multi-Category High- Resolution Remote Sensing Dataset. Journal of Earth Science. doi: 10.1007/s12583-025-0335-x
Chen, Y., Jiang, X., Wang, Y., Zhuang, D., 2018. Spatial characteristics of heavy metal pollution and the potential ecological risk of a typical mining area: A case study in China. Process Safety and Environmental Protection 113, 204–219. https://doi.org/10.1016/j.psep.2017.10.008
Chen, Z., Chen, Y., Shi, T., Chen, X., Pan, X., Lei, J., Wu, T., Li, Y., Liu, Q., Liu, X., 2023. Estimation of Soil Organic Carbon in Tropical Rainforest Regions by Combining Uav Hyperspectral and Lidar Data. https://doi.org/10.2139/ssrn.4547030
Cheng, H., Shen, R., Chen, Y., Wan, Q., Shi, T., Wang, J., Wan, Y., Hong, Y., Li, X., 2019. Estimating heavy metal concentrations in suburban soils with reflectance spectroscopy. Geoderma 336, 59–67. https://doi.org/10.1016/j.geoderma.2018.08.010
Fathabad, A.E., Shariatifar, N., Moazzen, M., Nazmara, S., Fakhri, Y., Alimohammadi, M., Azari, A., Mousavi Khaneghah, A., 2018. Determination of heavy metal content of processed fruit products from Tehran’s market using ICP- OES: A risk assessment study. Food and Chemical Toxicology 115, 436–446. https://doi.org/10.1016/j.fct.2018.03.044
Habashi, J., Mohammady Oskouei, M., Jamshid Moghadam, H., Beiranvand Pour, A., 2024. Optimizing alteration mineral detection: A fusion of multispectral and hyperspectral remote sensing techniques in the Sar-e-Chah-e Shur, Iran. Remote Sensing Applications: Society and Environment 35, 101249. https://doi.org/10.1016/j.rsase.2024.101249
Hu, J., Peng, D., Chen, J.M., Huete, A.R., Yu, L., Lou, Z., Cheng, E., Yang, X., Zhang, B., 2025. High-precision inversion of vegetation parameters in the AI era: Integrating hyperspectral remote sensing and deep learning. The Innovation 6, 100868. https://doi.org/10.1016/j.xinn.2025.100868
Jaffari, Z.H., Abbas, A., Kim, C.-M., Shin, J., Kwak, J., Son, C., Lee, Y.-G., Kim, S., Chon, K., Cho, K.H., 2024. Transformer-based deep learning models for adsorption capacity prediction of heavy metal ions toward biochar-based adsorbents. Journal of Hazardous Materials 462, 132773. https://doi.org/10.1016/j.jhazmat.2023.132773
Kyabutwa, P.L., Alyamni, N., Abot, J.L., Zestos, A.G., 2025. Recent Trends in Electrochemical Methods for Real-Time Detection of Heavy Metals in Water and Soil: A Review. Current Opinion in Electrochemistry 101749. https://doi.org/10.1016/j.coelec.2025.101749
Liu, J.; Lan, J.; Zeng, Y.; Luo, W.; Zhuang, Z.; Zou, J. Explainability Feature Bands Adaptive Selection for Hyperspectral Image Classification. Remote Sens. 2025, 17, 1620. https://doi.org/10.3390/rs17091620
Modzelewska, A., Fassnacht, F.E., Stereńczak, K., 2020. Tree species identification within an extensive forest area with diverse management regimes using airborne hyperspectral data. International Journal of Applied Earth Observation and Geoinformation 84, 101960. https://doi.org/10.1016/j.jag.2019.101960
Mohammed, H., Sadeek, S., Mahmoud, A.R., Zaky, D., 2016. Comparison of AAS, EDXRF, ICP-MS and INAA performance for determination of selected heavy metals in HFO ashes. Microchemical Journal 128, 1–6. https://doi.org/10.1016/j.microc.2016.04.002
Rawat, H., Singh, R., Dane, G., Gandhi, Y., Kumar, V., Mishra, S.K., Charde, V., Sharma, P., Narasimhaji, Ch.V., Singh, A., Acharya, R., 2024. Exploring the geographical variability of Asphaltum punjabianum (Shilajit) from India in elements and phytochemicals variations using GC–MS/MS, LC, ICP OES, and in-silico studies. Results in Chemistry 10, 101691. https://doi.org/10.1016/j.rechem.2024.101691
Shi, Y., Shen, X., Hu, M., Yang, A., Zhou, K., Yu, F., Tao, Y., Cao, L., 2025. . Computers and Electronics in Agriculture 239, 110898. https://doi.org/10.1016/j.compag.2025.110898
Tan, K., Wang, H., Chen, L., Du, Q., Du, P., Pan, C., 2020. Estimation of the spatial distribution of heavy metal in agricultural soils using airborne hyperspectral imaging and random forest. Journal of Hazardous Materials 382, 120987. https://doi.org/10.1016/j.jhazmat.2019.120987
Tao, C., Wang, Y., Cui, W., Zou, B., Zou, Z., Tu, Y., 2019. A transferable spectroscopic diagnosis model for predicting arsenic contamination in soil. Science of The Total Environment 669, 964–972. https://doi.org/10.1016/j.scitotenv.2019.03.186
Urbanowicz, R. J., et al. (2018). ReliefF-based feature selection: An updated review. Journal of Biomedical Informatics, 85, 189–203.
Wang, Y., Yang, Y., Li, Q., Zhang, Y., Chen, X., 2022a. Early Warning of Heavy Metal Pollution after Tailing Pond Failure Accident. J. Earth Sci. 33, 1047–1055. https://doi.org/10.1007/s12583-020-1103-6
Zhou, W., Yang, H., Xie, L., Li, H., Huang, L., Zhao, Y., Yue, T., 2021. Hyperspectral inversion of soil heavy metals in Three-River Source Region based on random forest model. CATENA 202, 105222. https://doi.org/10.1016/j.catena.2021.105222
戴磊,王贵玲,何雨江.基于分形理论研究土壤结构及其水分特征关系[J].地球科学,2021,46(09):3410-3420.
殷思达.电感耦合等离子体质谱法与原子吸收光谱法在土壤重金属检测中的对比分析[J].中国资源综合利用,2022,40(08):86-88.
杨汉水, 马琳, 王瑞禛, 陈伟涛, 王力哲, 2025. 基于无人机高光谱遥感的黑土土壤有机碳含量反演方法研究. 地球科学, 50(8): 3144-3152.
成永生,周瑶.土壤重金属高光谱遥感定量监测研究进展与趋势[J].中国有色金属学报,2021,31(11):3450-3467.
陈彪,彭欣月,周素红,等.基于多源数据融合的农村建筑智能识别与三维建模方法研究[J].热带地理,2023,43(02):190-201.
刘佳,汪大明,刘德长,等.协同利用高光谱与多光谱遥感技术提取油气异常信息[J].地球科学(中国地质大学学报),2015,40(08):1371-1380.
刘正盛.激光雷达(LiDAR)技术在植被覆盖度高的山区地质灾害识别与应用[J].地下水,2025,47(02):171-173+186.
陈哲锋.LiDAR技术在高植被覆盖区地质灾害调查中最优点云密度的研究与应用[J/OL].工程勘察,1-9[2025-10-22].
陈刚,郝社锋,蒋波,等.基于机载LiDAR技术植被茂密区小型滑坡识别与评价[J].自然资源遥感,2024,36(03):196-205.
曹锐,湛龙,郭金才,等.湖北秭归月亮包石英脉型金矿床地质特征研究[J].黄金,2007,(02):16-19.
王春洋,李天保,张嘉琦.谈土壤环境监测技术规范中的土壤环境质量评价若干问题[J].环境与发展,2018,30(03):155-156.DOI: 10.16647/j.cnki.cn15-1369/X.2018.03.091.
李会玲,刘严松,沈杜衡,等.铅锌矿集区土壤重金属含量高光谱反演方法研究[J].矿业研究与开发,2025,45(02):204-212.
陈博文,史硕,龚威,等.基于空谱特征优化选择的高光谱激光雷达地物分类[J].光学学报,2023,43(12):284-296.
孟畅,红梅,李斐.高光谱敏感波段筛选与机器学习协同提升土壤重金属预测精度[J].生态环境学报,2025,34(06):950-960.