Denoising of Geochemical Data using Deep Learning-Implications for Regional Surveys

被引:10
作者
Zhang, Steven E. [1 ]
Bourdeau, Julie E. [1 ]
Nwaila, Glen T. [3 ]
Parsa, Mohammad [1 ]
Ghorbani, Yousef [2 ]
机构
[1] Geol Survey Canada, 601 Booth St, Ottawa, ON K1A 0E8, Canada
[2] Univ Lincoln, Sch Chem, Joseph Banks Labs, Green Lane, Lincoln LN6 7DL, Lincs, England
[3] Univ Witwatersrand, Wits Min Inst, 1 Jan Smuts Ave, ZA-2000 Johannesburg, South Africa
关键词
Deep learning; Geochemical surveys; Autoencoder; Denoise; Geochemical data; AUTOENCODER NETWORK; RECOGNITION; GEOSTATISTICS; LAKE;
D O I
10.1007/s11053-024-10317-5
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
Regional geochemical surveys generate large amounts of data that can be used for a number of purposes such as to guide mineral exploration. Modern surveys are typically designed to permit quantification of data uncertainty through data quality metrics by using quality assurance and quality control (QA/QC) methods. However, these metrics, such as data accuracy and precision, are obtained through the data generation phase. Consequently, it is unclear how residual uncertainty in geochemical data can be minimized (denoised). This is a limitation to propagating uncertainty through downstream activities, particularly through complex models, which can result from the usage of artificial intelligence-based methods. This study aims to develop a deep learning-based method to examine and quantify uncertainty contained in geochemical survey data. Specifically, we demonstrate that: (1) autoencoders can reduce or modulate geochemical data uncertainty; (2) a reduction in uncertainty is observable in the spatial domain as a decrease of the nugget; and (3) a clear data reconstruction regime of the autoencoder can be identified that is strongly associated with data denoising, as opposed to the removal of useful events in data, such as meaningful geochemical anomalies. Our method to post-hoc denoising of geochemical data using deep learning is simple, clear and consistent, with the amount of denoising guided by highly interpretable metrics and existing frameworks of scientific data quality. Consequently, variably denoised data, as well as the original data, could be fed into a single downstream workflow (e.g., mapping, general data analysis or mineral prospectivity mapping), and the differences in the outcome can be subsequently quantified to propagate data uncertainty.
引用
收藏
页码:495 / 520
页数:26
相关论文
共 84 条
[1]  
AITCHISON J, 1982, J ROY STAT SOC B, V44, P139
[3]  
Amari SI., 1995, Advances in Neural Information Processing Systems, V8, P195
[4]  
AusIMM, 2014, MONOGRAPH, V30
[5]   Sample preparation for geochemical analysis: Strategies and significance [J].
Balaram, V. ;
Subramanyam, K. S. V. .
ADVANCES IN SAMPLE PREPARATION, 2022, 1
[6]  
Batterson W., 1989, ADV GEOPHYS, V61, P151
[7]   Learning Deep Architectures for AI [J].
Bengio, Yoshua .
FOUNDATIONS AND TRENDS IN MACHINE LEARNING, 2009, 2 (01) :1-127
[8]  
Bishop CM., 1995, Neural Networks for Pattern Recognition, DOI [10.1093/oso/9780198538493.001.0001, DOI 10.1093/OSO/9780198538493.001.0001]
[9]  
Bourdeau JE., 2023, Geological Survey of Canada, Open File, V8980, P43, DOI [10.4095/331911, DOI 10.4095/331911]
[10]   Method to enhance deep learning fault diagnosis by generating adversarial samples [J].
Cao, Jie ;
Ma, Jialin ;
Huang, Dailin ;
Yu, Ping ;
Wang, Jinhua ;
Zheng, Kangjie .
APPLIED SOFT COMPUTING, 2022, 116