A Spatially Constrained Multi-Autoencoder approach for multivariate geochemical anomaly recognition

Chen, Lirong; Guan, Qingfeng; Xiong, Yihui; Liang, Jingyi; Wang, Ying; Xu, Yanqing

doi:10.1016/j.cageo.2019.01.016

Cited by 43 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, the spatial distribution features represent the spatial distribution characteristics of various elements, such as the geospatial distribution of sample elements, spatial correlation or spatial heterogeneity. Based on existing research (L. Chen et al., 2019), this study used the three models as follows: AE to extract the combined structural features of multiple elements in the sample, MCAE to extract the spatial distribution features of multiple elements in the sample, and FCAE to extract the combined features of the above two.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Comparative Study on Three Autoencoder‐Based Deep Learning Algorithms for Geochemical Anomaly Identification

Feng

Chen

2022

Earth and Space Science

Self Cite

View full text Add to dashboard Cite

Deep autoencoder (AE) networks show a powerful ability for geochemical anomaly identification. Because of little contribution to the AE network, small probability samples (again, please check this) having comparatively high reconstructed errors can be recognized by the trained model as anomalous samples. However, different autoencoder networks have different abilities for anomaly identification. To test these methods for geochemical anomaly identification, we based our study on stream sediment data of the Cu‐Zn‐Ag metallogenic area in southwest Fujian province as samples. Three unsupervised deep learning models: the autoencoder (AE), multi‐convolutional autoencoder (MCAE), and fusion convolutional autoencoder (FCAE), were used to extract the combined structural, spatial distribution, and mixed features of multiple‐elements. The results showed that the anomalous area delineated by the FCAE model had the best consistency with the known copper mineral occurrences, followed by the MCAE and AE models, with area under the curve values (AUC) of 0.80, 0.78, and 0.61, respectively. FCAE and AE were insensitive to changes in convolution window size, while MCAE extracted more spatial distribution or mixed features. Overall, FCAE focused more on structural distribution or mixed features, combining the advantages of both MCAE and AE. Therefore, FCAE performed best among the three deep learning methods. This study provides a practical basis for selecting and constructing geochemical anomaly recognition models based on deep learning algorithms.

show abstract

Section: Methodsmentioning

confidence: 99%

“…At present, deep learning algorithms for geochemical anomaly identification have achieved good results in predicting mineral distribution (Chen, Guan, Xiong, et al., 2019; Z. J. Chen et al., 2009; Hu et al., 2021). For example, Y. P. Liu et al.…”

Section: Introductionmentioning

confidence: 99%

Comparative Study on Three Autoencoder‐Based Deep Learning Algorithms for Geochemical Anomaly Identification

Feng

Chen

2022

Earth and Space Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning has been used to help solve geoscience research problems [1][2][3][4][5]. For example, the use of deep learning to solve the problem of mineral prediction will help researchers overcome the difficulty of not fully considering geological variables and evaluating the reliability of the current model in the existing data [6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

CNN2D-SENet-Based Prospecting Prediction Method: A Case Study from the Cu Deposits in the Zhunuo Mineral Concentrate Area in Tibet

Liu

Ran

et al. 2023

Minerals

View full text Add to dashboard Cite

Intelligent prospecting and prediction are important research foci in the field of mineral resource exploration. To solve the problem of the performance degradation of deep convolutional neural networks, enhancing the attention to target information and suppressing unnecessary feature information, this paper proposes a new prospecting prediction method based on a two-dimensional convolutional neural network (CNN2D). This method mainly uses known Cu deposits as the positive sample labels, adopts the sliding window method for data enhancement, and uses the window area as a unit to extract spatial variation features. It is important to supplement squeeze-and-excitation networks (SENets) to add an attention mechanism to the channel dimension, assign a weight value to each feature layer, and finally make prospecting predictions by matching the features of the known deposit window area and the features of the unknown window area. This method allows the neural network to focus on certain characteristic channels and realizes prospecting prediction in the case where there are few known deposits so that the deep learning method can be more effectively used for the prospecting prediction of mineralization. Based on geological data, geochemical exploration data of water system sediments, and aeromagnetic data, and via this method, this study carried out prospecting prediction of Cu deposits in the Zhunuo area of Tibet and predicted 12 favorable Cu prospecting prediction areas. Combined with previous research results and field exploration, the predicted result is consistent with the established mineralization and prospecting pattern and has good prospects for Cu deposit prospecting.

show abstract

“…Artificial intelligence is an important direction also in geological research and mineral resource exploration (Zhou et al., 2018). Different machine learning algorithms have been applied in metallogenic prediction (Table 1), such as autoencoders (Chen, 2020; Chen et al., 2019; Xiong & Zuo, 2016), recurrent neural networks (Bernardini et al., 2020; Brown et al., 2000; Sehgal et al., 2004), random forest (Carranza & Laborte, 2016; Chen, 2019; Hariharan et al., 2017), support vector machine (SVM) (Chang et al., 2018), semi‐supervised learning neural networks (Gao et al., 2021), and restricted Boltzmann machine (RBM) (Chen, 2015; Chen et al., 2014; Hinton, 2010; Wang et al., 2019). In particular, a variety of neural network methods have been applied to metallogenic prediction (Tessema, 2017; Xu, Li, et al., 2021).…”

Section: Introductionmentioning

confidence: 99%

Intelligent Recognition of Ore‐Forming Anomalies Based on Multisource Data Fusion: A Case Study of the Daqiao Mining Area, Gansu Province, China

Cai

Chen

et al. 2021

Earth and Space Science

View full text Add to dashboard Cite

Novel prediction methods using artificial intelligence have been developed to improve the identification, discovery, and utilization of new types of mineral resources at new depths or using new technologies. However, most artificial intelligence methods require large training data sets that are often unavailable for mineralization prediction models, leading to inaccuracies. To address this issue, we developed a semi‐supervised machine‐learning method to identify metallogenic anomalies using the density‐based spatial clustering of applications with noise method and autoencoder. The outputs of this method show irregularity in distributions inferred from geological, geochemical, and hyperspectral remote sensing data that match known mineralization locations. We focus on the Daqiao mining area of Gansu Province in China to show that the model predictions are highly consistent with known deposits of the Yinmahe and Daqiao gold mines, and two new prospecting areas have been highlighted for further field confirmation. The accuracy of this semi‐supervised learning method was verified by an interdisciplinary intelligent analysis, showing that this method could have wide‐reaching applications for improving regional geological surveys.

show abstract

A Spatially Constrained Multi-Autoencoder approach for multivariate geochemical anomaly recognition

Cited by 43 publications

References 33 publications

Comparative Study on Three Autoencoder‐Based Deep Learning Algorithms for Geochemical Anomaly Identification

Comparative Study on Three Autoencoder‐Based Deep Learning Algorithms for Geochemical Anomaly Identification

CNN2D-SENet-Based Prospecting Prediction Method: A Case Study from the Cu Deposits in the Zhunuo Mineral Concentrate Area in Tibet

Intelligent Recognition of Ore‐Forming Anomalies Based on Multisource Data Fusion: A Case Study of the Daqiao Mining Area, Gansu Province, China

Contact Info

Product

Resources

About