Zijing Luo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zijing Luo has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Ehsan Farahbakhsh
Earthbyte Group, School of Geosciences, the University of Sydney, Sydney, Australia
7 shared publications - R. Dietmar Müller
EarthByte Group, School of Geosciences, University of Sydney, Sydney, NSW 2006, Australia
7 shared publications Stephen Hore
Geological Survey of South Australia, Adelaide, Australia
7 shared publications
Latest Publications
- Open Access
- 7 April 2026
- Published by Copernicus GmbH in Geoscientific Model Development
- Vol. 19 (7) , 2593-2625
DEEP-SEAM: an explainable semi-supervised deep learning framework for mineral prospectivity mapping
The global transition to clean energy is sharply increasing demand for rare earth elements (REEs), yet discovery rates are declining, especially in areas concealed by younger cover. Deep learning (DL) offers new opportunities for mineral prospectivity mapping (MPM), but its application is challenged by sparse labelled mineral occurrences, strong class imbalance, and limited model transparency. To address these issues, we present DEEP-SEAM, an explainable semi-supervised DL framework that integrates geological, geophysical, geochemical, remote sensing, and topographic datasets to predict REE prospectivity in the northern Curnamona Province, South Australia. The framework employs the Deviation Network (DevNet), a semi-supervised anomaly detection model that learns from a small number of known REE occurrences together with abundant unlabelled samples. DEEP-SEAM produces highly accurate predictions: the top 2 % of the mapped area contains 86 % of known REE deposits, and nearly all known occurrences fall within the highest-prospectivity zones. These areas show strong spatial association with felsic granites, major faults, and Mesoproterozoic metasedimentary sequences – features consistent with established REE mineral system models. To improve interpretability, we apply SHapley Additive exPlanations (SHAP), which highlight radiometric signatures, magnetic pseudo-gravity attributes, hydrothermal alteration indicators, and key geochemical principal components as the most influential predictors. These insights align with independent geological evidence, strengthening confidence in the predictive outcomes. DEEP-SEAM provides a transparent, scalable, and data-efficient approach for delineating REE prospectivity in complex and partially covered terranes, offering a valuable tool for reducing exploration risk and guiding future targeting efforts.
- 7 April 2026
- Published by Copernicus GmbH in Geoscientific Model Development
- Vol. 19 (7) , 2593-2625
Open AccessDEEP-SEAM: an explainable semi-supervised deep learning framework for mineral prospectivity mapping
The global transition to clean energy is sharply increasing demand for rare earth elements (REEs), yet discovery rates are declining, especially in areas concealed by younger cover. Deep learning (DL) offers new opportunities for mineral prospectivity mapping (MPM), but its application is challenged by sparse labelled mineral occurrences, strong class imbalance, and limited model transparency. To address these issues, we present DEEP-SEAM, an explainable semi-supervised DL framework that integrates geological, geophysical, geochemical, remote sensing, and topographic datasets to predict REE prospectivity in the northern Curnamona Province, South Australia. The framework employs the Deviation Network (DevNet), a semi-supervised anomaly detection model that learns from a small number of known REE occurrences together with abundant unlabelled samples. DEEP-SEAM produces highly accurate predictions: the top 2 % of the mapped area contains 86 % of known REE deposits, and nearly all known occurrences fall within the highest-prospectivity zones. These areas show strong spatial association with felsic granites, major faults, and Mesoproterozoic metasedimentary sequences – features consistent with established REE mineral system models. To improve interpretability, we apply SHapley Additive exPlanations (SHAP), which highlight radiometric signatures, magnetic pseudo-gravity attributes, hydrothermal alteration indicators, and key geochemical principal components as the most influential predictors. These insights align with independent geological evidence, strengthening confidence in the predictive outcomes. DEEP-SEAM provides a transparent, scalable, and data-efficient approach for delineating REE prospectivity in complex and partially covered terranes, offering a valuable tool for reducing exploration risk and guiding future targeting efforts.
- Open Access
- 16 December 2025
- Published by Copernicus GmbH
- Vol. 2025, 1-43
Reply on RC2
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.
- 16 December 2025
- Published by Copernicus GmbH
- Vol. 2025, 1-43
Open AccessReply on RC2
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.
- Open Access
- 16 December 2025
- Published by Copernicus GmbH
- Vol. 2025, 1-43
Reply on RC1
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.
- 16 December 2025
- Published by Copernicus GmbH
- Vol. 2025, 1-43
Open AccessReply on RC1
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.
- Open Access
- 13 October 2025
- Published by Copernicus GmbH
- Vol. 2025, 1-43
Reply on CEC1
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.
- 13 October 2025
- Published by Copernicus GmbH
- Vol. 2025, 1-43
Open AccessReply on CEC1
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.
- Open Access
- 12 October 2025
- Published by Copernicus GmbH
- Vol. 2025, 1-43
Comment on egusphere-2025-3283
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.
- 12 October 2025
- Published by Copernicus GmbH
- Vol. 2025, 1-43
Open AccessComment on egusphere-2025-3283
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.
- Open Access
- 10 October 2025
- Published by Copernicus GmbH
- p. 1-43
Comment on egusphere-2025-3283
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.
- 10 October 2025
- Published by Copernicus GmbH
- p. 1-43
Open AccessComment on egusphere-2025-3283
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.
- Open Access
- 15 September 2025
- Published by Copernicus GmbH in EGUsphere
- Vol. 2025, 1-43
An explainable semi-supervised deep learning framework for mineral prospectivity mapping: DEEP-SEAM v1.0
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.
- 15 September 2025
- Published by Copernicus GmbH in EGUsphere
- Vol. 2025, 1-43
Open AccessAn explainable semi-supervised deep learning framework for mineral prospectivity mapping: DEEP-SEAM v1.0
The clean energy transition demands a significant increase in exploration for critical minerals, particularly rare earth elements (REEs), beyond the well-explored surface deposits. Discovery rates have been declining for decades, escalating the need for new exploration methodologies. Deep learning (DL) utilizes multi-layer neural networks to automatically model high-level abstractions of data, extracting information relevant to the target task, thereby positioning itself as a potentially powerful tool for mineral prediction. But the non-linear and highly heterogeneous characteristics of complex exploration data sets paired with sparse, imbalanced training data and a lack of interpretability represent significant challenges. In this study, we have developed DEEP-SEAM v1.0, a novel explainable semi-supervised DL framework for prospectivity mapping of REE mineralisation in Northern Curnamona Province, South Australia. This framework proposes a comprehensive data preprocessing pipeline and introduces a semi-supervised anomaly detection DL model, termed the Deviation Network (DevNet). DevNet leverages a limited number of positive samples alongside a large number of unlabelled samples to effectively establish the mapping between multi-source exploration data and mineralisation probability. The results indicate that prospective mineralisation areas exhibit a strong spatial coupling with known REE deposits, with high-probability mineralisation areas primarily concentrated in faulted regions, felsic granites, and Mesoproterozoic strata. To address concerns about the poor interpretability of DL models, we incorporate a post-hoc model interpretation technique known as the SHapley Additive exPlanations method. The method facilitates an improved understanding of the decision-making mechanisms and logic underlying DevNet. By comparing DEEP-SEAM’s decisions with our understanding of mineral systems, we not only enhance the model’s transparency and interpretability but also strengthen the reliability and credibility of the predicted prospective mineralisation areas.