Evidential data integration to produce porphyry Cu prospectivity map, using a combination of knowledge and data‐driven methods

Riahi, Shokouh; Bahroudi, Abbas; Abedi, Maysam; Aslani, Soheila; Lentz, David R.

doi:10.1111/1365-2478.13169

Cited by 15 publications

(4 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The defuzzification involves partitioning the continuous fuzzy values from the synthesised map into a binary or multi-ranked prospectivity map showing favourable and unfavourable areas. This discretisation can be accomplished via various classification techniques, which include making a plot of the cumulative combined fuzzy favourability vs. the cumulative area, 54 the concentration area method of Cheng et al, 56 Riahi et al 57 and the natural breaks method. 58 The fuzzy logic model is finally validated by superimposing the deposit sites over the prospectivity map.…”

Section: Fuzzy Logicmentioning

confidence: 99%

Porphyry and skarn Cu prospectivity of Sumatra with GIS spatial modelling techniques

Mulja,

Heriawan,

Hawu Hede

2024

Applied Earth Science: Transactions of the Institutions of Mini

View full text Add to dashboard Cite

Decades of mineral exploration on Sumatra Island, situated along the Sunda magmatic arc in Indonesia, have only resulted in the discovery of one mid-sized, economically viable porphyry Cu deposit and a few exploited Cu-rich polymetallic skarns. Nevertheless, studies indicate that more Cu resources remain to be discovered. This contribution integrated geochemical, structural and relief evidential layers with the fuzzy logic- and weights-of-evidence (WoE) methods to produce mineral prospectivity maps that show not only a strong correlation between the generated favourable areas and known porphyry and skarn Cu prospects or lithologic units commonly associated with such deposits, but also other potentially new exploration districts throughout Sumatra. A local singularity fractal map of Cu-enriched zones helped define exploration priorities within the large fuzzy logic or WoE prospective areas, as well as cross-validated the results of the fuzzy models. The Cu potential maps can thus be used as base maps for porphyry and skarn Cu exploration. While the inclusion of relief data in the modelling proved useful for filtering out signal noise arising from other evidential layers and for overcoming the over-fitting issue encountered in the model that excluded this evidential layer, it could marginalise or even omit potential prospective areas lying outside the applied parameters. Although Sumatra Island hosts only one mid-sized, economically viable porphyry Cu deposit and a few exploited Cu-rich polymetallic skarns, studies indicate that more Cu resources remain to be discovered. This contribution integrated geochemical, structural, and relief evidential layers with the fuzzy logic- and weights-of-evidence (WoE) methods to produce mineral prospectivity maps that show a strong correlation between the generated favourable areas and the existing porphyry and skarn Cu prospects, as well as potentially new exploration districts throughout Sumatra. Moreover, a local singularity fractal map of Cu-enriched zones reduces the proposed target areas and cross-validates the results of the fuzzy model. The inclusion of relief data in the modelling filters out signal noise arising from other evidential layers and overcomes the over-fitting issue encountered in the model that excluded a relief map. The resulting Cu potential maps can thus be used as base maps for regional porphyry and skarn Cu exploration.

show abstract

Section: Fuzzy Logicmentioning

confidence: 99%

Porphyry and skarn Cu prospectivity of Sumatra with GIS spatial modelling techniques

Mulja,

Heriawan,

Hawu Hede

2024

Applied Earth Science: Transactions of the Institutions of Mini

View full text Add to dashboard Cite

show abstract

“…The most signi cant advantages of using remote sensing in porphyry Cu mineralization exploration studies is the close relationship between alteration and mineralization areas (Riahi et al 2022). Phyllic, argillic, and iron oxide alterations are common zones in cu porphyry systems.…”

Section: Aster Datamentioning

confidence: 99%

Porphyry Copper Prospectivity using Machine Learning Methods: A Case Study of the Shahr-e-Babak Prospecting Area, South Eastern Iran

Jahantigh,

Ramazi

2023

Preprint

View full text Add to dashboard Cite

Mineral prospectivity modelling (MPM) is an essential step in reducing cost and time at the reconnaissance stage of mineral exploration. In this paper, the MPM was conducted in the Shahr-e-Babak study area for porphyry copper prospectivity. For achieving this goal, the evidential layers, including geology, remote sensing, airborne geophysics, geochemistry, and elevation model, were used as the input of training models. Four machine learning methods, consisting of multilayer perceptron (MLP), Adaptive neuro fuzzy inference system (ANFIS), random forest (RF), and generalized regression neural network (GRNN), were used to generate the models. Then, the fractal method and the prediction area plot were applied to evaluate the models. The models were divided into low potential, moderate potential, and high potential zones. The effective weight of evidential layers was extracted using the P-A plot method. The weight of Cu anomalies, phyllic, argillic and iron oxide alterations, elevation data, PC1 geochemical anomalies, magnetic anomalies, and subvolcanic bodies were 0.71, 0.62, 0.49, 0.4, 0.32, 0.25, 0.25 and -0.49, respectively. In the next step, the weights were extracted for MLP, ANFIS, RF, and GRNN as 0.85, 0.78, 1.26, and 0.76, respectively. The statistical correlation coefficients between argillic, phyllic, and iron oxide alterations were calculated. In the final step, an integrated model was generated using machine learning methods. Then, the integrated model was divided into low, moderate, and high potential zones based on the fractal method. Favorable areas are located in the western and eastern parts of the study area based on the integrated model.

show abstract

“…clay alterations and iron oxides) on the radioactive elements K, eU and eTh distribution (Aisabokhae & Osazuwa, 2021;Badr, 2021;Dentith & Mudge, 2014, pp. 222;Ghoneim et al, 2021;Mamouch et al, 2022;Riahi et al, 2022Riahi et al, , 2021.…”

Section: Introductionmentioning

confidence: 99%

Mapping and litho‐geophysical classification of potential mining areas by spatial remote sensing and helicopter‐borne gamma‐ray spectrometry (Tikirt, Anti‐Atlas, Morocco)

Achkouch

Miftah

Ouchchen

et al. 2023

Geophysical Prospecting

View full text Add to dashboard Cite

The primary focus of this study is to explore the potential mineral areas. Advanced Spaceborne Thermal Emission and Reflection Radiometer images and radiometric data were combined in the Tikirt region to map hydrothermal alteration zones associated with mineralized deposits. Advanced Spaceborne Thermal Emission and Reflection Radiometer images were analysed using band ratios, principal component analysis and a fuzzy logic model to discover argillic, phyllic, propylitic and iron oxide alterations and to generate a mineral prospectivity map. In addition, mono‐element maps of radiometric elements (K in %, eU in ppm, eTh in ppm) and their behaviour in the ternary image have been elaborated to determine the concentrations of radiometric elements and the variation of radiometric character along the exposed terrains. The F parameter was calculated to target high potassium concentration areas associated with hydrothermal alteration zones. Combining the two methods highlighted four hydrothermal alteration zones considered very promising from a mining point of view. These zones are generally linked to the magma bodies affected by normal faults and exhibit a clear spatial correlation with mineral occurrences.

show abstract

Evidential data integration to produce porphyry Cu prospectivity map, using a combination of knowledge and data‐driven methods

Cited by 15 publications

References 58 publications

Porphyry and skarn Cu prospectivity of Sumatra with GIS spatial modelling techniques

Porphyry and skarn Cu prospectivity of Sumatra with GIS spatial modelling techniques

Porphyry Copper Prospectivity using Machine Learning Methods: A Case Study of the Shahr-e-Babak Prospecting Area, South Eastern Iran

Mapping and litho‐geophysical classification of potential mining areas by spatial remote sensing and helicopter‐borne gamma‐ray spectrometry (Tikirt, Anti‐Atlas, Morocco)

Contact Info

Product

Resources

About