Browsing by Author "Kalimenze, John Desderius"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    Machine learning based prospect targeting: A case of gold occurrence in central parts of Tanzania, East Africa
    (Elsevier, 2024) Gawusu, Sidique; Mvile, Benatus Norbert; Abu, Mahamuda; Kalimenze, John Desderius
    Soil geochemical analyses from central Tanzania reveal significant gold (Au) values, highlighting the potential for further exploration in the region. This study employs ensemble machine learning models—XGBoost-RF, XGBoost-SVM, and XGBoost-ANN—to enhance predictions of Au distribution. Among these, the XGBoost-ANN model showed the highest accuracy during the training phase, achieving a Mean Absolute Percentage Error (MAPE) of 1.275, a Root Mean Square Error (RMSE) of 0.031, an R² of 0.999, and a Pearson Correlation Coefficient (PCC) of 0.999. However, its performance declined in the testing phase with a MAPE of 0.0668 and an RMSE of 0.2491, indicating reduced predictiveness on new data. Spatial analyses using Global and Local Moran's I tests revealed no significant global spatial autocorrelation but identified localized clusters of high and low Au concentrations. Specific areas showed significant spatial dependence, enhancing our understanding of the complex geospatial distribution of Au. These findings support the combined use of predictive modeling and spatial statistical methods to refine mineral exploration strategies, highlighting the value of advanced analytics in identifying promising exploration targets.
  • Thumbnail Image
    Item
    Provenance studies of Au-bearing stream sediments and performance assessment of machine learning-based models: insight from whole-rock geochemistry central Tanzania, East Africa
    (Springer Science and Business Media LLC, 2024) Abu, Mahamuda; Mvile, Benatus Norbert; Kalimenze, John Desderius
    The source of clastic sediments generally, can be traced to their source through provenance studies using the whole rock geochemistry of clastic sediments. However, the provenance of the Au-bearing stream sediments within the central parts of Tanzania is yet to be deciphered. Hence, in this study, to enhance exploration targeting, the source of the Au-bearing stream sediments was characterized using whole-rock geochemistry. The performance of linear regression (LR), decision tree (DT), and polynomial regression (PR) models as prediction models for the Au mineralization in the area, were also compared as additional Au exploration techniques worth exploring in the area. The weathering condition proxies, CIA, ICV, CIW, and PIA as well as discriminant diagrams suggest weakly to intensely weathered sediments. The values of SiO2/Al2O3 and K2O/Al2O3 are indicative of felsic source rocks rather than compositional maturity due to sediments reworking. From Th/Cr, Cr/Th, Th/U, La/Sc, and Th/Sc proxies, the Au-bearing stream sediments are sourced from felsic igneous rocks. These indications are corroborated by the correlation matrix assessment. However, Au is not sourced from the same source rocks as the host sediments due probably, to a prior depositional mixing of the sediments before subsequent transportation to their current depositional environment. With R2 (0.62), MAE (0.6035), MSE (0.6546), and RMSE (0.8091) for LR, R2 (1.0), MAE (0.7500), MSE (1.6273), and RMSE (1.2752) for DT, and R2 (1.0), MAE (2.6608), MSE (12.7840), and RMSE (3.5755), for PR. The LR model performs better in predicting the Au occurrence in the area.
  • Thumbnail Image
    Item
    Provenance studies of Au-bearing stream sediments and performance assessment of machine learning-based models: insight from whole-rock geochemistry central Tanzania, East Africa
    (Springer Science and Business Media LLC, 2024) Abu, Mahamuda; Mvile, Benatus Norbert; Kalimenze, John Desderius
    The source of clastic sediments generally, can be traced to their source through provenance studies using the whole rock geochemistry of clastic sediments. However, the provenance of the Au-bearing stream sediments within the central parts of Tanzania is yet to be deciphered. Hence, in this study, to enhance exploration targeting, the source of the Au-bearing stream sediments was characterized using whole-rock geochemistry. The performance of linear regression (LR), decision tree (DT), and polynomial regression (PR) models as prediction models for the Au mineralization in the area, were also compared as additional Au exploration techniques worth exploring in the area. The weathering condition proxies, CIA, ICV, CIW, and PIA as well as discriminant diagrams suggest weakly to intensely weathered sediments. The values of SiO2/Al2O3 and K2O/Al2O3 are indicative of felsic source rocks rather than compositional maturity due to sediments reworking. From Th/Cr, Cr/Th, Th/U, La/Sc, and Th/Sc proxies, the Au-bearing stream sediments are sourced from felsic igneous rocks. These indications are corroborated by the correlation matrix assessment. However, Au is not sourced from the same source rocks as the host sediments due probably, to a prior depositional mixing of the sediments before subsequent transportation to their current depositional environment. With R2 (0.62), MAE (0.6035), MSE (0.6546), and RMSE (0.8091) for LR, R2 (1.0), MAE (0.7500), MSE (1.6273), and RMSE (1.2752) for DT, and R2 (1.0), MAE (2.6608), MSE (12.7840), and RMSE (3.5755), for PR. The LR model performs better in predicting the Au occurrence in the area.
  • Thumbnail Image
    Item
    Provenance studies of Au-bearing stream sediments and performance assessment of machine learning-based models: insight from whole-rock geochemistry central Tanzania, East Africa
    (Springer Science and Business Media LLC, 2024-01-29) Abu, Mahamuda; Mvile, Benatus Norbert; Kalimenze, John Desderius
    The source of clastic sediments generally, can be traced to their source through provenance studies using the whole rock geochemistry of clastic sediments. However, the provenance of the Au-bearing stream sediments within the central parts of Tanzania is yet to be deciphered. Hence, in this study, to enhance exploration targeting, the source of the Au-bearing stream sediments was characterized using whole-rock geochemistry. The performance of linear regression (LR), decision tree (DT), and polynomial regression (PR) models as prediction models for the Au mineralization in the area, were also compared as additional Au exploration techniques worth exploring in the area. The weathering condition proxies, CIA, ICV, CIW, and PIA as well as discriminant diagrams suggest weakly to intensely weathered sediments. The values of SiO2/Al2O3 and K2O/Al2O3 are indicative of felsic source rocks rather than compositional maturity due to sediments reworking. From Th/Cr, Cr/Th, Th/U, La/Sc, and Th/Sc proxies, the Au-bearing stream sediments are sourced from felsic igneous rocks. These indications are corroborated by the correlation matrix assessment. However, Au is not sourced from the same source rocks as the host sediments due probably, to a prior depositional mixing of the sediments before subsequent transportation to their current depositional environment. With R2 (0.62), MAE (0.6035), MSE (0.6546), and RMSE (0.8091) for LR, R2 (1.0), MAE (0.7500), MSE (1.6273), and RMSE (1.2752) for DT, and R2 (1.0), MAE (2.6608), MSE (12.7840), and RMSE (3.5755), for PR. The LR model performs better in predicting the Au occurrence in the area.
  • Thumbnail Image
    Item
    Soil geochemistry and multivariate statistical assessment of Copper–Gold-PGEs mineralization in parts of Singida Region of the Tanzania Craton, Tanzania, East Africa
    (Springer, 2023) Kalimenze, John Desderius; Abu, Mahamuda; Mvile, Benatus Norbert
    Multi-element mineralization of copper (Cu), gold (Au), and precious group of elements (PGEs) in the Kishapu-Igunga-Iramba areas in the central parts of Tanzania was evaluated in the study. The main aim was to characterize the mineralization with a focus on the pathfinder elements and the controls of the mineralization in the area through soil geochemistry and multivariate statistics and multivariate linear regression (MLR) methods. From the multivariate statistical methods applied, the Cu, Au, and PGEs mineralization in the area is associated with arsenic (As) and antimony (Sb). The Cu and Au occurrence in the area is a likely porphyry Cu-Au from their strong association. The mineralization (multi-elements) is strongly controlled by mafic–ultramafic rocks and volcaniclastics in the northern, southern, and central parts of the study area. From the MLR, Cu is strongly predicted by Zn, Ni, and Au with an error of ± 0.230, with Pd being predicted by only Pt and vice versa, with an error margin of ± 0.001. Au on the other hand is predicted by Cu, Fe, and Cr with an error margin of ± 0.473. The style of mineralization of these elements is comparable to their occurrence in the Neoproterozoic setting and the Paleoproterozoic Ubendian belt of Tanzania as well as the PGEs occurrence in South Africa and Canada. Coupling MLR with hierarchical cluster analysis and factor analysis brings out a more definitive elemental association to precious minerals occurrence from the study and is strongly recommended