outcome is that the method remains physically interpretable: the loading maps and reconstruction progression show that the highest-weighted modes are also the modes that rebuild the observed deposit signal. In this sense, the deposit-based weights are not only ranking coefficients, but also measures of which spatial patterns are most diagnostic of the training deposit. This is useful in brownfield exploration, where targets are more valuable if they can be related back to recognizable geophysical signatures rather than treated as black-box outputs. The first case, based on Deposit 6 and univariate TMI, provides the clearest proof of concept. sPCA substantially outperformed the raw TMI ranking, increasing total recovered test-deposit area from 10.2% to 54.1%, hit count from one to five, and cumulative recovery AUC from 14.04 to 83.15. These gains indicate that sPCA performs especially well when the reference deposit has a strong and internally coherent geophysical signature. In such settings, the decomposition isolates the dominant spatial geometry of the anomaly and reduces the influence of amplitude differences, local noise, and non-diagnostic background variation. The second case, based on Alemão (Deposit 3), shows why the joint use of TMI and radiometric U can be advantageous. Recovery improved progressively from 7.9% for Raw Multivariate to 31.0% for sPCA Univariate TMI, 52.8% for sPCA Univariate Radiometric U, and 77.7% for sPCA Multivariate. sPCA Multivariate also achieved the highest AUC and was the only method to hit all four test deposits. This progression suggests that feature extraction itself is important and that TMI and radiometric U contribute complementary information about the mineral system. A practical limitation is that variable selection must remain geologically informed. If datasets are unrelated to the same mineralizing system, or if their responses operate at incompatible scales, fusion could dilute rather than improve the similarity measure. Taken together, the two case studies show that sPCA is best viewed as an interpretable, data-driven filter that complements expert geological reasoning. It appears particularly attractive for brownfield exploration, where a known deposit can be used as a physically grounded template to search for similar targets. Future work should test how robust these gains remain across additional deposits, alternative variable combinations, and different window sizes, but the present results indicate that sPCA provides a promising and interpretable framework for similarity-based geophysical prospecting. References [1] Carranza, Emmanuel J. M. (2009). Geochemical Anomaly and Mineral Prospectivity Mapping in GIS. Elsevier. [2] Haldar, S. K. (2013). Mineral Exploration. Elsevier. [3] Hronsky, J. M. A.; Groves, D. I. (2008). Science of targeting: Definition, strategies, targeting and performance measurement. Australian Journal of Earth Sciences. 55(1), 3–12. [4] Nykänen, V.; Yousefi, M.; Sadeghi, M. (2025). Exploration information system: Mineral systems anatomy linked to computational techniques for mineral exploration targeting. Ore Geology Reviews. 187, 106961. [5] Partington, G. A.; Peters, K. J.; Czertowicz, T. A.; Greville, P. A.; Blevin, P. L.; Bahiru, E. A. (2024). Ranking mineral exploration targets in support of commercial decision making: A key component for inclusion in an exploration information system. Applied Geochemistry. 168, 106010. [6] Singer, D. A. (1993). Basic concepts in three-part quantitative assessments of undiscovered mineral resources. Nonrenewable Resources. 2(2), 69–81. [7] Yousefi, M.; Nykänen, V.; Harris, J.; Hronsky, J. M. A.; Kreuzer, O. P.; Bertrand, G.; Lindsay, M. (2024). Overcoming survival bias in targeting mineral deposits of the future: Towards null and
RkJQdWJsaXNoZXIy MTM0Mzk2