Results Case 1. Paulo Afonso: Univariate TMI After sampling the TMI grid with overlapping sliding windows and projecting the windows into the sPCA space (Figure 7), the deposit signature was progressively reconstructed using an increasing number of retained components. The dominant TMI dipole pattern emerged clearly in the first components and became progressively more complete as additional components were included (Figure 10). By K = 17, the reconstruction captured the main geometry and internal spatial variations of the deposit, while later components contributed only minor refinements and noise. This value was therefore selected as a suitable balance between retaining the essential deposit signature and avoiding the inclusion of weak higher-order components. Figure 7 - Top-weighted sPCA loading maps from the Case 1 ranking. The dominant components highlight the spatial modes most strongly expressed by the reference deposit and emphasized in the similarity comparison. PC2 and PC3 have the highest absolute deposit scores (Figure 7), indicating that these components capture spatial patterns expressed strongly by the deposit, whereas PC1 explains the greatest overall regional variance but is less strongly expressed in the deposit itself. The reconstruction progression further shows 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 quantify the relative importance of each spatial mode in reconstructing the deposit signature. When the top 250 prediction windows were mapped across the demonstration area (Figure 9), several windows coincided with known mineral occurrences, including deposits 5,8, and 11, even though these deposits were not used as reference inputs.
RkJQdWJsaXNoZXIy MTM0Mzk2