Quantitative analysis of crustal thickness evolution across past geological periods poses significant challenges but provides invaluable insights into the planet’s geological history. It may help uncover new areas with potential critical mineral deposits and reveal the impacts of crustal thickness and elevation changes on the development of the atmosphere, hydrosphere, and biosphere. However, a significant knowledge gap in reconstructing regional paleo-crustal thickness distribution is that most estimation proxies are limited to arc-related magmas. By mining extensive geochemical data from present-day subduction zones, collision orogenic belts, and non-subduction-related intraplate igneous rock samples worldwide, along with their corresponding Moho depths during magmatism, we have developed a machine learning-based mohometry linking geochemical data to Moho depth, which is universally applicable in reconstructing ancient orogenic systems’ paleo-crustal evolution and tracking complex tectonic histories in both spatial and temporal dimensions. Our novel mohometry model demonstrates robust performance, achieving an R² of 0.937 and RMSE of 4.3 km. Feature importance filtering highlights key geochemical proxies, allowing for accurate paleo-crustal thickness estimation even when many elements are missing. The mohometry validity is demonstrated through applications to southern Tibet, which has well-constrained paleo-crustal thicknesses, and the South China Block, which is noted for its complex tectonic evolution and extensive 800-km-wide Cretaceous extensional system. Additionally, the evolution of reconstructed paleo-crustal thickness, particularly in areas with anomalously thick crust, strongly correlates with porphyry ore deposits. These findings offer valuable insights for prospecting for new porphyry ore deposits, particularly in ancient orogens where significant surface erosion has occurred.

The lithospheric architecture of passive margins is crucial for understanding the tectonic processes that caused the break-up of Gondwana. We highlight the evolution of the South Atlantic passive margins by a simple thermal lithosphere-asthenosphere-boundary (LAB) model based on rifting time, crustal thickness, and stretching factors. We simulate the different rifting stages that caused the opening of the South Atlantic Ocean and pick the LAB as the T=1330 °C isotherm, which is calculated by 1D advection and diffusion. In a synthetic example, we demonstrate that the initial crustal thickness has the largest effect on the thermal LAB. For the South American passive margin, our modeled LAB shows a deep and smooth structure between 110-150 km depth at equatorial latitudes and a more variable LAB between 50-200 km along the southern part. This division reflects different stages of the South Atlantic opening: initial opening of the southern South Atlantic causing substantial lithospheric thinning, followed by rather oblique opening of the equatorial South Atlantic accompanied by severe thinning. The modeled LAB reflects a high variability associated with tectonic features on a small scale. Comparing the LAB of the conjugate South American and African passive margins in a Gondwana framework reveals a variable lithospheric architecture for the southern conjugate margins. Along selected conjugate margin segments stark differences up to 80 km of the LAB depths correlate with strong gradients in margin width. This mutual asymmetry suggests highly asymmetric melting and lithospheric thinning prior to rifting.