The Earth's mantle transition zone has significant control on material flux between upper and lower mantle, and thus constraining its properties is imperative to understand dynamic processes and circulation patterns. Global seismic datasets to study the transition zone typically display highly uneven spatial distribution. Thus, supplementation with complementary geometries is essential to improve knowledge of its physical structures, thermochemistry, and impact on convection. Here, we present an automated computational pipeline to compile, analyse, and model large datasets of ScSScS precursors. We integrate various data-driven methodologies to derive high resolution maps of transition zone discontinuity properties. Seismic measurements are combined with mineral physics calculations in an interdisciplinary inversion to obtain new models of thermochemistry beneath the subduction zones of Australasia, revealing high variability on short spatial length scales. Our results identify areas of low temperature and basalt enrichment associated with subducting slabs, providing insight into local dynamics and accumulation of basalt.