Determining mid-ocean ridge geography from upper mantle temperature

In this study, we examine the influence of the mantle and large-scale tectonics on the global mid-ocean ridge (MOR) system. Using solely seismically-inferred upper mantle temperatures below the melting zone (260-600 km) and an interpretable machine learning model (Random Forest and Principal Component Analysis), we can predict a priori the location (ocean basin and ridge system) of global MOR with up to 90% accuracy. Two features provide > 50% of the discriminative power: the temperature difference between the mid-layer (340-500 km) and other depths, and the depth-averaged temperature of the upper mantle. We suggest long-term (100s Myr) tectonic and large-scale convective processes primarily driven by deep subduction left ample, distinct but hidden fingerprints in the mantle that allow us to separate regions at ∼1000 km scale. Our result implies that the large-scale geophysical and geochemical differences observed along the MOR system are reflective, not primarily of shallow processes associated with melting, but of the integrated long-term tectonic, subduction, and convective flow history that determines the present-day upper mantle temperature structure.