Accessible seafloor minerals located near mid-ocean ridges are noticed to mitigate projected metal demands of the net-zero energy transition, promoting growing research interest in quantifying global distributions of seafloor massive sulfides (SMS). Mineral potentials are commonly estimated using geophysical and geological data that lastly rely on additional confirmation studies using sparsely available, locally limited, seafloor imagery, grab samples, and coring data. This raises the challenge of linking in-situ confirmation data to geophysical data acquired at disparate spatial scales to obtain quantitative mineral predictions. Although multivariate datasets for marine mineral research are incessantly acquired, robust, integrative data analysis requires cumbersome workflows and experienced interpreters. Here, we introduce an automated two-step machine learning approach that integrates automated mound detection with geophysical data to merge mineral predictors into distinct classes and reassess marine mineral potentials for distinct regions. The automated workflow employs a U-Net convolutional neural network to identify mound-like structures in bathymetry data and distinguishes different mound classes through classification of mound architectures and magnetic signatures. Finally, controlled source electromagnetic data is utilized to reassess predictions of potential SMS volumes. Our study focuses on the Trans-Atlantic Geotraverse (TAG) area, which is amid the most explored SMS area worldwide and includes 15 known SMS sites. The automated workflow classifies 14 of the 15 known mounds as exploration targets of either high- or medium-priority. This reduces the exploration area to less than 7% of the original survey area from 49 km2 to 3.1 km2.