Context <p>Restoration is an effective measure to counteract declines of reef-building coral populations. Despite decades of coral restoration research and practice, very little emphasis has been placed on how the spatial distribution of restoration sites influences ecosystem recovery and connectivity.</p> Objectives <p>Combining image classification of aerial data with geoinformatics, we aim to identify priority restoration sites to increase the structural connectivity and fertilization potential of coral keystone species.</p> Methods <p>We focus on <i>Acropora palmata</i> at two natural reefs with contrasting spatial distributions of the species and include a hypothetical reef with a random distribution as a comparative baseline to represent a highly structurally degraded system. Priority sites are then identified at each reefscape through spatial modelling using three connectivity metrics from classical landscape ecology.</p> Results <p>Our models suggest that restoration sites joining or bordering major patches of <i>A. palmata</i> have the greatest potential to increase structural connectivity. Reefs of more degraded status are favourable for restoration because they exhibit a greater increase in connectivity metrics per area restored, while also maximizing the fertilization potential between colonies. Furthermore, the spatial extent that needs to be restored to achieve maximum efficiency is greatly dependent on the initial coverage and distribution of the species.</p> Conclusions <p>Our study demonstrates the importance of including spatial planning in the site selection process of coral restoration and provides a methodological framework that can aid in tailoring related strategies in accordance with the spatial arrangement of the target species.</p>