This work addresses the challenge of producing chip level predictions on satellite imagery when only label proportions at a coarser spatial geometry are available, typically from statistical or aggregated data from administrative divisions (such as municipalities or communes). This kind of tabular data is usually widely available in many regions of the world and application areas and, thus, its exploitation may contribute to leverage the endemic scarcity of fine grained labelled data in Earth Observation (EO). This can be framed as a Learning from Label Proportions (LLP) problem setup. LLP applied to EO data is still an emerging field and performing comparative studies in applied scenarios remains a challenge due to the lack of standardized datasets. In this work, first, we show how simple deep learning and probabilistic methods generally perform better than standard more complex ones, providing a surprising level of finer grained spatial detail when trained with much coarser label proportions. Second, we provide a set of benchmarking datasets enabling comparative LLP applied to EO, providing both fine grained labels and aggregated data according to existing administrative divisions. Finally, we argue how this approach might be valuable when considering on-orbit inference and training. Source code is available at https://github.com/rramosp/llpeo. [+] This work has been submitted to the IEEE for review and possible publication. Copyright might be transferred without notice, after which this version may no longer be accessible.