Despite the availability of diverse geographical data, annotating it for analysis is time-consuming, requires specialist knowledge of the specific application domain, and existing supervised models based on domain-specific labeling have limited applicability. This expensive and time-consuming process results in unequal access to datasets, especially in low-income countries. To overcome these challenges, we developed a self-supervised algorithm that is pretrained on a globally diversified satellite dataset to annotate both labeled and unlabeled data, reducing the need for extensive labeling and processing resources. The model can be deployed across a wide range of geographic domains, not just those related to disaster monitoring or climate change, offering greater versatility than previous models that are limited by specific tasks and labeling requirements.
