You can visit our project website https://satbird.github.io. Was there a specific task in mind? Was there a specific gap that needed to be filled? The dataset was created for the task of predicting bird species encounter rates at scale, from remote sensing imagery and environmental data. Traditional methods in species distribution modelling (SDM) generally focus either on narrow sets of species or narrow geographical areas, while multi-species modelling is needed for understanding ecosystems. SatBird was designed to bridge knowledge gaps in species distributions, by leveraging abundant presence-absence data in the citizen science database eBird and globally available Sentinel-2 satellite data. Who created the dataset (e.g., which team, research group) and on behalf of which entity (e.g., company, institution, organization)?