Summary
Twenty-first century research is enabled by the availability of vast amounts of data, collected across a wide range of temporal and spatial scales, often in real time. Entire fleets of satellites, drones and other devices monitor the Earth at ever-increasing resolution, adding to the enormous corpus of maps and metadata that enable sciences from geology to biodiversity. While citizen science - or crowdsourcing science - has been successfully leveraged over the past several decades to close the analysis gap arising from large amounts of data, the sheer scale and complexity of these new data set