Citizen science – research conducted in whole or in part by people for whom science is not their profession – is increasingly valuable for society, ecology, and conservation. Natural resource and landscape management based on the best available science is increasingly relying, at least in part, on citizen science data to make informed and adaptive decisions supporting biodiversity conservation . The data collection power of citizen science is enormous, but as citizen science at this scale is a new development in ecology and conservation, there is a great deal of inefficiency in this process. The largest inefficiency is that, to this point, the most ‘successful’ citizen science projects generally have a haphazard sampling regime replete with redundancies and gaps in the associated citizen science data. Can we direct this enormous amount of effort more efficiently? What steps can be taken at the upstream portion of citizen science projects to maximise efficiency of analyses with downstream datasets? This project will build a workflow which allows us to maximise the information content that citizen scientists contribute to our collective knowledge of biodiversity by developing algorithms that predict the highest ‘valued’ sites in time and space for biodiversity sampling by citizen scientists which leads to more efficiently directing effort in space and time.