Intelligent Data Analysis
Applying machine learning and data mining techniques for efficient data handling.
Our team provides efficient data mobilisation and decision support, to realise Kew Science's priority to curate and provide data-rich evidence from our unrivalled collections as a global asset for scientific research.
We use our significant global-scale datasets as training data inputs for machine-learning applications. We use our scientific expertise to pose relevant questions, and to interpret and validate results.
We work with data from Kew, our partners and Global Biodiversity Information Facility (GBIF) and the Biodiversity Heritage Library (BHL). Our team's data mining research project uses data from digitised herbarium specimen collections mobilised via the GBIF network and scientific name publication data from the International Plant Names Index.
The products of this data mining research advance data understanding through the development of predictive models, and they are used to facilitate data curation via efficiencies in digitisation and linking allied data.