KNIME AG and Harvard’s Center for Geographic Analysis have launched a joint project to advance spatial data science. The project is part of the Spatiotemporal Thinking, Computing, and Applications (STC) Center which is funded by the NSF to enable pre-competitive research in partnerships among industry, academia, and government. The two-year project “Developing Workbenches for Spatial Data Science (HVD-21-07)” will explore methodologies to advance spatial data science research and teaching. To open up spatial analytics to a more diverse group of users, the partners will develop freely accessible KNIME Analytics Platform extensions for spatial statistics, modeling, and visualization. KNIME’s visual, no-code/low-code environment will enable multi-discipline users to more easily and efficiently collaborate, explore data, and surface insights. Further resources in the form of workbooks, workflow-based case studies, and best-practice workflows will be developed to help users get started with replicable and reproducible spatial data science across scientific disciplines.
The Center for Geographic Analysis (CGA), which works with entities across Harvard, strengthens university-wide geographic information systems (GIS) infrastructure and services. It provides a common platform for the integration of spatial data from diverse sources and knowledge from multiple disciplines and enables scholarly research that uses, improves, or studies geospatial analysis techniques. In addition, the CGA improves the teaching of GIS and geospatial data science at all levels across the University.
KNIME AG is an international company with offices in Zurich, Berlin, Konstanz, Austin, and online. Its KNIME Analytics Platform, an open-source software for creating data science, is intuitive, open, and continuously integrating new developments, making understanding data and designing data science workflows and reusable components accessible to everyone. KNIME has successfully demonstrated in past research projects that visual workflows are a central part of making data science accessible across disciplines.