ODINI – Ocean Data Integration Initiative

University of Haifa

The Ocean Data Integration Initiative

The vastness and complexity of the ocean systems requires oceanographic research to rely on multi-faceted in-situ and remotely-sensed observations, which describe physical, chemical, and biological seawater properties at a given time and place. Over the last century, numerous in-situ and remotely-sensed measurements have been carried out worldwide, resulting in the creation of an increasingly large amount of oceanic data.

The ability to comprehensively utilize the huge amount of available ocean data is currently hindered by the difficulty to integrate different datasets, which is largely done in a time and labor intensive manual manner. The ODINI project is aimed at addressing this challenge by resolving key missing tools and methods currently limiting the automation of the ocean data integration process, covering its three main phases: discover, merge, and evaluate.

Sagi, Lehahn and Bar (2020), Artificial intelligence for ocean science data integration: current state, gaps, and way forward. Elem. Sci. Anth, 8: 21.

Read Article

The Ocean Data Integration Process

In the Discovery phase, the list of possible candidate datasets for the project is compiled.

In the Merge phase, candidate datasets are harmonized semantically, computationally, and geographically to form one large and coherent data-set.

In the Evaluate phase, the results are analyzed to assess quality, coverage, and bias, and appropriate corrections are made to support assertions made over the data.