New publication: Machine learning-driven mapping of prokaryotic community diversity in the Mediterranean Sea using omics, earth observation, and model data

Researchers from the Marine Biology Station, Piran (National Institue of Biology) have in colaboration with partners from Italy, Spain and France used a machine learning algorithm to model the diversity of prokaryotic communities in the Mediterranean Sea.

Using the Machine Learning algortihm XGBoost trained on omics and model data, the researchers have successfully estimated the Shannon diversity index of prokaryotic communities, extending it from point-based to basin-wide fields.

Photoperiod emerged as the most important parameter in the determining the diversity.

Their model is also transferable to other planktonic communities.

The article is a result of the PETRIMED (link to project website) project and is available online in Ecological informatics: publication link