Predicting the spread of invasive marine species with open data and machine learning: Process and Challenges

• One of the world’s most complex marine challenges is the spread of invasive species. Invasive species cause severe harm to marine ecosystems and the people who depend on them, with economic impact alone amounting to several billion dollars annually. Recent advances in data science and artificial intelligence (AI) along with the increasing availability of free marine and other data online are improving the possibility to tackle these challenges. This paper presents the efforts by Ocean Data Factory Sweden (ODF Sweden), a data-driven innovation consortium in Gothenburg, to apply machine learning (ML) to one use case – the prediction of the spread of the Killer Shrimp, or Dikerogammarus Villosus, into the Baltic Sea (Figure 1). We discuss our process to address this use case as well as some reflections on the process and its challenges, in particular when taking into consideration the FAIR (findable, accessible, interoperable and reusable) principles in data science.

Subject headings

NATURVETENSKAP  -- Data- och informationsvetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences (hsv//eng)

NATURVETENSKAP  -- Geovetenskap och miljövetenskap (hsv//swe)

NATURAL SCIENCES  -- Earth and Related Environmental Sciences (hsv//eng)

Publication and Content Type

ref (subject category)

kon (subject category)