N EAR F UTURE P ELAGIC C ATCH P LANNING Brd Johan Hanssen - SINTEF - - PowerPoint PPT Presentation

This document is part of a project that has received funding from the European Union’s Horizon 2020 research and innovation programme under agreement No 732064. It is the property of the DataBio consortium and shall not be distributed or reproduced without the formal approval of the DataBio Management Committee. Find us at www.databio.eu.

1 This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 732064 This project is part

• f BDV PPP

TEAM CLP CLP- DECISION SUPPORT SYSTEM FOR NEAR FUTURE PELAGIC CATCH PLANNING

Bård Johan Hanssen - SINTEF Nord Peter Halland Haro - SINTEF Digital Per Gunnar Auran - SINTEF Ocean Pekka Kotilainen - SYKE MRC Ahmet Bilici - PROMATECH EMODnet OpenSeaLab Hackathon Antwerp, 17th November 2017

This document is part of a project that has received funding from the European Union’s Horizon 2020 research and innovation programme under agreement No 732064. It is the property of the DataBio consortium and shall not be distributed or reproduced without the formal approval of the DataBio Management Committee. Find us at www.databio.eu.

2

Project Context - DataBio WP3 – Fishery pilots + other related projects in our portifolio

Optimization of … … through utilization of Big Data Technology (48 international partners)

Essential value chain driver: Where to fish what when?

This document is part of a project that has received funding from the European Union’s Horizon 2020 research and innovation programme under agreement No 732064. It is the property of the DataBio consortium and shall not be distributed or reproduced without the formal approval of the DataBio Management Committee. Find us at www.databio.eu.

3

TEAM CLP – What & how?

Where is the fish likely to be? p(x,y,z,t | species) Knowledge transfer synergy:

• Feature strength & importance)
• Detailed data for f(x,y,z,t) - training

Physical Modeling – long term (SINTEF: 1970s -2010s) Machine Learning – Now (demo) Deep learning NN of catch probability:

• High catch probability heatmap
• Black box model trained on
• catch data
• physics, chemistry ++

This document is part of a project that has received funding from the European Union’s Horizon 2020 research and innovation programme under agreement No 732064. It is the property of the DataBio consortium and shall not be distributed or reproduced without the formal approval of the DataBio Management Committee. Find us at www.databio.eu.

4

TEAM CLP – Why? – Most rele levant busin iness vie iew from C2 pilo ilot

Stakeholders Business goals & supporting processes Big Data analytics Catch & Market data

This document is part of a project that has received funding from the European Union’s Horizon 2020 research and innovation programme under agreement No 732064. It is the property of the DataBio consortium and shall not be distributed or reproduced without the formal approval of the DataBio Management Committee. Find us at www.databio.eu.

5

Thank you for your attention!

Team CLP & Partners in SINTEF & DataBio Contact persons :

• {peter.haro|bard.hanssen|per.gunnar.auran}@sintef.no

This document is part of a project that has received funding from the European Union’s Horizon 2020 research and innovation programme under agreement No 732064. It is the property of the DataBio consortium and shall not be distributed or reproduced without the formal approval of the DataBio Management Committee. Find us at www.databio.eu.

6

DataBio WP3 – Fishery pilots – big picture elements