Project

A machine learning approach to explain and predict melanosis in Atlantic salmon

Publisher

Supervisor

Location

Greater Copenhagen area

Dark discolorations in salmon (dark spots) fillets are mainly caused by melanin deposits in the flesh. In the production of salmon the presences of these spots is very costly as the fillets become (partially) unusable. Through the past five years, producers of salmon have experienced a substantial increase in the fraction of salmons with dark spots in their production. Up to about 20% of the fish, have dark spots to some extent.

 

Knowledge of how and why these spots occur is scarce. Most of the existing studies look at one (or a few) potential causes at a time, in a controlled environment. Based on historical production data from Cermaq, one of the top three producers of salmon in the world, the student will take a machine leaning (ML) approach to broadening the knowledge of the nature of the dark spots. The student should consider existing hypothesis and how ML could support (or weaken) these. The project should focus on both prediction and interpretation. Finding associations in data that could be subject for future studies and/or could be incorporated in the workflows of Cermaq to reduce the problem.

 

Data from Cermaq database system (Fish Talk) throughout the past approx. 5 years is available. Data from other sources eg relevant weather data could be included.

 

It is the intention to publish the work. The student is encouraged to participate in writing a scientific article after finishing the master.

 

Supervisors:

Associate Professor Line H. Clemmensen, Statistics and Data Analysis Section, DTU Compute, lkhc@dtu.dk

PhD Student Kira Svendsen, Statistics and Data Analysis Section, DTU Compute, kdsv@dtu.dk

In collaboration with

Cermaq Norway, Nofima

Search in postings
Contact

Company / Organization

DTU Compute

Name

Kira Dynnes Svendsen

Position

Ph.d.-studerende

Mail

kdsv@dtu.dk

Supervisor info

MSc in Computer Science and Engineering

Supervisor

Kira Dynnes Svendsen

ECTS credits

30 - 35

Type

MSc thesis

MSc in Digital Media Engineering

Supervisor

Kira Dynnes Svendsen

ECTS credits

30 - 35

Type

MSc thesis

MSc in Mathematical Modelling and Computation

Supervisor

Kira Dynnes Svendsen

ECTS credits

30 - 35

Type

MSc thesis

Technical University of Denmark

For almost two centuries DTU, Technical University of Denmark, has been dedicated to fulfilling the vision of H.C. Ørsted – the father of electromagnetism – who founded the university in 1829 to develop and create value using the natural sciences and the technical sciences to benefit society.


Today, DTU is ranked as one of the foremost technical universities in Europe, continues to set new records in the number of publications, and persistently increases and develops our partnerships with industry, and assignments accomplished by DTU’s public sector consultancy.

Find us here

Anker Engelunds Vej 1
Bygning 101A
2800 Kgs. Lyngby

Denmark



Tlf. (+45) 45 25 25 25

CVR-nr. 30 06 09 46

All vacant positions
 

loading..