SUPR
Aquaculture breeding using machine learning
Dnr:

NAISS 2024/22-958

Type:

NAISS Small Compute

Principal Investigator:

Christos Palaiokostas

Affiliation:

Sveriges lantbruksuniversitet

Start Date:

2024-07-01

End Date:

2025-07-01

Primary Classification:

40201: Animal and Dairy Science.

Webpage:

Allocation

Abstract

Currently, I am an Associate Professor in the Department of Animal Breeding and Genetics at the Swedish University of Agricultural sciences (SLU). My research focusses on improving key production traits in farmed fish using selective breeding practices in genomic datasets. In the current project, will evaluate the efficiency of several machine learning models (e.g XGBoost, random forests, support vector machines and deep learning models) for selective breeding purposes in large aquaculture datasets, genotyped at varying densities. It should be stressed that limited work has been conducted so far regarding the efficiency of machine learning models for aquaculture breeding. The intended work will be a continuation of my recently published article: https://www.sciencedirect.com/science/article/pii/S2352513421000764 The state of the art HPC resources from SNIC would provide me with the necessary tools for conducting research that could I expect to be of value for the aquaculture industry.