Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species
The effect of different factors (spawning biomass, environmental conditions) on recruitment is a subject of great importance in the management of fisheries, recovery plans and scenario exploration. In this study, recently proposed supervised classification techniques, tested by the machine-learning...
Published in: | Ecological Informatics |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
2015
|
Subjects: | |
Online Access: | http://plymsea.ac.uk/id/eprint/6863/ https://doi.org/10.1016/j.ecoinf.2014.11.004 |
id |
ftplymouthml:oai:plymsea.ac.uk:6863 |
---|---|
record_format |
openpolar |
spelling |
ftplymouthml:oai:plymsea.ac.uk:6863 2023-05-15T17:38:19+02:00 Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species Fernandes, JA Irigoien, X Lozano, JA Inza, I Goikoetxea, N Pérez, A 2015-01-03 http://plymsea.ac.uk/id/eprint/6863/ https://doi.org/10.1016/j.ecoinf.2014.11.004 unknown Fernandes, JA; Irigoien, X; Lozano, JA; Inza, I; Goikoetxea, N; Pérez, A. 2015 Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species. Ecological Informatics, 25. 35-42. https://doi.org/10.1016/j.ecoinf.2014.11.004 <https://doi.org/10.1016/j.ecoinf.2014.11.004> Biology Computer Science Data and Information Ecology and Environment Fisheries Management Marine Sciences Meteorology and Climatology Oceanography Planning Policies Technology Publication - Article PeerReviewed 2015 ftplymouthml https://doi.org/10.1016/j.ecoinf.2014.11.004 2022-09-13T05:48:45Z The effect of different factors (spawning biomass, environmental conditions) on recruitment is a subject of great importance in the management of fisheries, recovery plans and scenario exploration. In this study, recently proposed supervised classification techniques, tested by the machine-learning community, are applied to forecast the recruitment of seven fish species of North East Atlantic (anchovy, sardine, mackerel, horse mackerel, hake, blue whiting and albacore), using spawning, environmental and climatic data. In addition, the use of the probabilistic flexible naive Bayes classifier (FNBC) is proposed as modelling approach in order to reduce uncertainty for fisheries management purposes. Those improvements aim is to improve probability estimations of each possible outcome (low, medium and high recruitment) based in kernel density estimation, which is crucial for informed management decision making with high uncertainty. Finally, a comparison between goodness-of-fit and generalization power is provided, in order to assess the reliability of the final forecasting models. It is found that in most cases the proposed methodology provides useful information for management whereas the case of horse mackerel is an example of the limitations of the approach. The proposed improvements allow for a better probabilistic estimation of the different scenarios, i.e. to reduce the uncertainty in the provided forecasts. Article in Journal/Newspaper North East Atlantic Plymouth Marine Science Electronic Archive (PlyMSEA - Plymouth Marine Laboratory, PML) Hake ENVELOPE(15.612,15.612,66.797,66.797) Ecological Informatics 25 35 42 |
institution |
Open Polar |
collection |
Plymouth Marine Science Electronic Archive (PlyMSEA - Plymouth Marine Laboratory, PML) |
op_collection_id |
ftplymouthml |
language |
unknown |
topic |
Biology Computer Science Data and Information Ecology and Environment Fisheries Management Marine Sciences Meteorology and Climatology Oceanography Planning Policies Technology |
spellingShingle |
Biology Computer Science Data and Information Ecology and Environment Fisheries Management Marine Sciences Meteorology and Climatology Oceanography Planning Policies Technology Fernandes, JA Irigoien, X Lozano, JA Inza, I Goikoetxea, N Pérez, A Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species |
topic_facet |
Biology Computer Science Data and Information Ecology and Environment Fisheries Management Marine Sciences Meteorology and Climatology Oceanography Planning Policies Technology |
description |
The effect of different factors (spawning biomass, environmental conditions) on recruitment is a subject of great importance in the management of fisheries, recovery plans and scenario exploration. In this study, recently proposed supervised classification techniques, tested by the machine-learning community, are applied to forecast the recruitment of seven fish species of North East Atlantic (anchovy, sardine, mackerel, horse mackerel, hake, blue whiting and albacore), using spawning, environmental and climatic data. In addition, the use of the probabilistic flexible naive Bayes classifier (FNBC) is proposed as modelling approach in order to reduce uncertainty for fisheries management purposes. Those improvements aim is to improve probability estimations of each possible outcome (low, medium and high recruitment) based in kernel density estimation, which is crucial for informed management decision making with high uncertainty. Finally, a comparison between goodness-of-fit and generalization power is provided, in order to assess the reliability of the final forecasting models. It is found that in most cases the proposed methodology provides useful information for management whereas the case of horse mackerel is an example of the limitations of the approach. The proposed improvements allow for a better probabilistic estimation of the different scenarios, i.e. to reduce the uncertainty in the provided forecasts. |
format |
Article in Journal/Newspaper |
author |
Fernandes, JA Irigoien, X Lozano, JA Inza, I Goikoetxea, N Pérez, A |
author_facet |
Fernandes, JA Irigoien, X Lozano, JA Inza, I Goikoetxea, N Pérez, A |
author_sort |
Fernandes, JA |
title |
Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species |
title_short |
Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species |
title_full |
Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species |
title_fullStr |
Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species |
title_full_unstemmed |
Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species |
title_sort |
evaluating machine-learning techniques for recruitment forecasting of seven north east atlantic fish species |
publishDate |
2015 |
url |
http://plymsea.ac.uk/id/eprint/6863/ https://doi.org/10.1016/j.ecoinf.2014.11.004 |
long_lat |
ENVELOPE(15.612,15.612,66.797,66.797) |
geographic |
Hake |
geographic_facet |
Hake |
genre |
North East Atlantic |
genre_facet |
North East Atlantic |
op_relation |
Fernandes, JA; Irigoien, X; Lozano, JA; Inza, I; Goikoetxea, N; Pérez, A. 2015 Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species. Ecological Informatics, 25. 35-42. https://doi.org/10.1016/j.ecoinf.2014.11.004 <https://doi.org/10.1016/j.ecoinf.2014.11.004> |
op_doi |
https://doi.org/10.1016/j.ecoinf.2014.11.004 |
container_title |
Ecological Informatics |
container_volume |
25 |
container_start_page |
35 |
op_container_end_page |
42 |
_version_ |
1766138711245848576 |