Forecasting mussel settlement using historical data and boosted regression trees
Many aquaculture sectors internationally, most notably for the cultivation of bivalves, rely almost completely on wild-caught juveniles (‘spat’) to stock farms, with poor ‘catches’ representing one the biggest constraints on global production. An example of this practice is green-lipped mussel Perna...
Published in: | Aquaculture Environment Interactions |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Inter-Research
2019
|
Subjects: | |
Online Access: | https://doi.org/10.3354/aei00337 https://doaj.org/article/13ebc91676e648408b0349adb2b9863e |
id |
ftdoajarticles:oai:doaj.org/article:13ebc91676e648408b0349adb2b9863e |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:13ebc91676e648408b0349adb2b9863e 2023-05-15T18:25:43+02:00 Forecasting mussel settlement using historical data and boosted regression trees Atalah, J Forrest, BM 2019-12-01T00:00:00Z https://doi.org/10.3354/aei00337 https://doaj.org/article/13ebc91676e648408b0349adb2b9863e EN eng Inter-Research https://www.int-res.com/abstracts/aei/v11/p625-638/ https://doaj.org/toc/1869-215X https://doaj.org/toc/1869-7534 1869-215X 1869-7534 doi:10.3354/aei00337 https://doaj.org/article/13ebc91676e648408b0349adb2b9863e Aquaculture Environment Interactions, Vol 11, Pp 625-638 (2019) Aquaculture. Fisheries. Angling SH1-691 Ecology QH540-549.5 article 2019 ftdoajarticles https://doi.org/10.3354/aei00337 2022-12-30T23:10:51Z Many aquaculture sectors internationally, most notably for the cultivation of bivalves, rely almost completely on wild-caught juveniles (‘spat’) to stock farms, with poor ‘catches’ representing one the biggest constraints on global production. An example of this practice is green-lipped mussel Perna canaliculus aquaculture in New Zealand, where the industry in the main growing region has been monitoring P. canaliculus settlement for almost 40 yr. This practice involves deploying settlement arrays across the region to guide the places and times to place spat-catching rope. Using a subset of these data spanning 25 yr (1993-2018), we identified regional spatio-temporal patterns of P. canaliculus spat settlement. Boosted regression tree (BRT) models were used to forecast settlement at 2 different sub-regions with consistent high catch yields. BRT models confirmed a strong seasonal influence on settlement, with highest predicted settlement levels coinciding with the main P. canaliculus spawning period (late summer to autumn). Positive relationships were detected between settlement and the occurrence of positive temperature anomalies, easterly winds, periods of large tidal range and Southern Ocean Oscillation Index values associated with La Niña episodes. The models were able to forecast P. canaliculus settlement with excellent prediction accuracy based on time of year and environmental conditions 1 mo prior to collection. This study highlights the benefit of undertaking long-term monitoring of spat settlement and the related environmental factors that affect this ecological process. In combination with advance modelling techniques that enable forecasting of settlement densities, such knowledge can help to overcome challenges in spat supply and enable production upscaling. Article in Journal/Newspaper Southern Ocean Directory of Open Access Journals: DOAJ Articles Southern Ocean New Zealand Aquaculture Environment Interactions 11 625 638 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Aquaculture. Fisheries. Angling SH1-691 Ecology QH540-549.5 |
spellingShingle |
Aquaculture. Fisheries. Angling SH1-691 Ecology QH540-549.5 Atalah, J Forrest, BM Forecasting mussel settlement using historical data and boosted regression trees |
topic_facet |
Aquaculture. Fisheries. Angling SH1-691 Ecology QH540-549.5 |
description |
Many aquaculture sectors internationally, most notably for the cultivation of bivalves, rely almost completely on wild-caught juveniles (‘spat’) to stock farms, with poor ‘catches’ representing one the biggest constraints on global production. An example of this practice is green-lipped mussel Perna canaliculus aquaculture in New Zealand, where the industry in the main growing region has been monitoring P. canaliculus settlement for almost 40 yr. This practice involves deploying settlement arrays across the region to guide the places and times to place spat-catching rope. Using a subset of these data spanning 25 yr (1993-2018), we identified regional spatio-temporal patterns of P. canaliculus spat settlement. Boosted regression tree (BRT) models were used to forecast settlement at 2 different sub-regions with consistent high catch yields. BRT models confirmed a strong seasonal influence on settlement, with highest predicted settlement levels coinciding with the main P. canaliculus spawning period (late summer to autumn). Positive relationships were detected between settlement and the occurrence of positive temperature anomalies, easterly winds, periods of large tidal range and Southern Ocean Oscillation Index values associated with La Niña episodes. The models were able to forecast P. canaliculus settlement with excellent prediction accuracy based on time of year and environmental conditions 1 mo prior to collection. This study highlights the benefit of undertaking long-term monitoring of spat settlement and the related environmental factors that affect this ecological process. In combination with advance modelling techniques that enable forecasting of settlement densities, such knowledge can help to overcome challenges in spat supply and enable production upscaling. |
format |
Article in Journal/Newspaper |
author |
Atalah, J Forrest, BM |
author_facet |
Atalah, J Forrest, BM |
author_sort |
Atalah, J |
title |
Forecasting mussel settlement using historical data and boosted regression trees |
title_short |
Forecasting mussel settlement using historical data and boosted regression trees |
title_full |
Forecasting mussel settlement using historical data and boosted regression trees |
title_fullStr |
Forecasting mussel settlement using historical data and boosted regression trees |
title_full_unstemmed |
Forecasting mussel settlement using historical data and boosted regression trees |
title_sort |
forecasting mussel settlement using historical data and boosted regression trees |
publisher |
Inter-Research |
publishDate |
2019 |
url |
https://doi.org/10.3354/aei00337 https://doaj.org/article/13ebc91676e648408b0349adb2b9863e |
geographic |
Southern Ocean New Zealand |
geographic_facet |
Southern Ocean New Zealand |
genre |
Southern Ocean |
genre_facet |
Southern Ocean |
op_source |
Aquaculture Environment Interactions, Vol 11, Pp 625-638 (2019) |
op_relation |
https://www.int-res.com/abstracts/aei/v11/p625-638/ https://doaj.org/toc/1869-215X https://doaj.org/toc/1869-7534 1869-215X 1869-7534 doi:10.3354/aei00337 https://doaj.org/article/13ebc91676e648408b0349adb2b9863e |
op_doi |
https://doi.org/10.3354/aei00337 |
container_title |
Aquaculture Environment Interactions |
container_volume |
11 |
container_start_page |
625 |
op_container_end_page |
638 |
_version_ |
1766207335562215424 |