Predicting fish weight using photographic image analysis: a case study of broad whitefish in the lower Mackenzie River watershed
Many small-scale fisheries are remote in nature, making data collection logistically difficult. Thus, there is a need for accessible solutions that address the data gaps present in these fisheries. One possible solution is to incorporate photography into community- or harvest-based monitoring framew...
Published in: | Arctic Science |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English French |
Published: |
Canadian Science Publishing
2022
|
Subjects: | |
Online Access: | https://doi.org/10.1139/as-2021-0017 https://doaj.org/article/661b209444784d63b74dbde36e7b43a0 |
id |
ftdoajarticles:oai:doaj.org/article:661b209444784d63b74dbde36e7b43a0 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:661b209444784d63b74dbde36e7b43a0 2023-05-15T14:23:48+02:00 Predicting fish weight using photographic image analysis: a case study of broad whitefish in the lower Mackenzie River watershed Sarah B. Gutzmann Emma E. Hodgson Douglas Braun Jonathan W. Moore Rachel A. Hovel 2022-12-01T00:00:00Z https://doi.org/10.1139/as-2021-0017 https://doaj.org/article/661b209444784d63b74dbde36e7b43a0 EN FR eng fre Canadian Science Publishing https://cdnsciencepub.com/doi/10.1139/as-2021-0017 https://doaj.org/toc/2368-7460 doi:10.1139/as-2021-0017 2368-7460 https://doaj.org/article/661b209444784d63b74dbde36e7b43a0 Arctic Science, Vol 8, Iss 4, Pp 1356-1361 (2022) image analysis community-based monitoring broad whitefish random forest analysis fisheries monitoring analyse d’image Environmental sciences GE1-350 Environmental engineering TA170-171 article 2022 ftdoajarticles https://doi.org/10.1139/as-2021-0017 2022-12-30T21:13:34Z Many small-scale fisheries are remote in nature, making data collection logistically difficult. Thus, there is a need for accessible solutions that address the data gaps present in these fisheries. One possible solution is to incorporate photography into community- or harvest-based monitoring frameworks and employ these images to estimate biological data. Here, we test this approach using łuk dagaii, or broad whitefish, Coregonus nasus (Pallus, 1776) in the Gwich'in Settlement Area, a remote region in the Mackenzie River system in Canada's Northwest Territories. We used photographs taken by Gwich'in collaborators using a simple, standardized set-up to ask the question: how accurately can weight be estimated from a photo? Using random forest models based on morphometric photograph measurements as well as season and location of harvest, we predicted broad whitefish weight to within 13% of true weight (257 g, for fish weighing an average of 2036 g). The model predictions were well distributed in their residuals for most fish, though we discuss biases at low and high weights. Image analysis is a simple, low cost, and accessible method that may contribute to ongoing, community/harvest-based fishery data collection where fish length (measured) and weight (predicted) can be tracked through time. Article in Journal/Newspaper Arctic Mackenzie river Northwest Territories Directory of Open Access Journals: DOAJ Articles Northwest Territories Mackenzie River Arctic Science |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English French |
topic |
image analysis community-based monitoring broad whitefish random forest analysis fisheries monitoring analyse d’image Environmental sciences GE1-350 Environmental engineering TA170-171 |
spellingShingle |
image analysis community-based monitoring broad whitefish random forest analysis fisheries monitoring analyse d’image Environmental sciences GE1-350 Environmental engineering TA170-171 Sarah B. Gutzmann Emma E. Hodgson Douglas Braun Jonathan W. Moore Rachel A. Hovel Predicting fish weight using photographic image analysis: a case study of broad whitefish in the lower Mackenzie River watershed |
topic_facet |
image analysis community-based monitoring broad whitefish random forest analysis fisheries monitoring analyse d’image Environmental sciences GE1-350 Environmental engineering TA170-171 |
description |
Many small-scale fisheries are remote in nature, making data collection logistically difficult. Thus, there is a need for accessible solutions that address the data gaps present in these fisheries. One possible solution is to incorporate photography into community- or harvest-based monitoring frameworks and employ these images to estimate biological data. Here, we test this approach using łuk dagaii, or broad whitefish, Coregonus nasus (Pallus, 1776) in the Gwich'in Settlement Area, a remote region in the Mackenzie River system in Canada's Northwest Territories. We used photographs taken by Gwich'in collaborators using a simple, standardized set-up to ask the question: how accurately can weight be estimated from a photo? Using random forest models based on morphometric photograph measurements as well as season and location of harvest, we predicted broad whitefish weight to within 13% of true weight (257 g, for fish weighing an average of 2036 g). The model predictions were well distributed in their residuals for most fish, though we discuss biases at low and high weights. Image analysis is a simple, low cost, and accessible method that may contribute to ongoing, community/harvest-based fishery data collection where fish length (measured) and weight (predicted) can be tracked through time. |
format |
Article in Journal/Newspaper |
author |
Sarah B. Gutzmann Emma E. Hodgson Douglas Braun Jonathan W. Moore Rachel A. Hovel |
author_facet |
Sarah B. Gutzmann Emma E. Hodgson Douglas Braun Jonathan W. Moore Rachel A. Hovel |
author_sort |
Sarah B. Gutzmann |
title |
Predicting fish weight using photographic image analysis: a case study of broad whitefish in the lower Mackenzie River watershed |
title_short |
Predicting fish weight using photographic image analysis: a case study of broad whitefish in the lower Mackenzie River watershed |
title_full |
Predicting fish weight using photographic image analysis: a case study of broad whitefish in the lower Mackenzie River watershed |
title_fullStr |
Predicting fish weight using photographic image analysis: a case study of broad whitefish in the lower Mackenzie River watershed |
title_full_unstemmed |
Predicting fish weight using photographic image analysis: a case study of broad whitefish in the lower Mackenzie River watershed |
title_sort |
predicting fish weight using photographic image analysis: a case study of broad whitefish in the lower mackenzie river watershed |
publisher |
Canadian Science Publishing |
publishDate |
2022 |
url |
https://doi.org/10.1139/as-2021-0017 https://doaj.org/article/661b209444784d63b74dbde36e7b43a0 |
geographic |
Northwest Territories Mackenzie River |
geographic_facet |
Northwest Territories Mackenzie River |
genre |
Arctic Mackenzie river Northwest Territories |
genre_facet |
Arctic Mackenzie river Northwest Territories |
op_source |
Arctic Science, Vol 8, Iss 4, Pp 1356-1361 (2022) |
op_relation |
https://cdnsciencepub.com/doi/10.1139/as-2021-0017 https://doaj.org/toc/2368-7460 doi:10.1139/as-2021-0017 2368-7460 https://doaj.org/article/661b209444784d63b74dbde36e7b43a0 |
op_doi |
https://doi.org/10.1139/as-2021-0017 |
container_title |
Arctic Science |
_version_ |
1766296293258297344 |