Random Forest Development and Modeling of Gross Primary Productivity in the Hudson Bay Lowlands
Peatlands are a critical component of the global carbon cycle. Within Canada, the Hudson Bay Lowlands (HBL) has accumulated an estimated 33 Gt of carbon as peat because of a small but persistent difference between gross primary productivity (GPP) and ecosystem respiration over millennia. However, th...
Published in: | Canadian Journal of Remote Sensing |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English French |
Published: |
Taylor & Francis Group
2024
|
Subjects: | |
Online Access: | https://doi.org/10.1080/07038992.2024.2355937 https://doaj.org/article/7b6345a476a041389b4debe879b573fe |
id |
ftdoajarticles:oai:doaj.org/article:7b6345a476a041389b4debe879b573fe |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:7b6345a476a041389b4debe879b573fe 2024-09-15T18:11:02+00:00 Random Forest Development and Modeling of Gross Primary Productivity in the Hudson Bay Lowlands Jason Beaver Elyn R. Humphreys Douglas King 2024-12-01T00:00:00Z https://doi.org/10.1080/07038992.2024.2355937 https://doaj.org/article/7b6345a476a041389b4debe879b573fe EN FR eng fre Taylor & Francis Group http://dx.doi.org/10.1080/07038992.2024.2355937 https://doaj.org/toc/1712-7971 1712-7971 doi:10.1080/07038992.2024.2355937 https://doaj.org/article/7b6345a476a041389b4debe879b573fe Canadian Journal of Remote Sensing, Vol 50, Iss 1 (2024) Environmental sciences GE1-350 Technology T article 2024 ftdoajarticles https://doi.org/10.1080/07038992.2024.2355937 2024-08-05T17:49:16Z Peatlands are a critical component of the global carbon cycle. Within Canada, the Hudson Bay Lowlands (HBL) has accumulated an estimated 33 Gt of carbon as peat because of a small but persistent difference between gross primary productivity (GPP) and ecosystem respiration over millennia. However, the impacts of disturbance and climate change on GPP are difficult to monitor across the HBL due to its vast size and remote location. This study evaluates the potential for random forest regression models to estimate GPP at five HBL eddy covariance flux monitoring sites using only optical data from MODIS (500 m, 8 day) or harmonized Landsat/Sentinel (HLS; 30 m, 16 day or more frequent). The results show that spatial resolution has less impact on modeled daily GPP compared to temporal resolution across model configurations. Using MODIS data, individual sites’ daily GPP could be simulated with minimal bias, R2 up to 0.89 and mean absolute error as low as 0.37 g C m−2 day−1. For annual GPP, MODIS (R2 = 0.84; mean absolute error 40.5 g C m−2 year−1) also outperformed the HLS models (R2 = 0.46; mean absolute error 86.4 g C m−2 year−1). Article in Journal/Newspaper Hudson Bay Directory of Open Access Journals: DOAJ Articles Canadian Journal of Remote Sensing 50 1 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English French |
topic |
Environmental sciences GE1-350 Technology T |
spellingShingle |
Environmental sciences GE1-350 Technology T Jason Beaver Elyn R. Humphreys Douglas King Random Forest Development and Modeling of Gross Primary Productivity in the Hudson Bay Lowlands |
topic_facet |
Environmental sciences GE1-350 Technology T |
description |
Peatlands are a critical component of the global carbon cycle. Within Canada, the Hudson Bay Lowlands (HBL) has accumulated an estimated 33 Gt of carbon as peat because of a small but persistent difference between gross primary productivity (GPP) and ecosystem respiration over millennia. However, the impacts of disturbance and climate change on GPP are difficult to monitor across the HBL due to its vast size and remote location. This study evaluates the potential for random forest regression models to estimate GPP at five HBL eddy covariance flux monitoring sites using only optical data from MODIS (500 m, 8 day) or harmonized Landsat/Sentinel (HLS; 30 m, 16 day or more frequent). The results show that spatial resolution has less impact on modeled daily GPP compared to temporal resolution across model configurations. Using MODIS data, individual sites’ daily GPP could be simulated with minimal bias, R2 up to 0.89 and mean absolute error as low as 0.37 g C m−2 day−1. For annual GPP, MODIS (R2 = 0.84; mean absolute error 40.5 g C m−2 year−1) also outperformed the HLS models (R2 = 0.46; mean absolute error 86.4 g C m−2 year−1). |
format |
Article in Journal/Newspaper |
author |
Jason Beaver Elyn R. Humphreys Douglas King |
author_facet |
Jason Beaver Elyn R. Humphreys Douglas King |
author_sort |
Jason Beaver |
title |
Random Forest Development and Modeling of Gross Primary Productivity in the Hudson Bay Lowlands |
title_short |
Random Forest Development and Modeling of Gross Primary Productivity in the Hudson Bay Lowlands |
title_full |
Random Forest Development and Modeling of Gross Primary Productivity in the Hudson Bay Lowlands |
title_fullStr |
Random Forest Development and Modeling of Gross Primary Productivity in the Hudson Bay Lowlands |
title_full_unstemmed |
Random Forest Development and Modeling of Gross Primary Productivity in the Hudson Bay Lowlands |
title_sort |
random forest development and modeling of gross primary productivity in the hudson bay lowlands |
publisher |
Taylor & Francis Group |
publishDate |
2024 |
url |
https://doi.org/10.1080/07038992.2024.2355937 https://doaj.org/article/7b6345a476a041389b4debe879b573fe |
genre |
Hudson Bay |
genre_facet |
Hudson Bay |
op_source |
Canadian Journal of Remote Sensing, Vol 50, Iss 1 (2024) |
op_relation |
http://dx.doi.org/10.1080/07038992.2024.2355937 https://doaj.org/toc/1712-7971 1712-7971 doi:10.1080/07038992.2024.2355937 https://doaj.org/article/7b6345a476a041389b4debe879b573fe |
op_doi |
https://doi.org/10.1080/07038992.2024.2355937 |
container_title |
Canadian Journal of Remote Sensing |
container_volume |
50 |
container_issue |
1 |
_version_ |
1810448640997588992 |