Biomes of the world under climate change scenarios: increasing aridity and higher temperatures lead to significant shifts in natural vegetation
The global potential distribution of biomes (natural vegetation) was modelled using 8,959 training points from the BIOME 6000 dataset and a stack of 72 environmental covariates representing terrain and the current climatic conditions based on historical long term averages (1979–2013). An ensemble ma...
Published in: | PeerJ |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
PeerJ Inc.
2023
|
Subjects: | |
Online Access: | http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10292195/ http://www.ncbi.nlm.nih.gov/pubmed/37377791 https://doi.org/10.7717/peerj.15593 |
id |
ftpubmed:oai:pubmedcentral.nih.gov:10292195 |
---|---|
record_format |
openpolar |
spelling |
ftpubmed:oai:pubmedcentral.nih.gov:10292195 2023-07-23T04:18:04+02:00 Biomes of the world under climate change scenarios: increasing aridity and higher temperatures lead to significant shifts in natural vegetation Bonannella, Carmelo Hengl, Tomislav Parente, Leandro de Bruin, Sytze 2023-06-23 http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10292195/ http://www.ncbi.nlm.nih.gov/pubmed/37377791 https://doi.org/10.7717/peerj.15593 en eng PeerJ Inc. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10292195/ http://www.ncbi.nlm.nih.gov/pubmed/37377791 http://dx.doi.org/10.7717/peerj.15593 ©2023 Bonannella et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited. PeerJ Biogeography Text 2023 ftpubmed https://doi.org/10.7717/peerj.15593 2023-07-02T00:48:10Z The global potential distribution of biomes (natural vegetation) was modelled using 8,959 training points from the BIOME 6000 dataset and a stack of 72 environmental covariates representing terrain and the current climatic conditions based on historical long term averages (1979–2013). An ensemble machine learning model based on stacked regularization was used, with multinomial logistic regression as the meta-learner and spatial blocking (100 km) to deal with spatial autocorrelation of the training points. Results of spatial cross-validation for the BIOME 6000 classes show an overall accuracy of 0.67 and R(2)(logloss) of 0.61, with “tropical evergreen broadleaf forest” being the class with highest gain in predictive performances (R(2)(logloss) = 0.74) and “prostrate dwarf shrub tundra” the class with the lowest (R(2)(logloss) = −0.09) compared to the baseline. Temperature-related covariates were the most important predictors, with the mean diurnal range (BIO2) being shared by all the base-learners (i.e.,random forest, gradient boosted trees and generalized linear models). The model was next used to predict the distribution of future biomes for the periods 2040–2060 and 2061–2080 under three climate change scenarios (RCP 2.6, 4.5 and 8.5). Comparisons of predictions for the three epochs (present, 2040–2060 and 2061–2080) show that increasing aridity and higher temperatures will likely result in significant shifts in natural vegetation in the tropical area (shifts from tropical forests to savannas up to 1.7 ×10(5) km(2) by 2080) and around the Arctic Circle (shifts from tundra to boreal forests up to 2.4 ×10(5) km(2) by 2080). Projected global maps at 1 km spatial resolution are provided as probability and hard classes maps for BIOME 6000 classes and as hard classes maps for the IUCN classes (six aggregated classes). Uncertainty maps (prediction error) are also provided and should be used for careful interpretation of the future projections. Text Arctic Climate change Tundra PubMed Central (PMC) Arctic PeerJ 11 e15593 |
institution |
Open Polar |
collection |
PubMed Central (PMC) |
op_collection_id |
ftpubmed |
language |
English |
topic |
Biogeography |
spellingShingle |
Biogeography Bonannella, Carmelo Hengl, Tomislav Parente, Leandro de Bruin, Sytze Biomes of the world under climate change scenarios: increasing aridity and higher temperatures lead to significant shifts in natural vegetation |
topic_facet |
Biogeography |
description |
The global potential distribution of biomes (natural vegetation) was modelled using 8,959 training points from the BIOME 6000 dataset and a stack of 72 environmental covariates representing terrain and the current climatic conditions based on historical long term averages (1979–2013). An ensemble machine learning model based on stacked regularization was used, with multinomial logistic regression as the meta-learner and spatial blocking (100 km) to deal with spatial autocorrelation of the training points. Results of spatial cross-validation for the BIOME 6000 classes show an overall accuracy of 0.67 and R(2)(logloss) of 0.61, with “tropical evergreen broadleaf forest” being the class with highest gain in predictive performances (R(2)(logloss) = 0.74) and “prostrate dwarf shrub tundra” the class with the lowest (R(2)(logloss) = −0.09) compared to the baseline. Temperature-related covariates were the most important predictors, with the mean diurnal range (BIO2) being shared by all the base-learners (i.e.,random forest, gradient boosted trees and generalized linear models). The model was next used to predict the distribution of future biomes for the periods 2040–2060 and 2061–2080 under three climate change scenarios (RCP 2.6, 4.5 and 8.5). Comparisons of predictions for the three epochs (present, 2040–2060 and 2061–2080) show that increasing aridity and higher temperatures will likely result in significant shifts in natural vegetation in the tropical area (shifts from tropical forests to savannas up to 1.7 ×10(5) km(2) by 2080) and around the Arctic Circle (shifts from tundra to boreal forests up to 2.4 ×10(5) km(2) by 2080). Projected global maps at 1 km spatial resolution are provided as probability and hard classes maps for BIOME 6000 classes and as hard classes maps for the IUCN classes (six aggregated classes). Uncertainty maps (prediction error) are also provided and should be used for careful interpretation of the future projections. |
format |
Text |
author |
Bonannella, Carmelo Hengl, Tomislav Parente, Leandro de Bruin, Sytze |
author_facet |
Bonannella, Carmelo Hengl, Tomislav Parente, Leandro de Bruin, Sytze |
author_sort |
Bonannella, Carmelo |
title |
Biomes of the world under climate change scenarios: increasing aridity and higher temperatures lead to significant shifts in natural vegetation |
title_short |
Biomes of the world under climate change scenarios: increasing aridity and higher temperatures lead to significant shifts in natural vegetation |
title_full |
Biomes of the world under climate change scenarios: increasing aridity and higher temperatures lead to significant shifts in natural vegetation |
title_fullStr |
Biomes of the world under climate change scenarios: increasing aridity and higher temperatures lead to significant shifts in natural vegetation |
title_full_unstemmed |
Biomes of the world under climate change scenarios: increasing aridity and higher temperatures lead to significant shifts in natural vegetation |
title_sort |
biomes of the world under climate change scenarios: increasing aridity and higher temperatures lead to significant shifts in natural vegetation |
publisher |
PeerJ Inc. |
publishDate |
2023 |
url |
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10292195/ http://www.ncbi.nlm.nih.gov/pubmed/37377791 https://doi.org/10.7717/peerj.15593 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Climate change Tundra |
genre_facet |
Arctic Climate change Tundra |
op_source |
PeerJ |
op_relation |
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10292195/ http://www.ncbi.nlm.nih.gov/pubmed/37377791 http://dx.doi.org/10.7717/peerj.15593 |
op_rights |
©2023 Bonannella et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited. |
op_doi |
https://doi.org/10.7717/peerj.15593 |
container_title |
PeerJ |
container_volume |
11 |
container_start_page |
e15593 |
_version_ |
1772180203583307776 |