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...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2023-06-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/15593.pdf |
| _version_ | 1827607452771680256 |
|---|---|
| author | Carmelo Bonannella Tomislav Hengl Leandro Parente Sytze de Bruin |
| author_facet | Carmelo Bonannella Tomislav Hengl Leandro Parente Sytze de Bruin |
| author_sort | Carmelo Bonannella |
| collection | DOAJ |
| 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 R2logloss of 0.61, with “tropical evergreen broadleaf forest” being the class with highest gain in predictive performances (R2logloss = 0.74) and “prostrate dwarf shrub tundra” the class with the lowest (R2logloss = −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 ×105 km2 by 2080) and around the Arctic Circle (shifts from tundra to boreal forests up to 2.4 ×105 km2 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. |
| first_indexed | 2024-03-09T06:54:15Z |
| format | Article |
| id | doaj.art-8873706227a141a0a44ed0c743a2945e |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T06:54:15Z |
| publishDate | 2023-06-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-8873706227a141a0a44ed0c743a2945e2023-12-03T10:10:52ZengPeerJ Inc.PeerJ2167-83592023-06-0111e1559310.7717/peerj.15593Biomes of the world under climate change scenarios: increasing aridity and higher temperatures lead to significant shifts in natural vegetationCarmelo Bonannella0Tomislav Hengl1Leandro Parente2Sytze de Bruin3Laboratory of Geo-Information Science and Remote Sensing, Wageningen University and Research, Wageningen, NetherlandsOpenGeoHub Foundation, Wageningen, NetherlandsOpenGeoHub Foundation, Wageningen, NetherlandsLaboratory of Geo-Information Science and Remote Sensing, Wageningen University and Research, Wageningen, NetherlandsThe 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 R2logloss of 0.61, with “tropical evergreen broadleaf forest” being the class with highest gain in predictive performances (R2logloss = 0.74) and “prostrate dwarf shrub tundra” the class with the lowest (R2logloss = −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 ×105 km2 by 2080) and around the Arctic Circle (shifts from tundra to boreal forests up to 2.4 ×105 km2 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.https://peerj.com/articles/15593.pdfClimate changeBiomesRCP scenariosMachine learningEnsemble modeling |
| spellingShingle | Carmelo Bonannella Tomislav Hengl Leandro Parente Sytze de Bruin Biomes of the world under climate change scenarios: increasing aridity and higher temperatures lead to significant shifts in natural vegetation PeerJ Climate change Biomes RCP scenarios Machine learning Ensemble modeling |
| title | 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_short | 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 |
| topic | Climate change Biomes RCP scenarios Machine learning Ensemble modeling |
| url | https://peerj.com/articles/15593.pdf |
| work_keys_str_mv | AT carmelobonannella biomesoftheworldunderclimatechangescenariosincreasingaridityandhighertemperaturesleadtosignificantshiftsinnaturalvegetation AT tomislavhengl biomesoftheworldunderclimatechangescenariosincreasingaridityandhighertemperaturesleadtosignificantshiftsinnaturalvegetation AT leandroparente biomesoftheworldunderclimatechangescenariosincreasingaridityandhighertemperaturesleadtosignificantshiftsinnaturalvegetation AT sytzedebruin biomesoftheworldunderclimatechangescenariosincreasingaridityandhighertemperaturesleadtosignificantshiftsinnaturalvegetation |