Delimiting the spatio-temporal uncertainty of climate-sensitive forest productivity projections using Support Vector Regression

As climate change makes many traditional empirical growth approaches not functional for forest dynamics modelling, new climate-sensitive models are needed. However, using these newly developed models for extrapolation, such as predicting forest productivity for new areas or future scenarios is still...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	M.A. González-Rodríguez, U. Diéguez-Aranda
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Pinus radiata Site index Extrapolation Machine learning Climate change Forest growth Ecology QH540-549.5
Acceso en línea:	https://doaj.org/article/ff2b1272137b403392d607f03446971b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ff2b1272137b403392d607f03446971b
record_format	dspace
spelling	oai:doaj.org-article:ff2b1272137b403392d607f03446971b2021-12-01T04:53:59ZDelimiting the spatio-temporal uncertainty of climate-sensitive forest productivity projections using Support Vector Regression1470-160X10.1016/j.ecolind.2021.107820https://doaj.org/article/ff2b1272137b403392d607f03446971b2021-09-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S1470160X21004854https://doaj.org/toc/1470-160XAs climate change makes many traditional empirical growth approaches not functional for forest dynamics modelling, new climate-sensitive models are needed. However, using these newly developed models for extrapolation, such as predicting forest productivity for new areas or future scenarios is still a difficult task. In this study, we proposed a method for delimiting the uncertainty of climate-sensitive extrapolations of forest productivity (site index, SI) using the regularisation approach implicit in distance-based Support Vector Regression. As a case study, we predicted forest productivity with a dataset of 165 permanent research plots of radiata pine forests in Galicia (NW of Spain) as a function of bioclimatic variables from the Worldclim 2 raster datasets. The developed model was based on the radial basis kernel and, after calibrating it using cross-validation, produced adequate performance metrics, explaining up to 56% of the site index’ variability. Then, we predicted forest productivity for the Galician territory basing on climate raster maps for current conditions and six future scenarios (using different Global Climate Models) and evaluated the resulting maps by delimiting the surfaces with predictions strongly regressed to the mean. This analysis revealed that the extrapolations for unseen climatic conditions were extremely regularised, even for current climate, being 60–99% of the territory regressed to the observational site index mean. In other words, the validity area delimited for the fitted model was narrow in comparison with the prediction extent. These results imply that the climatic conditions in these areas/scenarios were too different from the training datastet for making reliable predictions, at least under the optimum model setup defined by cross-validation. However, when we reduced the σ parameter, responsible for controlling distance-based regularisation, we observed a noticeable increase in validity area of the model, together with a drop in performance. This fact revealed the existence of a trade–off between highly specific models, with high performance and a small applicability area, and more generalisable models, with a broad validity area but lower performance. We concluded that the tested methodology could be a useful starting point for assessing the spatio-temporal uncertainty of forest productivity predictions in the future.M.A. González-RodríguezU. Diéguez-ArandaElsevierarticlePinus radiataSite indexExtrapolationMachine learningClimate changeForest growthEcologyQH540-549.5ENEcological Indicators, Vol 128, Iss , Pp 107820- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Pinus radiata Site index Extrapolation Machine learning Climate change Forest growth Ecology QH540-549.5
spellingShingle	Pinus radiata Site index Extrapolation Machine learning Climate change Forest growth Ecology QH540-549.5 M.A. González-Rodríguez U. Diéguez-Aranda Delimiting the spatio-temporal uncertainty of climate-sensitive forest productivity projections using Support Vector Regression
description	As climate change makes many traditional empirical growth approaches not functional for forest dynamics modelling, new climate-sensitive models are needed. However, using these newly developed models for extrapolation, such as predicting forest productivity for new areas or future scenarios is still a difficult task. In this study, we proposed a method for delimiting the uncertainty of climate-sensitive extrapolations of forest productivity (site index, SI) using the regularisation approach implicit in distance-based Support Vector Regression. As a case study, we predicted forest productivity with a dataset of 165 permanent research plots of radiata pine forests in Galicia (NW of Spain) as a function of bioclimatic variables from the Worldclim 2 raster datasets. The developed model was based on the radial basis kernel and, after calibrating it using cross-validation, produced adequate performance metrics, explaining up to 56% of the site index’ variability. Then, we predicted forest productivity for the Galician territory basing on climate raster maps for current conditions and six future scenarios (using different Global Climate Models) and evaluated the resulting maps by delimiting the surfaces with predictions strongly regressed to the mean. This analysis revealed that the extrapolations for unseen climatic conditions were extremely regularised, even for current climate, being 60–99% of the territory regressed to the observational site index mean. In other words, the validity area delimited for the fitted model was narrow in comparison with the prediction extent. These results imply that the climatic conditions in these areas/scenarios were too different from the training datastet for making reliable predictions, at least under the optimum model setup defined by cross-validation. However, when we reduced the σ parameter, responsible for controlling distance-based regularisation, we observed a noticeable increase in validity area of the model, together with a drop in performance. This fact revealed the existence of a trade–off between highly specific models, with high performance and a small applicability area, and more generalisable models, with a broad validity area but lower performance. We concluded that the tested methodology could be a useful starting point for assessing the spatio-temporal uncertainty of forest productivity predictions in the future.
format	article
author	M.A. González-Rodríguez U. Diéguez-Aranda
author_facet	M.A. González-Rodríguez U. Diéguez-Aranda
author_sort	M.A. González-Rodríguez
title	Delimiting the spatio-temporal uncertainty of climate-sensitive forest productivity projections using Support Vector Regression
title_short	Delimiting the spatio-temporal uncertainty of climate-sensitive forest productivity projections using Support Vector Regression
title_full	Delimiting the spatio-temporal uncertainty of climate-sensitive forest productivity projections using Support Vector Regression
title_fullStr	Delimiting the spatio-temporal uncertainty of climate-sensitive forest productivity projections using Support Vector Regression
title_full_unstemmed	Delimiting the spatio-temporal uncertainty of climate-sensitive forest productivity projections using Support Vector Regression
title_sort	delimiting the spatio-temporal uncertainty of climate-sensitive forest productivity projections using support vector regression
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/ff2b1272137b403392d607f03446971b
work_keys_str_mv	AT magonzalezrodriguez delimitingthespatiotemporaluncertaintyofclimatesensitiveforestproductivityprojectionsusingsupportvectorregression AT udieguezaranda delimitingthespatiotemporaluncertaintyofclimatesensitiveforestproductivityprojectionsusingsupportvectorregression
_version_	1718405702667468800

Delimiting the spatio-temporal uncertainty of climate-sensitive forest productivity projections using Support Vector Regression

Ejemplares similares