Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Reconstructing Past Global Vegetation With Random Forest Machine Learning, Sacrificing the Dynamic Response for Robust Results

Lindgren, Amelie LU ; Lu, Zhengyao LU ; Zhang, Qiong and Hugelius, Gustaf (2021) In Journal of Advances in Modeling Earth Systems 13(2).
Abstract

Vegetation is an important component in the Earth system, providing a direct link between the biosphere and atmosphere. As such, a representative vegetation pattern is needed to accurately simulate climate. We attempt to model global vegetation (biomes) with a data-driven approach, to test if this allows us to create robust global and regional vegetation patterns. This not only provides quantitative reconstructions of past vegetation cover as a climate forcing, but also improves our understanding of past land cover-climate interactions which have important implications for the future. By using a Random Forest (RF) machine learning tool, we train the vegetation reconstruction with available biomized pollen data of present and past... (More)

Vegetation is an important component in the Earth system, providing a direct link between the biosphere and atmosphere. As such, a representative vegetation pattern is needed to accurately simulate climate. We attempt to model global vegetation (biomes) with a data-driven approach, to test if this allows us to create robust global and regional vegetation patterns. This not only provides quantitative reconstructions of past vegetation cover as a climate forcing, but also improves our understanding of past land cover-climate interactions which have important implications for the future. By using a Random Forest (RF) machine learning tool, we train the vegetation reconstruction with available biomized pollen data of present and past conditions to produce broad-scale vegetation patterns for the preindustrial (PI), the mid-Holocene (MH, ∼6,000 years ago), and the Last Glacial Maximum (LGM, ∼21,000 years ago). We test the method's robustness by introducing a systematic temperature bias based on existing climate model spread and compare the result with that of LPJ-GUESS, an individual-based dynamic global vegetation model. The results show that the RF approach is able to produce robust patterns for periods and regions well constrained by evidence (the PI and the MH), but fails when evidence is scarce (the LGM). The apparent robustness of this method is achieved at the cost of sacrificing the ability to model dynamic vegetation response to a changing climate.

(Less)
Please use this url to cite or link to this publication:
author
; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Journal of Advances in Modeling Earth Systems
volume
13
issue
2
article number
e2020MS002200
publisher
Wiley-Blackwell
external identifiers
  • scopus:85101506129
ISSN
1942-2466
DOI
10.1029/2020MS002200
language
English
LU publication?
yes
id
e75a657e-3248-41b7-aa19-6c56efc2a721
date added to LUP
2021-12-23 14:54:48
date last changed
2022-04-27 06:55:15
@article{e75a657e-3248-41b7-aa19-6c56efc2a721,
  abstract     = {{<p>Vegetation is an important component in the Earth system, providing a direct link between the biosphere and atmosphere. As such, a representative vegetation pattern is needed to accurately simulate climate. We attempt to model global vegetation (biomes) with a data-driven approach, to test if this allows us to create robust global and regional vegetation patterns. This not only provides quantitative reconstructions of past vegetation cover as a climate forcing, but also improves our understanding of past land cover-climate interactions which have important implications for the future. By using a Random Forest (RF) machine learning tool, we train the vegetation reconstruction with available biomized pollen data of present and past conditions to produce broad-scale vegetation patterns for the preindustrial (PI), the mid-Holocene (MH, ∼6,000 years ago), and the Last Glacial Maximum (LGM, ∼21,000 years ago). We test the method's robustness by introducing a systematic temperature bias based on existing climate model spread and compare the result with that of LPJ-GUESS, an individual-based dynamic global vegetation model. The results show that the RF approach is able to produce robust patterns for periods and regions well constrained by evidence (the PI and the MH), but fails when evidence is scarce (the LGM). The apparent robustness of this method is achieved at the cost of sacrificing the ability to model dynamic vegetation response to a changing climate.</p>}},
  author       = {{Lindgren, Amelie and Lu, Zhengyao and Zhang, Qiong and Hugelius, Gustaf}},
  issn         = {{1942-2466}},
  language     = {{eng}},
  number       = {{2}},
  publisher    = {{Wiley-Blackwell}},
  series       = {{Journal of Advances in Modeling Earth Systems}},
  title        = {{Reconstructing Past Global Vegetation With Random Forest Machine Learning, Sacrificing the Dynamic Response for Robust Results}},
  url          = {{http://dx.doi.org/10.1029/2020MS002200}},
  doi          = {{10.1029/2020MS002200}},
  volume       = {{13}},
  year         = {{2021}},
}