EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting dominant terrestrial biomes at a global scale using machine learning algorithms, climate variable indices, and extreme event indices

Hisashi Sato iD

PLOS One · 2026

DOI: 10.1371/journal.pone.0324107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Hisashi Sato. Beteiligte Einrichtung: Research Institute for Global Change, Japan Agency for Marine-Earth Science and Technology (JAMSTEC), Yokohama, Japan. Hauptthemen laut MEDLINE: Machine Learning, Climate, Ecosystem, Climate Models. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Arctic Challenge for Sustainability II, Arctic Challenge for Sustainability III.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Understanding the global distribution of biomes is essential for biodiversity conservation, climate modeling, and land-use planning. Traditional approaches often summarize climate data into indices, and recent models sometimes include extreme events such as severe droughts or rare cold spells. This study evaluates how the choice of machine learning algorithm, climate data summarization, and extreme climate indices affect the accuracy and robustness of global biome modeling. Four algorithms were tested: random forest (RF), support vector machine (SVM), naive Bayes (NV), and LeNet convolutional neural network (CNN). RF and CNN achieved the highest accuracy, with CNN preferred due to RF’s stronger overfitting. Summarizing climate data into indices reduced accuracy by 1–2%, while adding extreme indices increased accuracy by

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningClimateEcosystemClimate ModelsRandom ForestPrediction AlgorithmsConvolutional Neural NetworksBayes TheoremSupport Vector MachineBiodiversityPredictive Learning ModelsAlgorithmsClassification Algorithms

Autor:innen und Institutionen

  • Research Institute for Global Change, Japan Agency for Marine-Earth Science and Technology (JAMSTEC), Yokohama, Japan.
  • Department of Ecosystem Studies, Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo, Japan.

ORCID-Profile: Hisashi Sato

Förderung

  • Arctic Challenge for Sustainability II
  • Arctic Challenge for Sustainability III

Zitieren

APA

Sato, H. (2026). Predicting dominant terrestrial biomes at a global scale using machine learning algorithms, climate variable indices, and extreme event indices. PLOS One. https://doi.org/10.1371/journal.pone.0324107

Vancouver

Sato H. Predicting dominant terrestrial biomes at a global scale using machine learning algorithms, climate variable indices, and extreme event indices. PLOS One. 2026. doi:10.1371/journal.pone.0324107

BibTeX
@article{Sato2026,
  author = {Sato, Hisashi},
  title = {Predicting dominant terrestrial biomes at a global scale using machine learning algorithms, climate variable indices, and extreme event indices},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0324107}
}
Kostenlos starten →