气候变化领域集成服务门户(CCPortal): Reconstructing past biomes states using machine learning and modern pollen assemblages: A case study from Southern Africa

CCPortal

DOI	10.1016/j.quascirev.2019.03.027
	Reconstructing past biomes states using machine learning and modern pollen assemblages: A case study from Southern Africa
	Sobol M.K.; Scott L.; Finkelstein S.A.
发表日期	2019
ISSN	0277-3791
起始页码	1
结束页码	17
卷号	212
英文摘要	Fossil pollen assemblages can assist in understanding biome responses to global climate change if there is reasonable probability that they represent specific biomes or bioregions. In this paper, we introduce a novel probabilistic presentation of pollen data and biome assignment. We apply a recently developed pollen-based vegetation classification method utilizing supervised machine learning to Southern Africa modern pollen assemblages. We present an updated modern pollen dataset from Southern Africa, linking the sites to previously defined vegetation units and ultimately, we generate probabilistic classification for fossil assemblages to reconstruct past vegetation. The modern pollen dataset (N = 211 sites) represents a long vegetation gradient, from desert to forest biomes, capturing broad climate gradients ranging from arid to subtropical. We validate two models using Random Forest algorithm to classify modern vegetation at different spatial resolutions: subcontinental (biomes) and regional (bioregions). When the modern pollen assemblages (N = 164 sites) are used to predict the vegetation types, the classification models are correct in a number of cases. In our dataset of 164 sites, the classification model correctly classifies pollen assemblages from savanna (91% correct), grassland (87%), and coastal forest (82%) vegetation types, while the best results for classification of regional vegetation are achieved for sub-humid savanna (95%), dry savanna (95%), coastal forest (91%), and wet grassland (90%). We apply the models to a fossil pollen sequence at Wonderkrater in the South African savanna, to reconstruct subcontinental and regional changes in past vegetation states over the last 60 000 years. The most probable vegetation state dominating the region since the Late Pleistocene is sub-humid savanna yet grassland occurred at times associated with high vegetation variability. Within the record, the most frequent and amplified variability in the inferred vegetation states occurred during the transitional phase between the Late Pleistocene and the Holocene. The machine learning approach for reconstructing past vegetation, offers a more complex and nuanced view of past vegetation dynamics and has the potential to support quantitative proxy-based techniques for palaeoclimatic reconstructions. © 2019
英文关键词	Biomes; Data analysis; Holocene; Late Pleistocene; Objective classification; Pollen datasets; Vegetation dynamics; Vegetation reconstructions
语种	英语
scopus关键词	Classification (of information); Climate change; Data reduction; Decision trees; Machine learning; Repair; Supervised learning; Biomes; Holocenes; Late Pleistocene; Pollen datasets; Vegetation dynamics; Vegetation; biome; climate change; climate variation; data set; fossil assemblage; fossil record; global climate; Holocene; machine learning; paleoecology; Pleistocene; Pleistocene-Holocene boundary; pollen; reconstruction; subtropical region; vegetation dynamics; vegetation type; Limpopo; South Africa; Wonderkrater
来源期刊	Quaternary Science Reviews
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/151954
作者单位	Department of Earth Sciences, University of Toronto, 22 Russell St, Toronto, M5S 3B1, Canada; Department of Plant Sciences, University of the Free State, PO Box 339, Bloemfontein, 9300, South Africa
推荐引用方式 GB/T 7714	Sobol M.K.,Scott L.,Finkelstein S.A.. Reconstructing past biomes states using machine learning and modern pollen assemblages: A case study from Southern Africa[J],2019,212.
APA	Sobol M.K.,Scott L.,&Finkelstein S.A..(2019).Reconstructing past biomes states using machine learning and modern pollen assemblages: A case study from Southern Africa.Quaternary Science Reviews,212.
MLA	Sobol M.K.,et al."Reconstructing past biomes states using machine learning and modern pollen assemblages: A case study from Southern Africa".Quaternary Science Reviews 212(2019).