气候变化领域集成服务门户(CCPortal): Drivers of Late Pleistocene human survival and dispersal: an agent-based modeling and machine learning approach

CCPortal

DOI	10.1016/j.quascirev.2019.105867
	Drivers of Late Pleistocene human survival and dispersal: an agent-based modeling and machine learning approach
	R. Vahdati A.; Weissmann J.D.; Timmermann A.; Ponce de León M.S.; Zollikofer C.P.E.
发表日期	2019
ISSN	0277-3791
卷号	221
英文摘要	Understanding Late Pleistocene human dispersals from Africa requires understanding a multifaceted problem with factors varying in space and time, such as climate, ecology, human behavior, and population dynamics. To understand how these factors interact to affect human survival and dispersal, we have developed a realistic agent-based model that includes geographic features, climate change, and time-varying vegetation and food resources. To enhance computational efficiency, we further apply machine learning algorithms. Our approach is new in that it is designed to systematically evaluate a large-scale agent-based model, and identify its key parameters and sensitivities. Results show that parameter interactions are the major source in generating variability in human dispersal and survival/extinction scenarios. In realistic scenarios with geographical features and time-evolving climatic conditions, random fluctuations become a major source of variability in arrival times and success. Furthermore, parameter settings as different as 92% of maximum possible difference, and occupying more than 30% of parameter space can result in similar dispersal scenarios. This suggests that historical contingency (similar causes – different effects) and equifinality (different causes – similar effects) are primary constituents of human dispersal scenarios. While paleoanthropology, archaeology and paleogenetics now provide insights into patterns of human dispersals at an unprecedented level of detail, elucidating the causes underlying these patterns remains a major challenge. © 2019 Elsevier Ltd
英文关键词	Climate dynamics; Data analysis; Data treatment; Global; Human dispersal; Machine learning; Model validation; Out of Africa; Paleogeography; Pleistocene; Sensitivity analysis
语种	英语
scopus关键词	Autonomous agents; Behavioral research; Climate change; Climate models; Computational efficiency; Data reduction; Learning algorithms; Learning systems; Sensitivity analysis; Simulation platform; Climate dynamics; Data treatment; Global; Human dispersal; Model validation; Out of Africa; Paleogeography; Pleistocene; Machine learning; anthropology; climate conditions; data assimilation; dispersal; extinction; global change; human evolution; individual-based model; machine learning; model validation; paleogeography; Pleistocene; sensitivity analysis; survival; Africa
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/151775
作者单位	Department of Anthropology, University of Zurich, Zurich, Switzerland; Pusan National University, Pusan, South Korea; Center for Climate Physics, Institute for Basic Science, Busan, South Korea
推荐引用方式 GB/T 7714	R. Vahdati A.,Weissmann J.D.,Timmermann A.,et al. Drivers of Late Pleistocene human survival and dispersal: an agent-based modeling and machine learning approach[J],2019,221.
APA	R. Vahdati A.,Weissmann J.D.,Timmermann A.,Ponce de León M.S.,&Zollikofer C.P.E..(2019).Drivers of Late Pleistocene human survival and dispersal: an agent-based modeling and machine learning approach.Quaternary Science Reviews,221.
MLA	R. Vahdati A.,et al."Drivers of Late Pleistocene human survival and dispersal: an agent-based modeling and machine learning approach".Quaternary Science Reviews 221(2019).