气候变化领域集成服务门户(CCPortal): Towards robust statistical inference for complex computer models

CCPortal

DOI	10.1111/ele.13728
	Towards robust statistical inference for complex computer models
	Oberpriller J.; Cameron D.R.; Dietze M.C.; Hartig F.
发表日期	2021
ISSN	1461023X
起始页码	1251
结束页码	1261
卷号	24 期号:6
英文摘要	Ecologists increasingly rely on complex computer simulations to forecast ecological systems. To make such forecasts precise, uncertainties in model parameters and structure must be reduced and correctly propagated to model outputs. Naively using standard statistical techniques for this task, however, can lead to bias and underestimation of uncertainties in parameters and predictions. Here, we explain why these problems occur and propose a framework for robust inference with complex computer simulations. After having identified that model error is more consequential in complex computer simulations, due to their more pronounced nonlinearity and interconnectedness, we discuss as possible solutions data rebalancing and adding bias corrections on model outputs or processes during or after the calibration procedure. We illustrate the methods in a case study, using a dynamic vegetation model. We conclude that developing better methods for robust inference of complex computer simulations is vital for generating reliable predictions of ecosystem responses. © 2021 The Authors. Ecology Letters published by John Wiley & Sons Ltd.
关键词	Bayesian Inference bias correction biased models data imbalance robust inference
英文关键词	calibration; complexity; computer simulation; correction; ecosystem response; nonlinearity; precision; uncertainty analysis; Bayes theorem; computer simulation; ecosystem; forecasting; statistical model; uncertainty; Bayes Theorem; Computer Simulation; Ecosystem; Forecasting; Models, Statistical; Uncertainty
语种	英语
来源期刊	Ecology Letters
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/204462
作者单位	Theoretical Ecology, University of Regensburg, Universitätsstraße 31, Regensburg, 93053, Germany; UK Centre for Ecology & Hydrology, Bush Estate, Penicuik, Midlothian EH260QB, United Kingdom; Department of Earth & Environment, Boston University, Boston, MA, United States
推荐引用方式 GB/T 7714	Oberpriller J.,Cameron D.R.,Dietze M.C.,et al. Towards robust statistical inference for complex computer models[J],2021,24(6).
APA	Oberpriller J.,Cameron D.R.,Dietze M.C.,&Hartig F..(2021).Towards robust statistical inference for complex computer models.Ecology Letters,24(6).
MLA	Oberpriller J.,et al."Towards robust statistical inference for complex computer models".Ecology Letters 24.6(2021).