DOI: 10.1016/j.atmosenv.2015.03.063
Scopus记录号: 2-s2.0-84926291930
论文题名: Examination of geostatistical and machine-learning techniques as interpolators in anisotropic atmospheric environments
作者: Tadić J ; M ; , Ilić V ; , Biraud S
刊名: Atmospheric Environment
ISSN: 0168-2563
EISSN: 1573-515X
出版年: 2015
卷: 111 起始页码: 28
结束页码: 38
语种: 英语
英文关键词: Airborne measurements
; Ensemble
; Neural networks
; Universal kriging
; Urban outflow
Scopus关键词: Artificial intelligence
; Boundary layers
; Carbon dioxide
; Learning systems
; Neural networks
; Uncertainty analysis
; Airborne measurements
; Ensemble
; Machine learning techniques
; Non-linear relationships
; Planetary boundary layers
; Uncertainty representation
; Universal kriging
; Urban outflow
; Interpolation
; anisotropy
; artificial neural network
; boundary layer
; carbon dioxide
; error analysis
; geostatistics
; interpolation
; kriging
; measurement method
; mixing ratio
; nonlinearity
; performance assessment
; prediction
; trajectory
; uncertainty analysis
; analytical error
; anisotropy
; Article
; atmosphere
; comparative study
; geostatistical analysis
; kriging
; machine learning
; preservation
; priority journal
; Billings County
; Lamont
; North Dakota
; Oklahoma [United States]
; United States
Scopus学科分类: Environmental Science: Water Science and Technology
; Earth and Planetary Sciences: Earth-Surface Processes
; Environmental Science: Environmental Chemistry
英文摘要: Selecting which interpolation method to use significantly affects the results of atmospheric studies. The goal of this study is to examine the performance of several interpolation techniques under typical atmospheric conditions. Several types of kriging and artificial neural networks used as spatial interpolators are here compared and evaluated against ordinary kriging, using real airborne CO2 mixing-ratio data and synthetic data. The real data were measured (on December 26, 2012) between Billings and Lamont, near Oklahoma City, Oklahoma, within and above the planetary boundary layer (PBL). Predictions were made all along the flight trajectory within a total volume of 5000km3 of atmospheric air (27×33×5.6km). We evaluated (a) universal kriging, (b) ensemble neural networks, (c) universal kriging with ensemble neural network outputs used as covariates, and (d) ensemble neural networks with ordinary kriging of the residuals as interpolation tools. We found that in certain cases, when the weaknesses of ordinary kriging interpolation schemes (based on an omnidirectional isotropic variogram presumption) became apparent, more sophisticated interpolation methods were in order. In this study, preservation of the potentially nonlinear relationship between the trend and coordinates (by using neural kriging output as a covariate in a universal kriging scheme) was attempted, with varying degrees of success (it was best performer in 4 out of 8 cases). The study confirmed the necessity of selecting an interpolation approach that includes a combination of expert understanding and appropriate interpolation tools. The error analysis showed that uncertainty representations generated by the kriging methods are superior to neural networks, but that the actual error varies from case to case. © 2015 Elsevier Ltd.
Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/81759
Appears in Collections: 气候变化事实与影响
There are no files associated with this item.
作者单位: Department of Global Ecology, Carnegie Institution for Science, Stanford, CA, United States; RT-RK Institute for Computer Based Systems, Novi Sad, Serbia; Lawrence Berkeley National Laboratory, Berkeley, CA, United States
Recommended Citation:
Tadić J,M,, Ilić V,et al. Examination of geostatistical and machine-learning techniques as interpolators in anisotropic atmospheric environments[J]. Atmospheric Environment,2015-01-01,111