The relevant range of scales for multi-scale contextual spatial modelling
文献类型：期刊论文
| 作者 | Behrens, Thorsten2,3; Rossel, Raphael A. Viscarra4; Kerry, Ruth5; MacMillan, Robert6; Schmidt, Karsten3; Lee, Juhwan4; Scholten, Thomas3; Zhu, A-Xing1,7
|
| 刊名 | SCIENTIFIC REPORTS
 |
| 出版日期 | 2019-10-15 |
| 卷号 | 9页码:9 |
| ISSN号 | 2045-2322 |
| DOI | 10.1038/s41598-019-51395-3 |
| 通讯作者 | Behrens, Thorsten(thorsten.behrens@uni-tuebingen.de) |
| 英文摘要 | Spatial autocorrelation in the residuals of spatial environmental models can be due to missing covariate information. In many cases, this spatial autocorrelation can be accounted for by using covariates from multiple scales. Here, we propose a data-driven, objective and systematic method for deriving the relevant range of scales, with distinct upper and lower scale limits, for spatial modelling with machine learning and evaluated its effect on modelling accuracy. We also tested an approach that uses the variogram to see whether such an effective scale space can be approximated a priori and at smaller computational cost. Results showed that modelling with an effective scale space can improve spatial modelling with machine learning and that there is a strong correlation between properties of the variogram and the relevant range of scales. Hence, the variogram of a soil property can be used for a priori approximations of the effective scale space for contextual spatial modelling and is therefore an important analytical tool not only in geostatistics, but also for analyzing structural dependencies in contextual spatial modelling. |
| WOS关键词 | RANDOM FORESTS ; SOIL ; GEOSTATISTICS ; VARIOGRAM ; PATTERNS |
| 资助项目 | German Research Foundation (DFG) under the Pedoscale project[BE 4023/3-1] |
| WOS研究方向 | Science & Technology - Other Topics |
| 语种 | 英语 |
| WOS记录号 | WOS:000490121400018 |
| 出版者 | NATURE PUBLISHING GROUP |
| 资助机构 | German Research Foundation (DFG) under the Pedoscale project |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/129663]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Behrens, Thorsten |
| 作者单位 | 1.Chinese Acad Sci, State Key Lab Environm Informat Syst, Inst Geog Sci & Nat Resources, Beijing 100101, Peoples R China 2.Eberhard Karls Univ Tuebingen, Cluster Excellence Machine Learning New Perspecti, Maria Linden Str 6, D-72076 Tubingen, Germany 3.Eberhard Karls Univ Tuebingen, Dept Geosci Soil Sci & Geomorphol, Ruemelinstr 19-23, D-72070 Tubingen, Germany 4.Curtin Univ, Fac Sci & Engn, Sch Mol & Life Sci, Soil & Landscape Sci, GPO Box U1987, Perth, WA 6845, Australia 5.Brigham Young Univ, Dept Geog, 690 Spencer W Kimball Tower, Provo, UT 84602 USA 6.LandMapper Environm Solut Inc, 702-250 Douglas St, Victoria, BC, Canada 7.Univ Wisconsin, Dept Geog, Madison, WI 53706 USA |
| 推荐引用方式 GB/T 7714 | Behrens, Thorsten,Rossel, Raphael A. Viscarra,Kerry, Ruth,et al. The relevant range of scales for multi-scale contextual spatial modelling[J]. SCIENTIFIC REPORTS,2019,9:9. |
| APA | Behrens, Thorsten.,Rossel, Raphael A. Viscarra.,Kerry, Ruth.,MacMillan, Robert.,Schmidt, Karsten.,...&Zhu, A-Xing.(2019).The relevant range of scales for multi-scale contextual spatial modelling.SCIENTIFIC REPORTS,9,9. |
| MLA | Behrens, Thorsten,et al."The relevant range of scales for multi-scale contextual spatial modelling".SCIENTIFIC REPORTS 9(2019):9. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。