U.S. flag An official website of the United States government.
Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

i

Evaluating machine learning approaches for the interpolation of monthly air temperature at Mt. Kilimanjaro, Tanzania



Details

  • Journal Title:
    Spatial Statistics
  • Personal Author:
    Appelhans, Tim ; Mwangomo, Ephraim ; Hardy, Douglas R. ; Hemp, Andreas ; Nauss, Thomas
  • NOAA Program & Office:
    NOAA General Documents
  • Description:
    Spatially high resolution climate information is required for a variety of applications in but not limited to functional biodiversity research. In order to scale the generally plot-based research findings to a landscape level, spatial interpolation methods of meteorological variables are required. Based on a network of temperature observation plots across the southern slopes of Mt. Kilimanjaro, the skill of 14 machine learning algorithms in predicting spatial temperature patterns is tested and evaluated against the heavily utilized kriging approach. Based on a 10-fold cross-validation testing design, regression trees generally perform better than linear and non-linear regression models. The best individual performance has been observed by the stochastic gradient boosting model followed by Cubist, random forest and model averaged neural networks which except for the latter are all regression tree-based algorithms. While these machine learning algorithms perform better than kriging in a quantitative evaluation, the overall visual interpretation of the resulting air temperature maps is ambiguous. Here, a combined Cubist and residual kriging approach can be considered the best solution.
  • Keywords:
  • Source:
    Spatial Statistics, 14, 91-113
  • DOI:
    https://doi.org/10.1016/j.spasta.2015.05.008
  • ISSN:
    2211-6753
  • Format:
    PDF
  • Publisher:
    Elsevier BV
  • Document Type:
    Journal Article
  • License:
    https://creativecommons.org/licenses/by-nc-nd/4.0/
  • Rights Information:
    CC BY-NC-ND
  • Compliance:
    Library
  • Download URL:
    https://repository.library.noaa.gov/view/noaa/59469/noaa_59469_DS1.pdf
  • File Type:
    Filetype[PDF - 3.20 MB]
  • Collection(s):
    NOAA General Documents
  • Main Document Checksum:
    urn:sha256:0c05fe6ea7359cb1cc92889067d90e43f146713ff8037571d1602fcbd84a8efc
PREVIOUS
ON THIS PAGE
Details
 Found an issue?
Send us an email at:
noaa.repository@noaa.gov
The NOAA IR serves as an archival repository of NOAA-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by NOAA or funded partners. As a repository, the NOAA IR retains documents in their original published format to ensure public access to scientific information.
BACK TO TOP