Current issue: 58(5)
Select issue
Silva Fennica 1926-1997
1990-1997
1980-1989
1970-1979
1960-1969
1950-1959
1940-1949
1926-1939
Acta Forestalia Fennica
1992-1999
1984-1991
1974-1983
1968-1973
1953-1968
1933-1952
1913-1932
Articles by Mari Myllymäki
Category : Research article
article id 22026,
category
Research article
(2023).
Understanding uncertainty in forest resources maps.
Silva Fennica
vol.
57
no.
2
article id 22026.
https://doi.org/10.14214/sf.22026
Keywords:
autocorrelation;
ensemble modelling;
kriging;
quantile;
random forest;
sequential Gaussian simulation
Highlights:
Forest resources maps without uncertainty assessment may lead to false impression of precision; Suitable tools for visualization of map products are lacking; Kriging method provided accurate uncertainty assessment for pixel-level predictions; Quantile random forest algorithm slightly underestimated the pixel-level uncertainties; With simulation it is possible to assess the uncertainty also for landscape-level characteristics.
Abstract |
Full text in HTML
|
Full text in PDF |
Author Info
Maps of forest resources and other ecosystem services are needed for decision making at different levels. However, such maps are typically presented without addressing the uncertainties. Thus, the users of the maps have vague or no understanding of the uncertainties and can easily make wrong conclusions. Attempts to visualize the uncertainties are also rare, even though the visualization would be highly likely to improve understanding. One complication is that it has been difficult to address the predictions and their uncertainties simultaneously. In this article, the methods for addressing the map uncertainty and visualize them are first reviewed. Then, the methods are tested using laser scanning data with simulated response variable values to illustrate their possibilities. Analytical kriging approach captured the uncertainty of predictions at pixel level in our test case, where the estimated models had similar log-linear shape than the true model. Ensemble modelling with random forest led to slight underestimation of the uncertainties. Simulation is needed when uncertainty estimates are required for landscape level features more complicated than small areas.
-
Kangas,
Natural Resources Institute Finland (Luke), Bioeconomy and environment, Yliopistokatu 6, 80101 Joensuu, Finland
https://orcid.org/0000-0002-8637-5668
E-mail:
annika.kangas@luke.fi
-
Myllymäki,
Natural Resources Institute Finland (Luke), Bioeconomy and environment, Latokartanonkaari 9, FI-00790 Helsinki, Finland
https://orcid.org/0000-0002-2713-7088
E-mail:
mari.myllymaki@luke.fi
-
Mehtätalo,
Natural Resources Institute Finland (Luke), Bioeconomy and environment, Yliopistokatu 6, 80101 Joensuu, Finland
https://orcid.org/0000-0002-8128-0598
E-mail:
lauri.mehtatalo@luke.fi
Click this link to register to Silva Fennica.
If you are a registered user, log in to save your selected articles for later access.
Your selected articles
Silva Fennica ·
Finnish Society of Forest Science
