A1 Journal article (refereed), original research

Distribution Statistics Preserving Post-Processing Method With Plot Level Uncertainty Analysis for Remotely Sensed Data-Based Forest Inventory Predictions


Open Access publication

Publication Details
Authors: Junttila Virpi, Kauranne Tuomo
Publisher: MDPI
Publication year: 2018
Language: English
Related Journal or Series Information: Remote Sensing
Volume number: 10
Issue number: 11
Start page: 1
End page: 18
Number of pages: 18
ISSN: 2072-4292
JUFO-Level of this publication: 1
Open Access: Open Access publication

Abstract

Remotely sensed data-based models used in operational forest inventory usually give precise and accurate predictions on average, but they often suffer from systematic under- or over-estimation of extreme attribute values resulting in too narrow or skewed attribute distributions. We use a post-processing method based on the statistics of a proper, representative training set to correct the predictions and their probability intervals, attaining corrected predictions that reproduce the statistics of the whole population. Performance of the method is validated with three forest attributes from seven study sites in Finland with training set sizes from 50 to over 400 field plots. The results are compared to those of the uncorrected predictions given by linear models using airborne laser scanning data. The post-processing method improves the accuracy assessment linear fit between the predictions and the reference set by 35.4–51.8% and the distribution fit by 44.5–95.0%. The prediction root mean square error declines on the average by 6.3%. The systematic under- and over-estimation are reduced consistently with all training set sizes. The level of uncertainty is maintained well as the probability intervals cover the real uncertainty while keeping the average probability interval width similar to the one in uncorrected predictions.


Last updated on 2019-13-03 at 12:00