Errors related to the automatized satellite-based change detection of boreal forests in Finland

Timo P. Pitkänen (Corresponding Author), Laura Sirro, Lauri Häme, Tuomas Häme, Markus Törmä, Annika Kangas

Research output: Contribution to journalArticleScientificpeer-review

Abstract

The majority of the boreal forests in Finland are regularly thinned or clear-cut, and these actions are regulated by the Forest Act. To generate a near-real time tool for monitoring management actions, an automatic change detection modelling chain was developed using Sentinel-2 satellite images. In this paper, we focus mainly on the error evaluation of this automatized workflow to understand and mitigate incorrect change detections. Validation material related to clear-cut, thinned and unchanged areas was collected by visual evaluation of VHR images, which provided a feasible and relatively accurate way of evaluating forest characteristics without a need for prohibitively expensive fieldwork. This validation data was then compared to model predictions classified in similar change categories. The results indicate that clear-cuts can be distinguished very reliably, but thinned stands exhibit more variation. For thinned stands, coverage of broadleaved trees and detections from certain single dates were found to correlate with the success of the modelling results. In our understanding, this relates mainly to image quality regarding haziness and translucent clouds. However, if the growing season is short and cloudiness frequent, there is a clear trade-off between the availability of good-quality images and their preferred annual span. Gaining optimal results therefore depends both on the targeted change types, and the requirements of the mapping frequency.
Original languageEnglish
Article number102011
JournalInternational Journal of Applied Earth Observation and Geoinformation
Volume86
DOIs
Publication statusPublished - 2020
MoE publication typeA1 Journal article-refereed

Fingerprint

boreal forest
Image quality
Satellites
Availability
cloud cover
trade-off
fieldwork
modeling
Monitoring
growing season
monitoring
prediction
detection
evaluation
satellite image
material
need

Keywords

  • change monitoring
  • forest management
  • accuracy assessment

Cite this

@article{5d3ac17c44014aeea8de2cef46930c67,
title = "Errors related to the automatized satellite-based change detection of boreal forests in Finland",
abstract = "The majority of the boreal forests in Finland are regularly thinned or clear-cut, and these actions are regulated by the Forest Act. To generate a near-real time tool for monitoring management actions, an automatic change detection modelling chain was developed using Sentinel-2 satellite images. In this paper, we focus mainly on the error evaluation of this automatized workflow to understand and mitigate incorrect change detections. Validation material related to clear-cut, thinned and unchanged areas was collected by visual evaluation of VHR images, which provided a feasible and relatively accurate way of evaluating forest characteristics without a need for prohibitively expensive fieldwork. This validation data was then compared to model predictions classified in similar change categories. The results indicate that clear-cuts can be distinguished very reliably, but thinned stands exhibit more variation. For thinned stands, coverage of broadleaved trees and detections from certain single dates were found to correlate with the success of the modelling results. In our understanding, this relates mainly to image quality regarding haziness and translucent clouds. However, if the growing season is short and cloudiness frequent, there is a clear trade-off between the availability of good-quality images and their preferred annual span. Gaining optimal results therefore depends both on the targeted change types, and the requirements of the mapping frequency.",
keywords = "change monitoring, forest management, accuracy assessment",
author = "Pitk{\"a}nen, {Timo P.} and Laura Sirro and Lauri H{\"a}me and Tuomas H{\"a}me and Markus T{\"o}rm{\"a} and Annika Kangas",
year = "2020",
doi = "10.1016/j.jag.2019.102011",
language = "English",
volume = "86",
journal = "International Journal of Applied Earth Observation and Geoinformation",
issn = "1569-8432",
publisher = "Elsevier",

}

Errors related to the automatized satellite-based change detection of boreal forests in Finland. / Pitkänen, Timo P. (Corresponding Author); Sirro, Laura; Häme, Lauri; Häme, Tuomas; Törmä, Markus; Kangas, Annika.

In: International Journal of Applied Earth Observation and Geoinformation, Vol. 86, 102011, 2020.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Errors related to the automatized satellite-based change detection of boreal forests in Finland

AU - Pitkänen, Timo P.

AU - Sirro, Laura

AU - Häme, Lauri

AU - Häme, Tuomas

AU - Törmä, Markus

AU - Kangas, Annika

PY - 2020

Y1 - 2020

N2 - The majority of the boreal forests in Finland are regularly thinned or clear-cut, and these actions are regulated by the Forest Act. To generate a near-real time tool for monitoring management actions, an automatic change detection modelling chain was developed using Sentinel-2 satellite images. In this paper, we focus mainly on the error evaluation of this automatized workflow to understand and mitigate incorrect change detections. Validation material related to clear-cut, thinned and unchanged areas was collected by visual evaluation of VHR images, which provided a feasible and relatively accurate way of evaluating forest characteristics without a need for prohibitively expensive fieldwork. This validation data was then compared to model predictions classified in similar change categories. The results indicate that clear-cuts can be distinguished very reliably, but thinned stands exhibit more variation. For thinned stands, coverage of broadleaved trees and detections from certain single dates were found to correlate with the success of the modelling results. In our understanding, this relates mainly to image quality regarding haziness and translucent clouds. However, if the growing season is short and cloudiness frequent, there is a clear trade-off between the availability of good-quality images and their preferred annual span. Gaining optimal results therefore depends both on the targeted change types, and the requirements of the mapping frequency.

AB - The majority of the boreal forests in Finland are regularly thinned or clear-cut, and these actions are regulated by the Forest Act. To generate a near-real time tool for monitoring management actions, an automatic change detection modelling chain was developed using Sentinel-2 satellite images. In this paper, we focus mainly on the error evaluation of this automatized workflow to understand and mitigate incorrect change detections. Validation material related to clear-cut, thinned and unchanged areas was collected by visual evaluation of VHR images, which provided a feasible and relatively accurate way of evaluating forest characteristics without a need for prohibitively expensive fieldwork. This validation data was then compared to model predictions classified in similar change categories. The results indicate that clear-cuts can be distinguished very reliably, but thinned stands exhibit more variation. For thinned stands, coverage of broadleaved trees and detections from certain single dates were found to correlate with the success of the modelling results. In our understanding, this relates mainly to image quality regarding haziness and translucent clouds. However, if the growing season is short and cloudiness frequent, there is a clear trade-off between the availability of good-quality images and their preferred annual span. Gaining optimal results therefore depends both on the targeted change types, and the requirements of the mapping frequency.

KW - change monitoring

KW - forest management

KW - accuracy assessment

U2 - 10.1016/j.jag.2019.102011

DO - 10.1016/j.jag.2019.102011

M3 - Article

VL - 86

JO - International Journal of Applied Earth Observation and Geoinformation

JF - International Journal of Applied Earth Observation and Geoinformation

SN - 1569-8432

M1 - 102011

ER -