##  [Multi-sensor Satellite Imagery Reveals Spatiotemporal Changes in Peatland Water Table After Restoration](/resource/multi-sensor-satellite-imagery-reveals-spatiotemporal-changes-peatland-water-table-after) 

Organization

[University of Oulu](/organization/university-oulu)

[Natural Resources Institute Finland](/organization/natural-resources-institute-finland)

[Parks and Wildlife Finland](/organization/parks-and-wildlife-finland)

 

 

Resource Type

[Peer reviewed article](/taxonomy/term/37)

 

 

Author(s)

Aleksi Isoaho

Lauri Ikkala

Lassi Päkkilä

Hannu Marttila

Santtu Kareksela

Aleksi Räsänen

 

 

Original Authors

Aleksi Isoaho

Lauri Ikkala

Lassi Päkkilä

Hannu Marttila

Santtu Kareksela

Aleksi Räsänen

 

 

Contacts

[Aleksi Isoaho](/contact/aleksi-isoaho)

 

 

Resource Date:

2024

 

 

[Remote sensing](https://www.sciencedirect.com/topics/earth-and-planetary-sciences/remote-sensing "Learn more about Remote sensing from ScienceDirect's AI-generated Topic Pages") (RS) has been suggested as a tool to spatially monitor the status of [peatland](https://www.sciencedirect.com/topics/earth-and-planetary-sciences/peatland "Learn more about peatland from ScienceDirect's AI-generated Topic Pages") ecosystem functioning after restoration. However, there have been only a few studies in which post-restoration [hydrological changes](https://www.sciencedirect.com/topics/earth-and-planetary-sciences/hydrological-change "Learn more about hydrological changes from ScienceDirect's AI-generated Topic Pages") have been quantified with RS-based modelling. To address this gap, we developed an approach to assess post-restoration spatiotemporal changes in the [peatland](https://www.sciencedirect.com/topics/agricultural-and-biological-sciences/peatlands "Learn more about peatland from ScienceDirect's AI-generated Topic Pages") water table (WT) with optical (Sentinel-2 and [Landsat](https://www.sciencedirect.com/topics/agricultural-and-biological-sciences/landsat "Learn more about Landsat from ScienceDirect's AI-generated Topic Pages") 7–9) and radar (Sentinel-1) imagery. We tested the approach in eleven northern boreal peatlands (six restored, and five control sites) impacted by [forestry](https://www.sciencedirect.com/topics/agricultural-and-biological-sciences/forestry "Learn more about forestry from ScienceDirect's AI-generated Topic Pages") drainage in northern Finland using [Google Earth Engine](https://www.sciencedirect.com/topics/earth-and-planetary-sciences/google-earth-engine "Learn more about Google Earth Engine from ScienceDirect's AI-generated Topic Pages") cloud computing capabilities. We constructed a random forest regression model with spatiotemporal field-measured WT data as a dependent variable and satellite imagery features as independent variables. To assess the spatiotemporal changes, we constructed representative maps for situations before and after restoration, separately for early summer high-water and midsummer low-water conditions. To further quantify temporal changes during 2015–2023 and to test their statistical significance, we conducted a bootstrap hypothesis test for the areas near the restoration measures and similar areas in the control sites. The regression model had a relatively good fit and explanatory capacity (overall R2 = 0.71, [RMSE](https://www.sciencedirect.com/topics/earth-and-planetary-sciences/root-mean-square-error "Learn more about RMSE from ScienceDirect's AI-generated Topic Pages") = 6.01 cm), while there were notable site-specific variations. The WT maps showed that the post-restoration changes were not uniform and concentrated near the restoration measures. The bootstrap test showed that the WT increased more in the restored areas (4.7–8.8 cm) than in the control areas (0.1–5.2 cm). Our results indicate that restoration impact on [surface hydrology](https://www.sciencedirect.com/topics/earth-and-planetary-sciences/surface-water-hydrology "Learn more about surface hydrology from ScienceDirect's AI-generated Topic Pages") can be quantified with multi-sensor satellite imagery and a machine learning approach in treeless peatlands.