English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Peatland is a globally important store of carbon. Peatland restoration efforts are being increasingly undertaken yet effective monitoring of landscape-scale restoration projects has been limited. A particular gap in our understanding is the length of time required before a site reaches the target state. To address this, a classification model based on remote sensing data was developed for a peatland restoration area on blanket bog in northern Scotland, UK, to evaluate whether post-restoration trajectories followed predictable trends over time. The model was trained against a chronosequence of sites within a 20 × 10 km study area that are being restored following drainage and intensive non-native afforestation. Two versions of the model were created to compare the accuracy obtainable from the suite of Sentinel-2 satellite data versus sub-metre resolution aerial imagery from GetMapping (RGB and IR). The Sentinel-2 based model greatly outperformed the aerial imagery-based model. Adding surface slope to the classification did not significantly improve the accuracy of prediction. Prediction of starting and target land covers was very robust, and both the most recent and oldest restoration sites were well predicted spatially. The main uncertainties in the model were within sites of intermediate restoration age, and sites which underwent additional treatments after the initial restoration. Using standard vegetation and wetness indices as indicators, it was possible to track the progression of areas that had been felled and rewetted towards the spectral signal of the control blanket bog locations. A further study examined the use of multiple years of satellite data (2015–2021) and including Sentinel-1 SAR imagery, and confirmed the findings obtained with only a single climatically average year, and furthermore examined the efficacy of different restoration methods. We observed consistent trends of restoration sites beginning to resemble the target hydrologically and ecologically functional blanket bog state after 10–20 years post intervention.

international journal of remote sensing

Assessing the Potential of using Sentinel-1 and 2 or high-resolution aerial imagery data with Machine Learning and Data Science Techniques to Model Peatland Restoration Progress – a Northern Scotland case study