Mapping Midaltitude Peatlands Using Sentinel-1/2 Images and Machine Learning in the Mountainous Region of Northeastern China

Peatlands, which constitute only 3% of Earth’s land surface, store an estimated 612 Pg of carbon. Due to escalating warming and anthropogenic impacts, numerous peatlands undergo degradation, releasing stored carbon into the atmosphere and exacerbating global warming. The accurate delineation of the extents and boundaries of peatlands is imperative to mitigate peatland degradation, but it also remains a considerable challenge. This study developed a peatland machine-learning classification model using an object-based random forest (RF) algorithm, comprehensive spatiotemporal features, and multisource remote sensing data, including Sentinel-1, Sentinel-2 imagery, and digital elevation model (DEM). A high-resolution peatland map (10 m) was generated for the Changbai Mountains (CBM) in northeastern China. The results show that spectral indices from May play a particularly significant role in enhancing the accuracy of the classification. The study achieved an overall accuracy (OA) exceeding 94%, with the classification accuracy for the peatland category surpassing 91%. The analysis revealed that peatlands cover approximately 1197.09 km2 in the area, with over 80% situated below 1000 m a.s.l., around 70% on slopes less than 4°, and more than 80% within 5 km of a water body. This study proposes the novel methods for selecting feature variables in classification, aiming to enhance the accuracy of peatland mapping, thus providing critical insights and a benchmark for future refined mapping efforts. The results from this mapping endeavor hold substantial implications for the conservation and management of peatlands.