Peatlands are an important ecosystem due to their role in carbon sequestration as well as other ecosystem services including; climate regulation and water regulation. Peatlands cover a small fraction (~3 %) of the terrestrial surface. Nevertheless, they account for approximately one-third of global Soil Organic Carbon stock. In Ireland, peatlands cover ~21% of the land area and account for between 50-75% of the total SOC stock. However, much of this area has been degraded through anthropogenic activities such as drainage and peat extraction. Therefore, there is a need to develop a system to identify management-related impacts on peatland function. The system will directly support rehabilitation and conservation activities, aiding identification of candidate sites for rewetting and restoration. Both high-resolution satellite data (Copernicus Sentinel-2) and very high-resolution aerial photography will be used. Peatlands will be delineated using the Derived Irish Peat map (DIPM2) in both datasets. Semi-automatic object-based image analysis and machine learning-based techniques will be used to extract the extent of drains on Irish peatlands. Furthermore, a multi-scale approach will be implemented to generate Normalized Difference Vegetation Index maps. NDVI will be generated from both in-situ and remote sensors (Sentinel-2/Aerial imagery). Overall, the outputs generated from these datasets (LULC, drainage and NDVI maps) will be integrated into a GIS framework. The main aim of this study is to assess the impact of anthropogenic management of peatlands, using GIS, Earth Observation and Machine Learning (ML).