The potential of Self-Organising maps clustering to characterise a harvested peatland using airborne radiometric data and OS digital elevation model.

Peatlands are becoming recognized as important carbon sequestration centres. Through restoration projects of peatlands in which the water table is raised, they may become carbon neutral or possibly carbon negative. Restoration projects require a knowledge of intra-peat variation across potentially large spatial areas. This is often difficult with traditional in-situ point measurements. The integration of multidimensional geophysical datasets and digital elevation models, combined with modern data analytical techniques, may provide a rapid means of accessing intra-peat variation. In this study, an airborne radiometric survey, being flown nationally over the Republic of Ireland, combined with a digital elevation model, is used to delineate areas within an industrial peatland where peat thickness is less than 1m. Radiometric data are particularly suited to peat studies as they are sensitive to water content and peat thickness and require relatively little expert knowledge to utilise. Peat, as a mostly organic material, acts as a low signal environment where variations in the signal are linked to intra-peat variation of thickness, density and/or water content. This study uses an unsupervised machine learning, self-organizing map clustering methodology to group the study site into three zones interpreted as 1) the edge of the bog where peat layer is thinning or there is influence on the radiometric signal from non-peat soils outside of the bog, 2) the normal peat conditions where thickness and saturation appear as a relative constant in the radiometric response, and 3) areas where the peat is either thinner or drier. A ground geophysical survey was conducted to verify this interpretation. The delineation of such spatial variations in the radiometric response could aid any restoration project in the initial stages or act as a baseline study to monitor changes to the peatland during and after a restoration project is complete. Future work will see this methodology extended to other peatland types such as blanket bogs and natural raised bogs, as well as the integration of concurrent airborne electromagnetic data to link the near-surface radiometric response to the deeper vadose zone and define a more comprehensive classification scheme for these peatland sites.