Monitoring peatland water table depth with optical and radar satellite imagery

Peatland water table depth (WTD) and wetness have widely been monitored with optical synthetic aperture radar (SAR) remote sensing but there is a lack of studies that used multi-sensor data, i.e., combination SAR data. We assessed how well WTD can be whether approach boosts explanatory capacity are differences in regression performance between data peatland types. Our consisted continuous multiannual from altogether 50 restored undrained Finnish peatlands, (Landsat 5–8, Sentinel-2) Sentinel-1 C-band processed Google Earth Engine. calculated random forest regressions dependent variable being independent variables consisting 21 10 metrics. The average was moderate models (R2 43.1%, nRMSE 19.8%), almost as high 42.4%, 19.9%) considerably lower 21.8%, 23.4%) trained separately for each site. When the included several sites were six habitat type management option combinations, R2 40.6% models, 36.6% 33.7% models. There considerable site-specific variation model ?3.3–88.8% ran site) multi-sensor, or performed best. higher than open sparsely treed densely peatlands. most important SWIR-based metrics VV backscatter. results suggest works usually better does monitoring increases moderately little.