Dissolved iron (dFe) transported by the Amur River greatly contributes to phytoplankton growth in the Sea of Okhotsk. Nevertheless, there has been little research on the dFe source of rivers, especially in the Amur-Mid Basin which is situated in a sporadic permafrost area. In the Amur-Mid Basin, permafrost generally exists under wetlands in the flat valley, and these permafrost wetlands could be a dFe source of rivers. To asess the importance of the permafrost wetlands as a dFe source, first we made a landcover map with high resolution of 30 m using Landsat-8 data and a machine learning technique (decision tree analysis). As a result of decision tree analysis, three normalized indices (normalized diference vegetation index, normalized difference soil index, and normalized difference water index) and slope enabled us to classify landcovers into three vegetation types: wetland, forest, and grassland. Using this landcover map, we investigated the coverages of the permafrost wetland in the sampled watersheds and examined the correlation with river water chemistry (dFe, dissolved organice carbon: DOC, and electrical conductivity: EC). As a result, dFe and DOC concentrations showed a clear positive correlation (dFe: r2 = 0.66, DOC: r2 = 0.46) with the coverage of permafrost wetlands, while EC showed a negative correlation with those (r2 = 0.45). These findings are the first to demonstrate the direct evidence about the importance of permafrost wetlands to supply dFe and DOC to rivers in the Amur-Mid Basin.