The characterization of ecosystem functional types (EFTs) and the construction of ecosystem functional patterns are critical for understanding and preserving the integrity of biological communities, ecosystem services, and the climate. The western part of Songnen Plain, one of the typical regions in Northeast China, is sensitive to global changes. Based on moderate resolution imaging spectroradiometer data for the period of 2003 to 2012, five indices, namely land surface water index, land surface temperature, enhanced vegetation index, net photosynthesis, albedo, and their derived variables, including the average, the maximum value, and the difference between the maximum and minimum values during the growing season, are selected as the ecosystem functioning indicators in the western Songnen Plain. The fuzzy C-means clustering method is used to identify the EFTs. The correspondence analysis method is utilized to discriminate the consistency and heterogeneity between EFTs and land cover types. The selected variables indicating carbon, energy, and water flux of the regional ecosystem could be involved in the ecosystem functional classification. EFT could be associated with multiple land cover types, and the heterogeneity pattern of ecosystem functions and structures may be dissimilar.