Small-Area Estimation of County-Level Forest Attributes Using Ground Data and Remote Sensed Auxiliary Information

Small-area estimation (SAE) is a concept that has considerable potential for precise estimation of forest ecosystem attributes in partitioned forest populations. In this study, several estimators were compared as SAE techniques for 12 counties in the northern Oregon Coast range. The estimators that were compared consisted of three indirect estimators, multiple linear regression (MLR), gradient nearest neighbor imputation (GNN), and most similar neighbor imputation (MSN), and five composite estimators based on MLR, MSN, and GNN with county-level direct estimates. Forest attributes of interest were density (trees/ha), basal area (m2/ha), cubic volume (m3/ha), quadratic mean diameter (cm), and average height of 100 largest trees per ha. The sample consisted of 680 annual Forest Inventory Analysis plots, a spatially balanced sample across all conditions and ownerships. The auxiliary data consisted of 16 Landsat variables, a land cover classification, tree cover, and elevation. Overall, the composite estimators were superior when both precision and bias of estimation were considered.