Accuracy assessment of georectified aerial photographs: Implications for measuring lateral channel movement in a GIS

Aerial photographs are commonly used to measure planform river channel change. We investigated the sources and implications of georectification error in the measurement of lateral channel movement by testing how the number (6–30) and type (human versus natural landscape features) of ground-control points (GCPs) and the order of the transformation polynomial (first-, second-, and third-order) affected the spatial accuracy of a typical georectified aerial photograph. Error was assessed using the root-mean-square error (RMSE) of the GCPs as well as error in 31 independent test points. The RMSE and the mean and median values of test-point errors were relatively insensitive to the number of GCPs above eight, but the upper range of test-point errors showed marked improvement (i.e., the number of extreme errors was reduced) as more GCPs were used for georectification. Using more GCPs thus improved overall georectification accuracy, but this improvement was not indicated by the RMSE, suggesting that independent test-points located in key areas of interest should be used in addition to RSME to evaluate georectification error.The order of the transformation polynomial also influenced test-point accuracy; the second-order polynomial function yielded the best result for the terrain of the study area. GCP type exerted a less consistent influence on test-point accuracy, suggesting that although hard-edged points (e.g., roof corners) are favored as GCPs, some soft-edged points (e.g., trees) may be used without adding significant error. Based upon these results, we believe that aerial photos of a floodplain landscape similar to that of our study can be consistently georectified to an accuracy of approximately ± 5 m, with 10% chance of greater error. The implications of georectification error for measuring lateral channel movement are demonstrated with a multiple buffer analysis, which documents the inverse relationship between the size of the buffers applied to two channel centerlines and the magnitude of change detected between them. This study demonstrates the importance of using an independent test-point analysis in addition to the RSME to evaluate and treat locational error in channel change studies.