Digital elevation modeling using artificial neural networks, deterministic and geostatistical interpolation methods

The digital elevation model (DEM) is the name given to a structure used indicate surface. Determination of features such as elevation, basin slope and area are very important in engineering applications. These properties determined by DEM their power represent accuracy or truth vital In addition latitude (X), longitude(Y) coordinate information, altitude information required, intermediate values different methods for DEM. this study, Mert River Basin Samsun (Turkey) was chosen application area. Heights estimated from X, Y information. Three Artificial Neural Networks, IDW Kriging were used. Networks (ANN) analyzed with three inputs. are: (i) x information; (ii) y (iii) It form Radial Based Network, Multilayer Network Generalized Network. X interpolation methods. Results evaluated using Coefficient (R²), Mean Absolute Error (MAE) Root Square (RMSE) comparison criteria. According modeling results: observed that results all reached sufficient level accuracy. method found be most successful model, followed ANN.