Well log and 3-D seismic data were used to construct three depth maps for the top of the target L horizon of the Nash Draw field in southeastern New Mexico. The first two depth maps were made using Landmark° software packages TDQ and Z-map. The third depth map was made using a multilayer perceptron (MLP) neural network to regress for velocity at each seismic bin. At Nash Draw the wells are confined to the central region of the seismic survey, and conventional geostatistics reliably interpolated depths only in the region defined by well control. The MLP approach used the best three of 28 statistically ranked seismic attributes to predict the average velocity field from the surface to the L horizon. Each map was constructed using 15 wells as control points with three wells excluded for testing. Test wells one and two were located away from the control wells and have anomalous average velocities/depths.
Accurate depth maps are useful for reservoir development, particularly for stratigraphic and structural trap location, drilling depth and reservoir modeling.
The three test wells were used to compare the robustness of the computed depth maps, and all depth predictions were compared to the true depths determined from gamma ray logs for each well. TDQ, Z-map and MLP predicted values within 229.4, 104.7 and 7.6 feet, respectively, at test-well-1; 129.4, 47.7 and 43.7 feet, respectively, at test-well-2; and 12.4, 4.1 and 16.5 feet, respectively, for test-well-3.
Geostatistical methods underestimate the depths to the top of the L for the test wells lying outside the central clustering of control wells, while the MLP solution calculates a relationship that should be valid in each seismic bin in the field. Further refinements in the data and improved methodology are expected to yield a higher degree of accuracy between the real and predicted depths using MLP.