Oil and Gas Development Potential for Wyoming

This dataset is a predictive model of Wyoming oil and gas development potential. The model represents where new oil and gas development is most likely to occur, with lowest development potential represented by values of 0 and highest development potential values represented by 1. The binary response variable was geospatial data representing producing and non-producing oil and gas wells. Nine topographic, geological and geophysical variables were used to predict development, including data on bedrock geology and Euclidean distance from geologic faults both from the Wyoming State Geological Survey. We used a nonparametric Random Forests model in R, developed to address statistical issues related to over-fit and parameter sensitivity in CART (Classification and Regression Tree) models. Model validation was performed using out-of-bag (OOB) testing techniques to produce standard error statistics including area under the receiver operating characteristic curve (ROC AUC), Cohen?s kappa, OOB error, and class error. Within the Random Forest models independent boot-strapping (OOB) subsets with many thousands of iterations are used for model validation and each tree is constructed using a different bootstrap sample from the original data. The ROC AUC was 0.83, Cohen?s kappa was 0.62, OOB error was 22.4%, and overall model accuracy (total number of correct classifications divided by the total number of sample points) was 82.5%. Additionally, we applied the Boyce index to measure observed versus expected occurrence, using independent validation data points and binned versions of the models. Results indicated a highly significant model (Boyce Index = 0.99; P < 0.001). Further modeling details are provided in Copeland et al. (2009) and Copeland et al. (In Review). Citations: Copeland, HE, KE Doherty, DE Naugle, A Pocewicz, J Kiesecker (2009) Mapping oil and gas potential in the US intermountain west and estimating impacts to species. PLoS ONE 4(10):e7400 Copeland, HE, A Pocewicz, DE Naugle, T Griffiths, D Keinath, J Evans, J Platt (In Review). Measuring the effectiveness of conservation: A novel framework to quantify the benefits of sage-grouse conservation policy and easements in Wyoming. PLoS ONE The projection of this dataset is: US NAD83 Lambert Conformal Conic False easting 0 False northing 0 Central meridian -107.0 Standard parallel 1 33.0 Standard parallel 2 45.0 Latitude of origin 41.0