Since the passage of Public Law 95-87, Surface Mining Control and Reclamation Act (SMCRA) of 1977, coal mined land reclamation has been evaluated primarily by yield testing.  Many states, such as Illinois and Indiana, require that reclamation success be based be based on crop production of the mined land compared to an approved reference area or other guidelines.  Often, if a mined land does not meet reclamation requirements in the specified time period, the process of yield testing can continue for many years.  Researchers, mine owners, and regulators have expressed the need for a more efficient and less time consuming method for assessing reclamation success.  Previous research has advocated the use of a soil based productivity index for determining reclamation success and subsequently a basis for bond release.  In our experiment, georeferenced corn and soybean (only Lewis Mine) yield data, cone penetrometer test (CPT) at different soil depths, elevation (plus terrain derivatives), and apparent electrical conductivity (EC_a) data were collected for two fields at the Cedar Creek Mine site in western, IL and one field at the Lewis Mine site in southwestern, IN.  Yield data for each site was clustered using a k-means approach into high, medium and low yield clusters and canonical discriminant analysis was performed using our measured variables.  Results show that we are able to discriminate among yield categories with a 60% success rate and that EC_a, elevation, terrain derivatives and CPT variables linked to soil compaction are the best discriminators among yield categories.  Our experiment shows that the use of a soil productivity model may be beneficial in determining mined land reclamation success along with bond release.