Final Product of Mask R-CNN prediction of RCH in SGL in PA

This is the final result of using Mask R-CNN to predict the location of relict charcoal hearths (RCH) in and near State Game Lands throughout Pennsylvania. Please note that only those RCHs falling into one (or more) of the three cluster analyses is considered to be a likely true positive (i.e., an actual charcoal hearth). That is, where ClusterCT =0. Variables: id= unique identifier starting with 3-digit SGL number, PAN or PAS (projections) and, within those a unique four-digit identifier<br> score= confidence score<br> SGL= State Game Land number<br> SGLImage= name of TIFF file of merged lidar tiles<br> Confirm= Whether the predicted hearth was determined, through visual inspection, to be a likely true positive (Y) or a false positive (N)<br> Bin#- in assessing these predictions we “binned” the results based upon the confidence score.<br> Bin_select= 1 if this record (predicted RCH) was selected for assessment within that bin<br> TrainID= Original ID of the training data (only training data that matched with a prediction are included). <br> Clusters5_300= resultant clusters from DBSCAN where minimum cluster size= 5 and maximum distance= 300 meters<br> Clusters10_500= resultant clusters from DBSCAN where minimum cluster size= 10 and maximum distance= 500 meters<br> Clusters20_1000= resultant clusters from DBSCAN where minimum cluster size= 20 and maximum distance= 1000 meters<br> CLUSTERCT = How many of the above clusters included the predicted RCH (0-3). Derived from the previous three variables. <br> 3Cluster= whether or not this predicted RCH was included in all three clusters. For additional information, please see https://zenodo.org/deposit/4593788 .