Despite the need for quality land cover information, large-area, high spatial resolution land cover mapping has proven to be a difficult task for a variety of reasons including large data volumes, complexity of developing training and validation datasets, data availability, and heterogeneity in data and landscape conditions. We investigate the use of geographic object-based image analysis (GEOBIA), random forest (RF) machine learning, and National Agriculture Imagery Program (NAIP) orthophotography for mapping general land cover across the entire state of West Virginia, USA, an area of roughly 62,000 km². We obtained an overall accuracy of 96.7% and a Kappa statistic of 0.886 using a combination of NAIP orthophotography and ancillary data. Despite the high overall classification accuracy, some classes were difficult to differentiate, as highlight by the low user’s and producer’s accuracies for the barren, impervious, and mixed developed classes. In contrast, forest, low vegetation, and water were generally mapped with accuracy. The inclusion of ancillary data and first- and second-order textural measures generally improved classification accuracy whereas band indices and object geometric measures were less valuable. Including super-object attributes improved the classification slightly; however, this increased the computational time and complexity. From the findings of this research and previous studies, recommendations are provided for mapping large spatial extents.

Land development processes are driven by complex interactions between socio-economic and spatial factors. Acquiring an understanding of such processes and the underlying procedures helps urban and regional planners, environmental scientists, and policy makers to base their decisions on valid and profound information. In this work, remote-sensing-derived land-cover data were used to characterize the patterns of land development from the beginning of 1985 to the beginning of 2015, in the state of West Virginia (WV), US. We applied spatial pattern analysis, ridge regression, and Geographically Weighted Ridge Regression (GWRR) to examine the impact of population, energy resources, existing land developments dynamics, and economic status on land transformation. We showed that in presence of multicollinearity of explanatory variables, how penalizing regression models in both local and global levels lead to a better fit and decreases the model’s variance. We used geographical error analysis of regression models to visualize the difference between the model estimates and actual values. The findings of this research indicate that because of shifting geography of opportunities, the patterns and processes of land development in the studied region are unstable. This leads to fragmented land developments and prevents formation of large communities.