Soil patterns are formed by the type, intensity, and spatial arrangement of land uses as well as underlying environmental landscape properties. The SCORPAN conceptual model provides a framework for quantitative mapping of soils at the landscape scale. In this model soils are predicted as a function of mapped soil properties (S), climate (C), organisms/vegetation (O), relief (R), parent material (P) that are also dependent on age/time (A) and geographic space (N). Our objectives were to apply the SCORPAN model to soil-landscape conditions in north-east Florida and implement a quantitative soil-landscape model. Our study area was the Santa Fe River Watershed in north-east Florida (3,585 km2) with soils that are predominantly sandy in texture and formed on karst terrain. The underlying geologic units include Eocene limestone, capped by Miocene sediments which tend to be rather clayey and phosphatic, and Pliocene and Pleistocene-Holocene sediments which tend to be sandy at the surface but having loamy subsoils or substrate at varying depths. Land cover is mixed with high- and low-intensity uses ranging from agriculture to upland forest and pine plantations. Topography is level to gently sloping and undulating. Our goal was to gain insight into complex landscape responses originating from anthropogenic stresses superimposed on a landscape formed on diverse parent material and dissected by a scarp with distinct lowland and upland areas. We used site-specific soil observations, soil information databases (Soil Data Mart, SSURGO, and Florida Soil Characterization Data) and auxiliary environmental datasets to characterize the SCORPAN factors within a spatially-explicit framework for a time period from 1990 to current during which major land use shifts occurred within the watershed. Classification and regression trees were used to integrate field and digital datasets. Numerous tree models were developed that predicted soil patterns throughout the watershed using the environmental factor datasets. Our goal was to identify a parsimonious model that predicted soil patterns with high quality and precision using numerous error metrics. Tree-based soil patterns were compared to field mapped soil types indicating that specific factor combinations of land use, parent material, topography, and other landscape metrics were able to distinguish specific soil types (i.e., orders, suborders, etc.). Our model shows promise for mapping soil-landscapes in north-east Florida in an objective, quantitative soil mapping framework. In the future, this approach may be transferred to other soil-landscapes which should reduce costs of field mapping activities, providing high resolution soil data that complement existing soil survey maps.