Significant rugged and relatively inaccessible land areas of the western U.S. remain to be mapped under the auspices of the National Cooperative Soil Survey. The objectives of this study were to test the use of digital soil mapping (DSM) techniques in Organ Pipe Cactus National Monument (ORPI), a remote and hyperthermic region of the Sonoran Desert in southwestern Arizona. Specifically, goals were to (i) generate a “pre-map” of soil-landscape relationships in ORPI, and (ii) derive a rule-based model for predicting soil taxonomy in ORPI based on digital datasets and soil survey data from surrounding areas. Pre-mapping soil-landscape analysis included unsupervised classification of environmental covariates for predicting pedogenic environments. Surrogate covariate layers were derived from ASTER satellite imagery, digital elevation models and terrain attributes, digital geology and vegetation maps, and PRISM climate data. The unsupervised classification was coupled with field reconnaissance to determine the most relevant data for soil-landscape classification. In addition, we utilized Decision Tree Analysis (DTA) to model Subgroup level Soil Taxonomy within ORPI by extracting environmental covariate data from neighboring areas with recent soil survey data. The pre-mapping exercises indicated great potential for using DSM techniques to separate distinct soil-landscape relationships within ORPI. In particular, various ASTER data products provided distinct separation of landforms and soil diagnostic horizons that matched well with an earlier Order 3 soil survey of ORPI. DTA analysis further demonstrated the applicability of DSM techniques to predict Soil Taxonomy across ORPI based on data from surrounding soil survey areas. Our results to date indicate that DSM techniques may be used effectively in soil surveys around arid regions of the southwestern US.