Digital soil mapping requires two basic pieces of information: spatial information on the environmental conditions which co-vary with the soil conditions and the information on relationship between the set of environmental conditions and soil conditions. The former falls into the category of GIS/remote sensing analysis. The latter is often obtained through extensive field sampling. Extensive field sampling is very labor intensive and costly. This paper explores the concept of purposive sampling to improve the efficiency of field sampling for digital soil mapping. We believe that unique soil conditions (soil types or soil properties) can be associated with unique combination of environmental conditions. These unique combination of environmental conditions can be perceived as the critical points and the variation of soil conditions from one critical point (one soil type) to another (another soil type) can then be perceived as a linear variation which can be approximated using some linear functions. We used the fuzzy c-means classification to identify these unique combinations and their spatial locations. Field sampling efforts were then allocated to investigate the soil at these sites for establishing the relationships between soil conditions and environmental conditions. The established relationships were then used to map the spatial distribution of soil conditions. Two case studies, one in U.S. and another in China using this approach showed that this approach is effective for digital soil mapping.