Evaluation of the Transferability of a Knowledge-Based Soil-Landscape Model

Abstract

Knowledge-based digital soil mapping has been used extensively to predict soil taxonomic and physico-chemical soil characteristics. Fuzzy logic knowledge-based models allow explicit integration of knowledge and expertise from soil mappers familiar with a region. Questions remain about the transferability of soil-landscape models developed in one region to other regions. Objectives of this study were to develop and evaluate a knowledge-based model to predict soil series and fuzzy drainage classes and assess its transferability potential between similar soil landscapes in Essex County, Vermont. Two study areas, study area W1, 3.5 km² in size and study area W2, 1.9 km² in size, were sampled at 128 and 42 sites, respectively. Both study areas are located in Essex County, Vermont. Rule-based fuzzy inference was used based on fuzzy membership functions characterizing soil-environment relationships to create a model derived from expert knowledge. The model was implemented using the Soil Inference Engine (SIE), which provides tools and a user-friendly interface for soil scientists to prepare environmental data, define soil-environment models, run soil inference, and compile final map products. Defuzzified raster predictions were compared to field mapped soil series and fuzzy drainage class properties to assess their accuracy.

In W1 the model was 73.7 and 88.8% accurate, respectively, in predicting soil series and fuzzy drainage classes using an independent validation set. In W2, similar results were achieved, with 71.4 and 89.9% accuracies, respectively. It was shown that the prediction model was transferable to a landscape with similar soil characteristics. For future soil prediction applications it is critical to identify constraints and thresholds that limit transferability of prediction models such as SIE to other soil-landscapes.