Quantifying intra-field soil variability using categorical data: A case study of predicting soil organic matter using soil survey maps

• Two new models predict a continuous soil attribute using zone-level categorical inputs. • Both models outperformed the baseline field-averaging method. • The framework supports scalable prediction with minimal input data. • The framework has the potential to generalize to other soil attributes. Accurate estimation of the spatial distribution of soil properties is essential for advancing precision agriculture. This study evaluates two modeling strategies for predicting a continuous soil attribute, log-transformed soil organic matter (SOM%), using zone-level categorical predictors such as soil type. The first approach employs a zonal regression model incorporating soil-type coefficients, while the second leverages normalized pairwise comparisons among intra-field zones. Both models are assessed against a baseline strategy reflecting composite sampling practice, in which a single field-wise average is assumed. Incorporating categorical structure increased the prediction accuracy; the zonal regression model achieved an RMSE of 0.097 (R² = 0.89), and the normalized pairwise model reached an RMSE of 0.108 (R² = 0.85), both improving upon the baseline field averaging method based on within-field samples (RMSE = 0.140, R² = 0.75). The proposed framework is generalizable to other soil attributes (e.g., pH, CEC, texture fractions) where zone-level delineation is available. This work offers a scalable, interpretable, and field-deployable methodology, contributing to spatial soil inference and site-specific agricultural decision-making under sparse sampling conditions.