Enhancing soil maps to better understand soil types is important for environmental and agricultural purposes. A study compared three methods of improving soil maps using a machine-learning algorithm called DSMART. By adding soil landscape relationships to the algorithm, the accuracy of predicting soil type distribution was significantly improved. The study found that including these relationships led to a higher percentage of accurate predictions compared to the original method. This means that considering the specific environment can help predict the types of soil that are likely to be present in a certain area.