Chemical species distributions in rock sequences can be modelled using Gaussian processes (GPs) to predict the weight percentage between known data points. This method can be improved by dividing the modelled area into regions of different mineralogy. In the context of many iron ore deposits, marker shales give the initial guidance of where these regions may lie. These shales give rise to distinctive peaks in the natural gamma downhole logs, which are conventionally identified by hand. A GP method has been developed to automate this task.Once the appropriate boundary has been located on the basis of shale occurrences, chemical assays from exploration drill holes are used to find the exact boundaries of interest. These boundaries divide the drill hole stratigraphy into regions of different mineralogy, each of which display their own distinct correlations between the main elements and oxides (Fe, SiO2 and Al2O3). Iron ore shows a negative correlation between Fe and Al2O3, but in banded iron formation (BIF) there is a positive correlation between these species. Similarly, SiO2 and Al2O3 have a positive correlation in the shales and ore but a negative correlation in the BIF. Correlations obtained within ore-, BIF- and shale-dominated regions are therefore better than those obtained using the entire log and can be used to improve the results obtained when modelling.