The fundamental component of resource estimation is domain modelling. However, in such deposits as roll front uranium, they are mostly deposited in sandstone and on the contact of oxidised and reduced rock domains which makes it difficult to model. The Grade-Thickness (GT) as well as contour method is one of the most applied resource estimation techniques in roll-front uranium deposits. However, explicit modelling and GT contouring by using the GT information extracted by drill holes is exceedingly difficult, time consuming and inconsistent. This research studies domain modelling of roll front uranium mineralisation using the GT values within the radial basis function (RBF) aided implicit modelling framework. It also compares the spatial associations of the RBF determined domain of mineralisation to the domains obtained by GT contours. Then, the block grades within the domain of mineralisation are estimated by using Kriging and selected machine learning models to compare their spatial associations and overall, in situ tons and grade estimates with each other and GT contours. The domain of mineralisation modelled by RBF appears to spatially correlate well with the domain of mineralisation obtained by GT contours. The performance of the selected machine learning models performed quite good with k-NN (k Nearest Neighbour) having values of Coefficient of Determination (R2) = 0.792, Root Mean Squared Error (RMSE) = 0.0216 and Mean Absolute Error (MAE) = 0.0048 and the random forest (RF) with R2=0.751, RMSE=0.0236, and MAE=0.0077. A visual validation of these models, swath plots, grade tonnage curves suggests that the k-NN and Ordinary Kriging (OK) results are remarkably close to each other perfectly aligning with the drill hole intersections in terms of grades while RF estimates show significant deviations of higher grades from the other methods and the supporting drill hole information. There is a significant difference between GT in situ resource estimates as observed within this study and OK and k-NN results were approximately 4 per cent and 1 per cent respectively.