Prediction of interface of geological formations using generalized additive model

Geological information such as geological interfaces is important for the design of underground excavation and supporting measures. This in turn requires a method to predict accurately locations gap areas between boreholes. study presents generalized additive model (GAM) location interfaces. The performance GAM evaluated using both simulated data borehole determination rockhead two different formations Singapore. results show that can provide reasonable confidence interval (CI) mean trend prediction (PI) sense 95% CI covers about actual curve while PI around testing data. Furthermore, complexity be well reflected uncertainty geologically complex area larger than regular area. More importantly, users impose prior or personal judgment regarding shape profile on model. an feature enable further improvement accuracy prediction.Highlights A used interfacesThe from SingaporeThe predictionGeological relatively largeExpert knowledge applied model, which improves