Hydrocarbon Pay zone Prediction using AI Neural Network Modeling.

This paper captures the ability of AI neural network technology to analyze petrophysical datasets for pattern recognition and accurate prediction of the pay zone of a vertical well from the Santa Fe field in Kansas. During this project, data from 10 completed wells in the Santa Fe field were gathered, resulting in a dataset with 25,580 records, ten predictors (logs data), and a single binary output (Yes or No) to identify the availability of Hydrocarbon over a half feet depth segment in the well. Several models composed of different predictors combinations were also tested to determine how impactful some logs were compared to others for the prediction process. With 32 tested models using a base set of 5 logs (X, Y GR, DEPT, and CALI) and different combinations of 5 other logs ( RT90, RHOB, NPHI, PE, DT). All models containing RT90, NP, or DT led to a better prediction matching the pay zone established based on a petrophysical analysis and completion data from the well. Results from this project could be used as another support to help and justify decision-making for a Petro physicist regarding work in the field with less experience.