Towards A Neural-Network-Based Decision Tree Learning Algorithm for Petroleum Production Prediction

Prediction of oil well production is important for estimating economic benefit of a well. However, this prediction task is difficult because of the complex subsurface conditions of wells. In addition, the amount of data being collected in databases today has far exceeded our ability to reduce and analyze data without the use of automated analysis techniques. In response to the problems above, advancement in data mining technology in recent years has improved its ability for discovering information within a database that can then be used to support decisions. Data mining technology is a powerful AI tool that effectively extracts information from massive observational data sets as well as discovers new and meaningful knowledge for the user. This paper presents a neural based decision-learning (NDT) model which can obtain explicit information on the processing involved in generating predictions of oil production. In our experiment, the NDT model that uses a neural network to extract the underlying attribute dependencies was evaluated in comparison with the conventional C4.5 model on some historical data sets obtained from the oil fields in Saskatchewan, Canada. The results generated by the NDT model are found to be satisfactory.