Associative Model for the Forecasting of Time Series Based on the Gamma Classifier
The paper describes a novel associative model for the forecasting of time series in petroleum engineering. The model is based on the Gamma classifier, which is inspired on the Alpha-Beta associative memories, taking the alpha and beta operators as basis for the gamma operator. The objective is to reproduce and predict future oil production in different scenarios in an adjustable time window. The distinctive features of the experimental data set are spikes, abrupt changes and frequent discontinuities, which considerably decrease the precision of traditional forecasting methods. As experimental results show, this classifier-based predictor exhibits competitive performance. The advantages and limitations of the model, as well as lines of improvement, are discussed.
KeywordsTime series forcasting associative models oil production time series Gamma classifier
- 2.van Golf-Racht, T.D.: Fundamentals of Fractured Reservoir Engineering, Developments in Petroleum Science, vol. 12. Elsevier, Amsterdam (1982)Google Scholar
- 5.He, Z., Yang, L., Yen, J., Wu, C.: Neural-Network Approach to Predict Well Performance Using Available Field Data. In: SPE Western Regional Meeting, Bakersfield, California, March 26-30, SPE 68801 (2001)Google Scholar
- 7.Johnson, R.A., Wichern, D.W.: Applied Multivariate Statistical Analysis (Prentice Hall series in statistics), 5th edn. Prentice Hall (2001)Google Scholar
- 8.López-Yáñez, I., Argüelles-Cruz, A.J., Camacho-Nieto, O., Yáñez-Márquez, C.: Pollutants Time-Series Prediction Using the Gamma classifier. Int. J. of Computational Intelligence Systems 4(4), 680–711 (2011)Google Scholar