An important technique for estimating future oil well production is Decline Curve Analysis (DCA).
But in practice, deterministic predictions of future declines are often inaccurate, as they are based on multiple assumptions and restrictions.
Therefore, exploration and production (E&P) companies miss many opportunities to capitalize on real-time market conditions.
- To increase the accuracy of production forecasting, different AI models were trained and compared.
- Eight critical influencing parameters are considered as input factors to build the model.
- Models were trained using 80% of all data generated through simulation while 20% was used for testing the models.
- Results show that RSM and LSSVM have very accurate oil recovery forecasting capabilities.