Reliable predictions of oil formation volume factor based on transparent and auditable machine learning approaches
Corresponding Author and Email:David A.Wood, dw@dwasolutions.com; ORCID: https://orcid.org/0000-0003-3202-4069
Citation:Wood, D.A., Choubineh, A. Reliable predictions of oil formation volume factor based on transparent and auditable machine learning approaches. Advances in Geo-Energy Research, 2019, 3(3): 225-241, doi: 10.26804/ager.2019.03.01.
Article Type:Original article
Abstract:
Neural-network, machine-learning algorithms are effective prediction tools but can behave as black boxes in many applications by not easily providing the exact calculations and relationships among the underlying input variables (which may or may not be independent of each other) involved each of their predictions. The transparent open box (TOB) learning network algorithm overcomes this limitation by providing the exact calculations involved in all its predictions and achieving acceptable and auditable levels of prediction accuracy. The TOB network, based on an optimized data-matching algorithm, can be applied in spreadsheet or fully-coded configurations. This algorithm offers significant benefits to analysis and prediction of many complex and difficult to measure non-linear systems. To demonstrate its prediction performance, the algorithm is applied to the prediction of crude oil formation volume factor at bubble point using published datasets of 166, 203 and 237 data records involving 4 variables (reservoir temperature, gas-oil ratio, oil gravity and gas specific gravity). Two of these datasets display uneven and irregular data coverage. The TOB network demonstrates high prediction accuracy (Root Mean Square Error (RMSE) ~ 0.03; R2 > 0.95) for the more evenly distributed dataset. The performance of the TOB readily reveals the risk of overfitting such datasets. With its high levels of transparency and inhibitions to being overfitted, the TOB learning network offers an insightful approach to machine learning applied to predicting complex non-linear systems. Its results complement and benchmark the prediction contributions of neural networks and empirical correlations. In doing so it provides further insight to the underlying data.
Keywords:Machine learning transparency, non-correlation-based machine learning, oil formation volume factor prediction, sparse data impacts, avoidance of overfitting.
Download this Manuscript:PDF
Download Supporting Information:FILE
