Averaging Predictions of Rate-Time Models Using Bayesian Leave-Future-Out Cross-Validation and the Bayesian Bootstrap in Probabilistic Unconventional Production Forecasting

Leopoldo M. Ruiz Maraggi, Larry W. Lake, Mark P. Walsh

Unconventional Resources Technology Conference (URTEC)

... Cross-Validation We rarely have access to out-of-sample data (new realizations of the data). One attempt to capture outof-sample prediction error...

Physics-Constrained Deep Learning for Production Forecast in Tight Reservoirs

Nguyen T. Le, Roman J. Shor, Zhuoheng Chen

Unconventional Resources Technology Conference (URTEC)

... for multi-step ahead prediction, but the accumulation of error makes it more and more unstable as more and more estimated values of the target...

Using Bayesian Leave-One-Out and Leave-Future-Out Cross- Validation to Evaluate the Performance of Rate-Time Models to Forecast Production of Tight-Oil Wells

Leopoldo M. Ruiz Maraggi, Larry W. Lake, Mark P. Walsh

Unconventional Resources Technology Conference (URTEC)

...n (CV) One attempt to capture out-of-sample prediction error is by splitting the sample data set into training and testing (hold-out) sets. The model...

Machine Learning Approach to Improve Calculated Bottom-hole Pressure

Esmail Eltahan, Reza Ganjdanesh, Wei Yu, Kamy Sepehrnoori, Ryan Williams, Jack Nohavitsa

Unconventional Resources Technology Conference (URTEC)

... , 𝜎). 𝜎 is either inherited from the uncertainty model or defined based on the average error of the predictive method. If the replaced prediction violates...

Chapter 13: Linking Cognitive Science and Disciplinary Geoscience Practice: The Importance of the Conceptual Model

Thomas F. Shipley, Basil Tikoff

AAPG Special Volumes

...-section prediction error is reporting the perspective shape of the 3-D solid at the cut location (Cohen and Hegarty, 2014). Students often misunderstand...

Pilot Phase of the Aguada Federal Block, Black-Oil Window

Osvaldo Nielsen, David Curia, Pablo Pateti, Javier Caniggia, Alexis Ortega, Morten Slinde

AAPG Special Volumes

... that provides the best possible combination with the lowest prediction error (Figure 17). Seismic TOC prediction solely on density and compressional...

Multidisciplinary thermal maturity studies using vitrinite reflectance and fluid inclusion microthermometry: A new calibration of old techniques

Rick C. Tobin, Brenda L. Claxton

AAPG Bulletin

... is relatively constant from about 0.6 to 1.5% Ro, the actual prediction error is more significant at lower levels of thermal maturity than it is at higher levels...

Benchmarking exploration predictions and performance using 20+ yr of drilling results: One company’s experience

Kurt W. Rudolph, and Frank J. Goulding

AAPG Bulletin

... that exceeded 7% error, three were in areas of poor seismic imaging related to subsalt or onshore fold belts. Figure 18. Frequency plot of depth prediction...

Search and Discovery

Search and Discovery.com

Datapages - Browse by Author

Search and Discovery.com

Datapages - Browse by Date

Search and Discovery.com

3D Geostatistical Interpolation and Geological Interpretation of Paleo…Groundwater Rise in the Holocene Coastal Prism in the Netherlands

Kim M. Cohen

Special Publications of SEPM

... delta axis. B) Kriging prediction error (σK) for 6.0 kyr BP, indicating spatial distribution of interpolation quality. Low values occur closest around...

Chapter Nine: Inversion and Interpretation of Impedance Data

Rebecca B. Latimer

AAPG Special Volumes

... prediction-error: Geophysics, v. 61, p. 1575–1588. Aki, K., and P. G. Richards, 1980, Quantitative seismology, 1st edition: W. H. Freeman and Company, 2...