Real-time Formation Evaluation for Optimal Decision Making While Drilling&lt;subtitle&gt;Examples from the Southern North Sea&lt;/subtitle&gt;

Bristow, J. F.

doi:10.1306/mth13780c1

Cited by 5 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fast probabilistic inversion of geophysical data is specifically crucial for processing measurements during drilling since it opens the possibility to use probabilistic decision algorithms (Alyaev et al., 2019; Chen et al., 2015; Kullawan et al., 2018) to adjust the trajectory during operation, resulting in better well placement. The intentional adjustment of the drilling trajectory termed geosteering, is essential for hydrocarbon wells (Bristow, 2000), but is gradually introduced in other types of drilling, for example, geothermal (Ungemach et al., 2021) and civil wells and tunnels (Johnson et al., 2021).…”

Section: Introductionmentioning

confidence: 99%

“…While in some problems, it is possible to use regularization to find a single physically viable solution, for many keeping several likely solution modes and estimating their probabilities is useful.Fast probabilistic inversion of geophysical data is specifically crucial for processing measurements during drilling since it opens the possibility to use probabilistic decision algorithms (Alyaev et al, 2019;Chen et al, 2015;Kullawan et al, 2018) to adjust the trajectory during operation, resulting in better well placement. The intentional adjustment of the drilling trajectory termed geosteering, is essential for hydrocarbon wells (Bristow, 2000), but is gradually introduced in other types of drilling, for example, geothermal (Ungemach et al, 2021) and civil wells and tunnels (Johnson et al, 2021).The most widespread method is stratigraphic-based geosteering inversion, which assumes that the unknown geomodel can be represented as curved and possibly faulted geological layers (strata), and the geophysical log response only depends on the vertical position within the stratigraphy. For the inversion, the geophysical logs from a geosteered horizontal well and corresponding logs from an offset vertical well are projected onto the stratigraphic geomodel.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Direct Multi‐Modal Inversion of Geophysical Logs Using Deep Learning

Alyaev

Elsheikh

2022

Earth and Space Science

View full text Add to dashboard Cite

Geosteering of wells requires fast interpretation of geophysical logs which is a non‐unique inverse problem. Current work presents a proof‐of‐concept approach to multi‐modal probabilistic inversion of logs using a single evaluation of an artificial deep neural network (DNN). A mixture density DNN (MDN) is trained using the ”multiple‐trajectory‐prediction” loss functions, which avoids mode collapse typical for traditional MDNs, and allows multi‐modal prediction ahead of data. The proposed approach is verified on the real‐time stratigraphic inversion of gamma‐ray logs. The multi‐modal predictor outputs several likely inverse solutions/predictions, providing more accurate and realistic solutions compared to a deterministic regression using a DNN. For these likely stratigraphic curves, the model simultaneously predicts their probabilities, which are implicitly learned from the training geological data. The stratigraphy predictions and their probabilities obtained in milliseconds from the MDN can enable better real‐time decisions under geological uncertainties.

show abstract