US 12,282,129 B2
Geosteering interpretation using bayesian inference
Siyang Song, Humble, TX (US); Shahin Tasoujian, Houston, TX (US); Eirik Hansen, Sola (NO); Robert P. Darbe, Tomball, TX (US); and Vytautas Usaitis, The Woodlands, TX (US)
Assigned to Halliburton Energy Services, Inc., Houston, TX (US)
Filed by Halliburton Energy Services, Inc., Houston, TX (US)
Filed on Mar. 16, 2022, as Appl. No. 17/696,474.
Prior Publication US 2023/0296801 A1, Sep. 21, 2023
Int. Cl. G01V 1/50 (2006.01); G01V 1/46 (2006.01); G06N 5/022 (2023.01); G06N 5/025 (2023.01)
CPC G01V 1/50 (2013.01) [G01V 1/46 (2013.01); G06N 5/022 (2013.01); G06N 5/025 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
based on indication of a control point during propagation of a wellbore trajectory, via a bottom hole assembly through a formation:
generating, via a particle generator, a plurality of interpretations of the control point based, at least in part, on wellbore measurements corresponding to the control point;
for each interpretation of the plurality of interpretations, generating, via a pseudo log generator, a pseudo log based, at least in part, on the interpretation and historical well data;
determining posterior probabilities for the plurality of interpretations based, at least in part, on evaluation of pseudo logs against historical formation property measurements and a set of one or more rules based on knowledge of the formation;
updating a geological model to indicate the control point and with at least a subset of the plurality of interpretations based, at least in part, on the posterior probabilities; and
performing a geosteering operation based on the updated geological model.