US 11,854,259 B2
Holdup measurement using quantized classification and categorized local regression
Mayir Mamtimin, Spring, TX (US); Jeffrey James Crawford, Katy, TX (US); and Weijun Guo, Houston, TX (US)
Assigned to HALLIBURTON ENERGY SERVICES, INC., Houston, TX (US)
Filed by HALLIBURTON ENERGY SERVICES, INC., Houston, TX (US)
Filed on Dec. 30, 2021, as Appl. No. 17/565,927.
Claims priority of provisional application 63/168,669, filed on Mar. 31, 2021.
Prior Publication US 2022/0319166 A1, Oct. 6, 2022
Int. Cl. G06V 10/82 (2022.01); G01V 5/12 (2006.01); E21B 47/003 (2012.01); G06V 10/766 (2022.01); G06V 20/10 (2022.01)
CPC G06V 20/194 (2022.01) [E21B 47/003 (2020.05); G01V 5/12 (2013.01); G06V 10/766 (2022.01); G06V 10/82 (2022.01); E21B 2200/22 (2020.05)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
accessing a spectral image associated with a gamma spectrum generated downhole in a wellbore;
classifying a component of a holdup measurement for the wellbore into a specific quantized level of a plurality of quantized levels of holdup measurements through application of a machine learning classification model to the spectral image; and
quantifying a continuous value for the component of the holdup measurement for the wellbore based on a machine learning quantification model associated with the specific quantized level.