# US 11,994,647 B2 · Compensated formation saturation using assisted physics and neural networks > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,994,647 B2 - Document ID: US11994647B2 - Status: Granted - Kind: B2 - Application number: 17/550,588 - Filed: 2021-12-14 - Published: 2023-06-15 - Granted: 2024-05-28 - Earliest claimed: 2021-12-14 - Assignees: Halliburton Energy Services, Inc. - Applicants: Halliburton Energy Services, Inc. - Inventors: Mayir Mamtimin; Jeffrey James Crawford; Weijun Guo - Web page: https://patentgrep.com/patent/US11994647B2 ## CPC - G01V 5/101: {and detecting the secondary Y-rays produced in the surrounding layers of the bore hole} - G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02) ## Abstract Aspects of the subject technology relate to determining holdup compensated formation saturation while refraining from calculating holdup. Inelastic gamma spectrum data for an inelastic gamma spectrum generated downhole in a wellbore can be accessed. Further, capture gamma spectrum data for one or more capture gamma spectrums generated downhole in the wellbore can be accessed. A model that accounts for holdup measurement can be applied to both the inelastic gamma spectrum data and the capture gamma spectrum data to identify a compensated oil saturation for a formation surrounding at least a portion of the wellbore based on both the inelastic gamma spectrum and the one or more capture gamma spectrums. ## Claims ### Claim 1 A method comprising: accessing inelastic gamma spectrum data for an inelastic gamma spectrum generated downhole in a wellbore; accessing capture gamma spectrum data for one or more capture gamma spectrums generated downhole in the wellbore; applying a model that accounts for holdup measurement to both the inelastic gamma spectrum data and the capture gamma spectrum data to identify a compensated oil saturation for a formation surrounding at least a portion of the wellbore based on both the inelastic gamma spectrum and the one or more capture gamma spectrums. ### Claim 2 (depends on 1) The method of claim 1, wherein the model is applied to identify the compensated oil saturation without actually calculating the holdup measurement. ### Claim 3 (depends on 2) The method of claim 2, wherein the model is applied to identify the compensated oil saturation without compensating either or both the inelastic gamma spectrum data and the capture gamma spectrum data with a calculated holdup measurement to identify the compensated oil saturation. ### Claim 4 (depends on 1) The method of claim 1, wherein the model is an assisted-physics based model. ### Claim 5 (depends on 4) The method of claim 4, wherein the assisted-physics based model is generated based on inelastic gamma spectrums induced by one or more radiation sources in one or more wellbores, capture gamma spectrums induced by the one or more radiation sources in the one or more wellbores, and characteristics of radiation generated by the one or more radiation sources to induce the inelastic gamma spectrums and the capture gamma spectrums. ### Claim 6 (depends on 5) The method of claim 5, wherein the assisted-physics based model is generated based on known characteristics of one or more formations surrounding the one or more wellbores, known characteristics of the one or more wellbores, and known characteristics of the one or more radiation sources. ### Claim 7 (depends on 6) The method of claim 6, wherein the assisted-physics based model is generated by constructing a correlation between the inelastic gamma spectrums, the capture gamma spectrums, and the characteristics of the radiation emitted by the one or more radiation source based on: the known characteristics of the one or more formations; the known characteristics of the one or more wellbores; and the known characteristics of the one or more radiation sources. ### Claim 8 (depends on 1) The method of claim 1, wherein the model is a machine learning model that is generated based on inelastic gamma spectrums induced by one or more radiation sources in one or more wellbores, capture gamma spectrums induced by the one or more radiation sources in the one or more wellbores, and characteristics of radiation emitted by the one or more radiation sources to induce the inelastic gamma spectrums and the capture gamma spectrums. ### Claim 9 (depends on 1) The method of claim 1, wherein the inelastic gamma spectrum data and the capture gamma spectrum data is generated by a plurality of detectors disposed in the wellbore. ### Claim 10 (depends on 1) The method of claim 1, wherein the capture gamma spectrum data includes either or both a time-instance spectrum and a time-decay spectrum of capture gamma measurements. ### Claim 11 A system comprising: one or more processors; and a computer-readable medium comprising instructions stored therein, which when executed by the one or more processors, cause the one or more processors to: access inelastic gamma spectrum data for an inelastic gamma spectrum generated downhole in a wellbore; access capture gamma spectrum data for one or more capture gamma spectrums generated downhole in the wellbore; and apply a model that accounts for holdup measurement to both the inelastic gamma spectrum data and the capture gamma spectrum data to identify a compensated oil saturation for a formation surrounding at least a portion of the wellbore based on both the inelastic gamma spectrum and the one or more capture gamma spectrums. ### Claim 12 (depends on 11) The system of claim 11, wherein the model is applied to identify the compensated oil saturation without actually calculating the holdup measurement. ### Claim 13 (depends on 12) The system of claim 12, wherein the model is applied to identify the compensated oil saturation without compensating either or both the inelastic gamma spectrum data and the capture gamma spectrum data with a calculated holdup measurement to identify the compensated oil saturation. ### Claim 14 (depends on 11) The system of claim 11, wherein the model is an assisted-physics based model. ### Claim 15 (depends on 14) The system of claim 14, wherein the assisted-physics based model is generated based on inelastic gamma spectrums induced by one or more radiation sources in one or more wellbores, capture gamma spectrums induced by the one or more radiation sources in the one or more wellbores, and characteristics of radiation emitted by the one or more radiation sources to induce the inelastic gamma spectrums and the capture gamma spectrums. ### Claim 16 (depends on 15) The system of claim 15, wherein the assisted-physics based model is generated by constructing a correlation between the inelastic gamma spectrums, the capture gamma spectrums, and the characteristics of the radiation emitted by the one or more radiation source based on: known characteristics of the one or more formations; known characteristics of the one or more wellbores; and known characteristics of the one or more radiation sources. ### Claim 17 (depends on 11) The system of claim 11, wherein the model is a machine learning model that is generated based on inelastic gamma spectrums induced by one or more radiation sources in one or more wellbores, capture gamma spectrums induced by the one or more radiation sources in the one or more wellbores, and characteristics of radiation emitted by the one or more radiation sources to induce the inelastic gamma spectrums and the capture gamma spectrums. ### Claim 18 (depends on 11) The system of claim 11, wherein the inelastic gamma spectrum data and the capture gamma spectrum data is generated by a plurality of detectors disposed in the wellbore. ### Claim 19 (depends on 11) The system of claim 11, wherein the capture gamma spectrum data includes either or both a time-instance spectrum and a time-decay spectrum of capture gamma measurements. ### Claim 20 A gamma ray detector system comprising: a downhole gamma ray detector; and a processing unit configured to: access inelastic gamma spectrum data for an inelastic gamma spectrum generated downhole in a wellbore through the gamma ray detector; access capture gamma spectrum data for one or more capture gamma spectrums generated downhole in the wellbore through the gamma ray detector; and apply a model that accounts for holdup measurement to both the inelastic gamma spectrum data and the capture gamma spectrum data to identify a compensated oil saturation for a formation surrounding at least a portion of the wellbore based on both the inelastic gamma spectrum and the one or more capture gamma spectrums.