Feedback
Settings

Settings

Goto Application

1. WO2022093506 - CONFIDENCE VOLUMES FOR EARTH MODELING USING MACHINE LEARNING

Submit observation
PermaLink
Publication Number WO/2022/093506
Publication Date 05.05.2022
International Application No. PCT/US2021/053827
International Filing Date 06.10.2021
IPC
G01V 1/50 2006.1
GPHYSICS
01MEASURING; TESTING
VGEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
1Seismology; Seismic or acoustic prospecting or detecting
40specially adapted for well-logging
44using generators and receivers in the same well
48Processing data
50Analysing data
E21B 41/00 2006.1
EFIXED CONSTRUCTIONS
21EARTH OR ROCK DRILLING; MINING
BEARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
41Equipment or details not covered by groups E21B15/-E21B40/95
G01V 99/00 2009.1
GPHYSICS
01MEASURING; TESTING
VGEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
99Subject matter not provided for in other groups of this subclass
G06N 3/04 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
CPC
E21B 2200/20
EFIXED CONSTRUCTIONS
21EARTH DRILLING; MINING
BEARTH DRILLING, e.g. DEEP DRILLING
2200Special features related to earth drilling for obtaining oil, gas or water
20Computer models or simulations, e.g. for reservoirs under production, drill bits
E21B 2200/22
EFIXED CONSTRUCTIONS
21EARTH DRILLING; MINING
BEARTH DRILLING, e.g. DEEP DRILLING
2200Special features related to earth drilling for obtaining oil, gas or water
22Fuzzy logic, artificial intelligence, neural networks or the like
E21B 44/02
EFIXED CONSTRUCTIONS
21EARTH DRILLING; MINING
BEARTH DRILLING, e.g. DEEP DRILLING
44Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems
02Automatic control of the tool feed
E21B 49/00
EFIXED CONSTRUCTIONS
21EARTH DRILLING; MINING
BEARTH DRILLING, e.g. DEEP DRILLING
49Testing the nature of borehole walls; Formation testing; Methods or apparatus for obtaining samples of soil or well fluids, specially adapted to earth drilling or wells
G01V 1/50
GPHYSICS
01MEASURING; TESTING
VGEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
1Seismology; Seismic or acoustic prospecting or detecting
40specially adapted for well-logging
44using generators and receivers in the same well
48Processing data
50Analysing data
G01V 2210/667
GPHYSICS
01MEASURING; TESTING
VGEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
2210Details of seismic processing or analysis
60Analysis
66Subsurface modeling
667Determining confidence or uncertainty in parameters
Applicants
  • QUANTICO ENERGY SOLUTIONS LLC [US]/[US]
Inventors
  • ZHANG, Barry F.
  • DE JESUS, Orlando
  • SANSAL, Tuna Altay
  • TIAN, Edward
Agents
  • PATTERSON, William B.
  • MOORE, Eric
Priority Data
17/082,39928.10.2020US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) CONFIDENCE VOLUMES FOR EARTH MODELING USING MACHINE LEARNING
(FR) VOLUMES DE CONFIANCE POUR MODELAGE DU TERRAIN À L'AIDE D'UN APPRENTISSAGE MACHINE
front page image
Abstract
(EN) Aspects of the present disclosure relate to confidence volumes for earth modeling using machine learning. A method includes receiving detected data, wherein the detected data includes formation attributes relating to one or more depth points along or near a wellbore. The method further includes providing inputs to a plurality of machine learning models based on the detected data. The method further includes receiving output values from the plurality of machine learning models based on the inputs. The method further includes determining a measure of variance among the output values. The method further includes generating a confidence indicator related to the output values based on the measure of variance.
(FR) Des aspects de la présente invention concernent des volumes de confiance pour modelage du terrain à l'aide d'un apprentissage machine. Un procédé consiste à recevoir des données détectées, les données détectées comprenant des attributs de formation concernant un ou plusieurs points de profondeur le long ou près d'un puits de forage. Le procédé consiste en outre à fournir des entrées à une pluralité de modèles d'apprentissage machine sur la base des données détectées. Le procédé consiste en outre à recevoir des valeurs de sortie provenant de la pluralité de modèles d'apprentissage machine sur la base des entrées. Le procédé consiste en outre à déterminer une mesure de variance parmi les valeurs de sortie. Le procédé consiste en outre à générer un indicateur de confiance se rapportant aux valeurs de sortie sur la base de la mesure de variance.
Related patent documents
US20220129788
Latest bibliographic data on file with the International Bureau
# -