MX2022015868A - Metodo para predecir caracteristicas geologicas a partir de registros de imagenes de pozo. - Google Patents

Metodo para predecir caracteristicas geologicas a partir de registros de imagenes de pozo.

Info

Publication number
MX2022015868A
MX2022015868A MX2022015868A MX2022015868A MX2022015868A MX 2022015868 A MX2022015868 A MX 2022015868A MX 2022015868 A MX2022015868 A MX 2022015868A MX 2022015868 A MX2022015868 A MX 2022015868A MX 2022015868 A MX2022015868 A MX 2022015868A
Authority
MX
Mexico
Prior art keywords
borehole image
geological features
images
backpropagation
occurrence
Prior art date
Application number
MX2022015868A
Other languages
English (en)
Inventor
Aldea Oriol Falivene
Pedram Zarian
Original Assignee
Shell Int Research
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shell Int Research filed Critical Shell Int Research
Publication of MX2022015868A publication Critical patent/MX2022015868A/es

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V20/00—Geomodelling in general
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Geophysics (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

Un método para predecir una ocurrencia de una característica geológica en un registro de imágenes de pozo mediante el uso de un proceso activado por retropropagación entrenado al ingresar un conjunto de imágenes de entrenamiento (12) de un registro de imágenes de pozo, calcular iterativamente una predicción de la probabilidad de ocurrencia de la característica geológica para el conjunto de imágenes de entrenamiento y ajustar los parámetros en el modelo activado por retropropagación hasta que el modelo esté entrenado. El modelo activado por retropropagación entrenado se usa para predecir la ocurrencia de las características geológicas en registros de imágenes de pozo que no son de entrenamiento. El conjunto de imágenes de entrenamiento puede incluir características no geológicas y/o datos simulados, que incluyen imágenes ampliadas (22) e imágenes sintéticas (24).
MX2022015868A 2020-06-24 2021-06-22 Metodo para predecir caracteristicas geologicas a partir de registros de imagenes de pozo. MX2022015868A (es)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202063043655P 2020-06-24 2020-06-24
PCT/EP2021/066949 WO2021259912A1 (en) 2020-06-24 2021-06-22 Method for predicting geological features from borehole image logs

Publications (1)

Publication Number Publication Date
MX2022015868A true MX2022015868A (es) 2023-01-24

Family

ID=76796932

Family Applications (1)

Application Number Title Priority Date Filing Date
MX2022015868A MX2022015868A (es) 2020-06-24 2021-06-22 Metodo para predecir caracteristicas geologicas a partir de registros de imagenes de pozo.

Country Status (5)

Country Link
US (1) US20230222773A1 (es)
EP (1) EP4172664A1 (es)
BR (1) BR112022025927A2 (es)
MX (1) MX2022015868A (es)
WO (1) WO2021259912A1 (es)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024100220A1 (en) 2022-11-10 2024-05-16 Shell Internationale Research Maatschappij B.V. Method for predicting fault seal behaviour

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170286802A1 (en) 2016-04-01 2017-10-05 Saudi Arabian Oil Company Automated core description
AU2017305417B2 (en) * 2016-08-03 2023-06-15 Geoquest Systems B.V. Multi-scale deep network for fault detection
EP3682271B1 (en) * 2017-09-12 2024-02-14 Services Pétroliers Schlumberger Seismic image data interpretation system
CN109389128B (zh) 2018-08-24 2021-08-27 中国石油天然气股份有限公司 电成像测井图像特征自动提取方法及装置
AU2019367605A1 (en) 2018-10-25 2021-03-11 Chevron U.S.A. Inc. System and method for quantitative analysis of borehole images
US20210089897A1 (en) * 2019-09-24 2021-03-25 Quantico Energy Solutions Llc High-resolution earth modeling using artificial intelligence

Also Published As

Publication number Publication date
EP4172664A1 (en) 2023-05-03
BR112022025927A2 (pt) 2023-03-14
WO2021259912A1 (en) 2021-12-30
US20230222773A1 (en) 2023-07-13

Similar Documents

Publication Publication Date Title
US11449684B2 (en) Contrastive pre-training for language tasks
WO2018170035A8 (en) Collaborative sensing and prediction of source rock properties
EP3846109A3 (en) Method and apparatus for training online prediction model, device and storage medium
CN109271643A (zh) 一种翻译模型的训练方法、翻译方法和装置
ZA202007714B (en) System and method for real time prediction of water level and hazard level of a dam
WO2020123100A3 (en) Automated seismic interpretation systems and methods for continual learning and inference of geological features
CN107836000A (zh) 用于语言建模和预测的改进的人工神经网络
Tsai et al. First-break automatic picking with deep semisupervised learning neural network
GB2602920A (en) Deep learning seismic attribute fault predictions
GB2617722A (en) Generating data based on pre-trained models using generative adversarial models
US11669056B2 (en) Generation of a control system for a target system
EP4116861A3 (en) Method and apparatus for pre-training semantic representation model and electronic device
EP4310620A3 (en) Hybrid ensemble approach for iot predictive modelling
MX2022015868A (es) Metodo para predecir caracteristicas geologicas a partir de registros de imagenes de pozo.
Montenegro et al. Analysis of the sensitivity of the End-Of-Turn Detection task to errors generated by the Automatic Speech Recognition process
Tian et al. BEBERT: Efficient and robust binary ensemble BERT
WO2022075678A3 (ko) 의사 정상 데이터를 이용한 자가 감독 학습 기반의 차량 이상징후 탐지 장치 및 방법
CN108764026B (zh) 一种基于时序检测单元预筛选的视频行为检测方法
GB2624950A (en) System and method for diagnosing borehole structure variances using independent component analysis
MX2022011830A (es) Metodo para predecir caracteristicas geologicas a partir de imagenes de nucleos geologicos usando un proceso de segmentacion de aprendizaje profundo.
MX2021012019A (es) Deteccion rapida de fusiones genicas.
RU2600099C1 (ru) Способ нейросетевого прогнозирования изменения значений функции с её предварительной вейвлет-обработкой и устройство его осуществления
WO2023014298A3 (zh) 神经网络模型的构建方法及装置
MX2022015893A (es) Metodo para predecir caracteristicas estructurales a partir de imagenes de nucleo.
MX2023012700A (es) Metodo para predecir las caracteristicas geologicas a partir de imagenes de seccion delgada por medio de un proceso de clasificacion de aprendizaje profundo.