Machine Learning in Computer Vision Software for Geomechanics Modeling

2021 ◽  
Author(s):  
Abdelwahab Noufal ◽  
Jaijith Sreekantan ◽  
Rachid Belmeskine ◽  
Mohamed Amri ◽  
Abed Benaichouche
Keyword(s):  
Machine Learning ◽  
Data Gathering ◽  
In Situ Stress ◽  
Effective Field ◽  
Rock Properties ◽  
Earth Model ◽  
Transient Effects ◽  
Rock Interaction ◽  
Wellbore Instability ◽  
Detail Design

Abstract AI-GEM (Artificial Intelligence of Geomechanics Earth Modelling) tool aims to detect the geomechanical features, especially the elastic parameters and stresses. Characterizing the wellbore instability issues is one of the factors increases cost of drilling and creating an AI-based tool will enhance and present a real-time solution for wellbore instability. These features are usually interpreted manually, depending on the experience and usually impacted by inconsistencies due to biased or unexperienced interpreters. Therefore, there is a need for a robust automatic or semiautomatic approach to reduce time, manual efficiency and consistency. The range of Geomechanics issues is wide and interfaces with many other upstream disciplines (e.g., Petrophysics, Geophysics, Production Geology, Drilling and Reservoir Engineering). Safe and effective field operation is built on the understanding and implementation of the subsurface in-situ stress state throughout the life of the field; the quantification of key subsurface uncertainties through well thought-out data gathering and characterization programs. The integration with appropriate Geomechanics modelling and the field surveillance /monitoring strategy. There are two major aspects that must be addressed during the design phase of any Geomechanics project. The first and most important is developing a realistic estimate of the expected mechanical behaviour of the rocks and its potential response as a result of drilling. The second is to design an economic, safe well and support method for the determined rocks behaviour. The design process begins with the feasibility study followed by preliminary design, the detail design, tender design and throughout the construction. The design is constantly updated during each phase as more information becomes available and this requires the involvement of Geologists, Engineers and Subject Matter Expert throughout the phases of a project. A central concern for all geomechanical designs is the well-rock interaction, which is not only includes the final state but also the transient effects of the well processes as well as time and stress of the dependent rock properties. The end-to-end workflow to achieve the mechanical earth model is automated, guided and orchestrated with the help of machine learning framework such as recommendation engine for offset well data, prediction of well logs, and optimization for all calibration with existing test results, enabling end users to run sensitivity and scenario analysis so on and so forth.

scholarly journals HealthTEC Innovation Design - a proposal for a novel Master degree program based on Unmet Clinical Need, global Healthcare Challenges, and 21st century skills

2020 ◽  
Vol 6 (3) ◽  
pp. 599-603
Author(s):  
Michael Friebe
Keyword(s):  
Machine Learning ◽  
21St Century ◽  
21St Century Skills ◽  
Data Analytics ◽  
Industrial Revolution ◽  
Data Gathering ◽  
Healthcare Systems ◽  
Disruptive Innovation ◽  
Incremental Innovation ◽  
Healthcare Provision

AbstractThe effectiveness, efficiency, availability, agility, and equality of global healthcare systems are in question. The COVID-19 pandemic have further highlighted some of these issues and also shown that healthcare provision is in many parts of the world paternalistic, nimble, and often governed too extensively by revenue and profit motivations. The 4th industrial revolution - the machine learning age - with data gathering, analysis, optimisation, and delivery changes has not yet reached Healthcare / Health provision. We are still treating patients when they are sick rather then to use advanced sensors, data analytics, machine learning, genetic information, and other exponential technologies to prevent people from becoming patients or to help and support a clinicians decision. We are trying to optimise and improve traditional medicine (incremental innovation) rather than to use technologies to find new medical and clinical approaches (disruptive innovation). Education of future stakeholders from the clinical and from the technology side has not been updated to Health 4.0 demands and the needed 21st century skills. This paper presents a novel proposal for a university and innovation lab based interdisciplinary Master education of HealthTEC innovation designers.

Risk-Controlled Wellbore Stability Criterion Based on Machine Learning Assisted Finite Element Model

2021 ◽  
Author(s):  
Hussain AlBahrani ◽  
Nobuo Morita
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Finite Element ◽  
Finite Element Model ◽  
Stability Criterion ◽  
Element Model ◽  
Rock Failure ◽  
Wellbore Stability ◽  
Wellbore Instability ◽  
Conventional Methods

Abstract In many drilling scenarios that include deep wells and highly stressed environments, the mud weight required to completely prevent wellbore instability can be impractically high. In such cases, what is known as risk-controlled wellbore stability criterion is introduced. This criterion allows for a certain level of wellbore instability to take place. This means that the mud weight calculated using this criterion will only constrain wellbore instability to a certain manageable level, hence the name risk-controlled. Conventionally, the allowable level of wellbore instability in this type of models has always been based on the magnitude of the breakout angle. However, wellbore enlargements, as seen in calipers and image logs, can be highly irregular in terms of its distribution around the wellbore. This irregularity means that risk-controlling the wellbore instability through the breakout angle might not be always sufficient. Instead, the total volume of cavings is introduced as the risk control parameter for wellbore instability. Unlike the breakout angle, the total volume of cavings can be coupled with a suitable hydraulics model to determine the threshold of manageable instability. The expected total volume of cavings is determined using a machine learning (ML) assisted 3D elasto-plastic finite element model (FEM). The FEM works to model the interval of interest, which eventually provides a description of the stress distribution around the wellbore. The ML algorithm works to learn the patterns and limits of rock failure in a supervised training manner based on the wellbore enlargement seen in calipers and image logs from nearby offset wells. Combing the FEM output with the ML algorithm leads to an accurate prediction of shear failure zones. The model is able to predict both the radial and circumferential distribution of enlargements at any mud weight and stress regime, which leads to a determination of the expected total volume of cavings. The model implementation is first validated through experimental data. The experimental data is based on true-triaxial tests of bored core samples. Next, a full dataset from offset wells is used to populate and train the model. The trained model is then used to produce estimations of risk-controlled stability mud weights for different drilling scenarios. The model results are compared against those produced by conventional methods. Finally, both the FEM-ML model and the conventional methods results are compared against the drilling experience of the offset wells. This methodology provides a more comprehensive and new solution to risk controlling wellbore instability. It relies on a novel process which learns rock failure from calipers and image logs.

The Convergence of IoT, Machine Learning, and Big Data for Advancing Flood Analytics Knowledge  

2021 ◽  
Author(s):  
Vidya Samadi ◽  
Rakshit Pally
Keyword(s):  
Machine Learning ◽  
Big Data ◽  
Language Processing ◽  
Situational Awareness ◽  
Critical Infrastructure ◽  
Probability Distributions ◽  
Data Gathering ◽  
Flood Frequency ◽  
Flood Frequency Analysis ◽  
Crowd Intelligence

<p>Floods are among the most destructive natural hazard that affect millions of people across the world leading to severe loss of life and damage to property, critical infrastructure, and agriculture. Internet of Things (IoTs), machine learning (ML), and Big Data are exceptionally valuable tools for collecting the catastrophic readiness and countless actionable data. The aim of this presentation is to introduce Flood Analytics Information System (FAIS) as a data gathering and analytics system.  FAIS application is smartly designed to integrate crowd intelligence, ML, and natural language processing of tweets to provide warning with the aim to improve flood situational awareness and risk assessment. FAIS has been Beta tested during major hurricane events in US where successive storms made extensive damage and disruption. The prototype successfully identifies a dynamic set of at-risk locations/communities using the USGS river gauge height readings and geotagged tweets intersected with watershed boundary. The list of prioritized locations can be updated, as the river monitoring system and condition change over time (typically every 15 minutes).  The prototype also performs flood frequency analysis (FFA) using various probability distributions with the associated uncertainty estimation to assist engineers in designing safe structures. This presentation will discuss about the FAIS functionalities and real-time implementation of the prototype across south and southeast USA. This research is funded by the US National Science Foundation (NSF).</p>

Machine Learning for Multiple Petrophysical Properties Regression Based on Core Images and Well Logs in a Heterogenous Reservoir

2021 ◽  
Author(s):  
Tao Lin ◽  
Mokhles Mezghani ◽  
Chicheng Xu ◽  
Weichang Li
Keyword(s):  
Machine Learning ◽  
Model Building ◽  
Image Features ◽  
Well Logs ◽  
Model Complexity ◽  
Rock Properties ◽  
Core Analysis ◽  
Petrophysical Properties ◽  
Blind Test ◽  
Porosity And Permeability

Abstract Reservoir characterization requires accurate prediction of multiple petrophysical properties such as bulk density (or acoustic impedance), porosity, and permeability. However, it remains a big challenge in heterogeneous reservoirs due to significant diagenetic impacts including dissolution, dolomitization, cementation, and fracturing. Most well logs lack the resolution to obtain rock properties in detail in a heterogenous formation. Therefore, it is pertinent to integrate core images into the prediction workflow. This study presents a new approach to solve the problem of obtaining the high-resolution multiple petrophysical properties, by combining machine learning (ML) algorithms and computer vision (CV) techniques. The methodology can be used to automate the process of core data analysis with a minimum number of plugs, thus reducing human effort and cost and improving accuracy. The workflow consists of conditioning and extracting features from core images, correlating well logs and core analysis with those features to build ML models, and applying the models on new cores for petrophysical properties predictions. The core images are preprocessed and analyzed using color models and texture recognition, to extract image characteristics and core textures. The image features are then aggregated into a profile in depth, resampled and aligned with well logs and core analysis. The ML regression models, including classification and regression trees (CART) and deep neural network (DNN), are trained and validated from the filtered training samples of relevant features and target petrophysical properties. The models are then tested on a blind test dataset to evaluate the prediction performance, to predict target petrophysical properties of grain density, porosity and permeability. The profile of histograms of each target property are computed to analyze the data distribution. The feature vectors are extracted from CV analysis of core images and gamma ray logs. The importance of each feature is generated by CART model to individual target, which may be used to reduce model complexity of future model building. The model performances are evaluated and compared on each target. We achieved reasonably good correlation and accuracy on the models, for example, porosity R2=49.7% and RMSE=2.4 p.u., and logarithmic permeability R2=57.8% and RMSE=0.53. The field case demonstrates that inclusion of core image attributes can improve petrophysical regression in heterogenous reservoirs. It can be extended to a multi-well setting to generate vertical distribution of petrophysical properties which can be integrated into reservoir modeling and characterization. Machine leaning algorithms can help automate the workflow and be flexible to be adjusted to take various inputs for prediction.

scholarly journals A Sound-based Machine Learning to Predict Traffic Vehicle Density

2021 ◽  
Vol 9 (1) ◽  
pp. 55-62
Author(s):  
Geoferleen Flores ◽  
◽  
Eduardo Jr. Piedad ◽  
Anzeneth Figueroa ◽  
Romari Tumamak ◽  
...  
Keyword(s):  
Machine Learning ◽  
Traffic Flow ◽  
Data Gathering ◽  
Sound Intensity ◽  
Support Vector ◽  
Mean Square ◽  
Significant Challenge ◽  
Vehicle Density ◽  
Smart Technologies ◽  
Machine Learning Models

Traffic flow mismanagement is a significant challenge in all countries especially in crowded cities. An alternative solution is to utilize smart technologies to predict traffic flow. In this study, frequency spectrum describing traffic sound characteristics is used as an indicator to predict the next five-minute vehicle density. Sound frequency and vehicle intensity are collected during a thirteen-hour data gathering. The collected sound intensity and frequency are then used to learn three machine-learning models - support vector machine, artificial neural network, and random forest and to predict vehicle intensity. It was found out that the performances of the three models based on root-mean-square-error values are 12.97, 16.01, and 10.67, respectively. These initial and satisfactory results pave a new way to predict traffic flow based on traffic sound characteristics which may serve as a better alternative to conventional features.

Application of Computational Intelligence in Generating Synthetic Reservoir Rock Mechanical Parameters for Building Geo-Models.

2015 ◽  
Author(s):  
L. C. Akubue ◽  
A.. Dosunmu ◽  
F. T. Beka
Keyword(s):  
Neural Network ◽  
Statistical Analysis ◽  
Numerical Models ◽  
Petroleum Industry ◽  
Oil Field ◽  
Wellbore Stability ◽  
Reservoir Rock ◽  
Rock Properties ◽  
Earth Model ◽  
Sonic Log

Abstract Oil field Operations such as wellbore stability Management and variety of other activities in the upstream petroleum industry require geo-mechanical models for their analysis. Sometimes, the required subsurface measurements used to estimate rock parameters for building such models are unavailable. On this premise, past studies have offered variety of methods and investigative techniques such as empirical correlations, statistical analysis and numerical models to generate these data from available information. However, the complexity of the relationships that exists between the natural occurring variables make the aforementioned techniques limited. This work involves the application of Artificial Neural Networks (ANNs) to generating rock properties. A three-layer back-propagation neural network model was applied predicting pseudo-sonic data using conventional wireline log data as input. Four well data from a Niger-Delta field were used in this study, one for training, one for validating and the two others for generating and testing results. The network was trained with different sets of initial random weights and biases using various learning algorithms. Root mean square error (RMSE) and correlation coefficient (CC) were used as key performance indicators. This Neural-Network-Generated-Sonic-log was compared with those generated with existing correlations and statistical analysis. The results showed that the most influential input vectors with various configurations for predicting sonic log were Depth-Resistivity-Gamma ray-Density (with correlating coefficient between 0.7 and 0.9). The generated sonic was subsequently used to compute for other elastic properties needed to build mechanical earth model for evaluating the strength properties of drilled formations, hence optimise drilling performance. The models are useful in Minimizing well cost, as well as reducing Non Productive Time (NPT) caused by wellbore instability. This technique is particularly useful for mature fields, especially in situations where obtaining this well logs are usually not practicable.

Combining Machine Learning and Classic Drilling Theories to Improve Rate of Penetration Prediction

2021 ◽  
Author(s):  
Hongbao Zhang ◽  
Baoping Lu ◽  
Lulu Liao ◽  
Hongzhi Bao ◽  
Zhifa Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Processing ◽  
Cost Estimation ◽  
Linear Process ◽  
Parameters Optimization ◽  
Data Driven ◽  
Rock Properties ◽  
Rate Of Penetration ◽  
Modelling Method ◽  
Drilling Parameters

Abstract Theoretically, rate of penetration (ROP) model is the basic to drilling parameters design, ROP improvement tools selection and drill time & cost estimation. Currently, ROP modelling is mainly conducted by two approaches: equation-based approach and machine learning approach, and machine learning performs better because of the capacity in high-dimensional and non-linear process modelling. However, in deep or deviated wells, the ROP prediction accuracy of machine learning is always unsatisfied mainly because the energy loss along the wellbore and drill string is non-negligible and it's difficult to consider the effect of wellbore geometry in machine learning models by pure data-driven methods. Therefore, it's necessary to develop robust ROP modelling method for different scenarios. In the paper, the performance of several equation-based methods and machine learning methods are evaluated by data from 82 wells, the technical features and applicable scopes of different methods are analysed. A new machine learning based ROP modelling method suitable for different well path types was proposed. Integrated data processing pipeline was designed to dealing with data noises, data missing, and discrete variables. ROP effecting factors were analysed, including mechanical parameters, hydraulic parameters, bit characteristics, rock properties, wellbore geometry, etc. Several new features were created by classic drilling theories, such as downhole weight on bit (DWOB), hydraulic impact force, formation heterogeneity index, etc. to improve the efficiency of learning from data. A random forest model was trained by cross validation and hyperparameters optimization methods. Field test results shows that the model could predict the ROP in different hole sections (vertical, deviated and horizontal) and different drilling modes (sliding and rotating drilling) and the average accuracy meets the requirement of well planning. A novel data processing and feature engineering workflow was designed according the characteristics of ROP modelling in different well path types. An integrated data-driven ROP modelling and optimization software was developed, including functions of mechanical specific energy analysis, bit wear analysis and predict, 2D & 3D ROP sensitivity analysis, offset wells benchmark, ROP prediction, drilling parameters constraints analysis, cost per meter prediction, etc. and providing quantitative evidences for drilling parameters optimization, drilling tools selection and well time estimation.

3D seismic imaging of volcanogenic massive sulfide deposits in the Flin Flon mining camp, Canada: Part 2 — Forward modeling

Geophysics ◽  
2012 ◽  
Vol 77 (5) ◽  
pp. WC81-WC93 ◽  
Author(s):  
Michal Malinowski ◽  
Ernst Schetselaar ◽  
Donald J. White
Keyword(s):  
Synthetic Data ◽  
Massive Sulfide ◽  
Ore Deposits ◽  
Earth Model ◽  
Seismic Modeling ◽  
Volcanogenic Massive Sulfide ◽  
Data Set ◽  
Rock Interaction ◽  
Time Migration ◽  
Flin Flon

We applied seismic modeling for a detailed 3D geologic model of the Flin Flon mining camp (Canada) to address some imaging and interpretation issues related to a [Formula: see text] 3D survey acquired in the camp and described in a complementary paper (part 1). A 3D geologic volumetric model of the camp was created based on a compilation of geologic data constraints from drillholes, surface geologic mapping, interpretation of 2D seismic profiles, and 3D surface and grid geostatistical modeling techniques. The 3D modeling methodology was based on a hierarchical approach to account for the heterogeneous spatial distribution of geologic constraints. Elastic parameters were assigned within the model based on core sample measurements and correlation with the different lithologies. The phase-screen algorithm used for seismic modeling was validated against analytic and finite-difference solutions to ensure that it provided accurate amplitude-variation-with-offset behavior for dipping strata. Synthetic data were generated to form zero-offset (stack) volume and also a complete prestack data set using the geometry of the real 3D survey. We found that the ability to detect a clear signature of the volcanogenic massive sulfide with ore deposits is dependent on the mineralization type (pyrite versus pyrrhotite rich ore), especially when ore-host rock interaction is considered. In the presence of an increasing fraction of the host rhyolite rock within the model volume, the response from the lower impedance pyrrhotite ore is masked by that of the rhyolite. Migration tests showed that poststack migration effectively enhances noisy 3D DMO data and provides comparable results to more computationally expensive prestack time migration. Amplitude anomalies identified in the original 3D data, which were not predicted by our modeling, could represent potential exploration targets in an undeveloped part of the camp, assuming that our a priori earth model is sufficiently accurate.

APPLICATION OF GUIDELINE CHARTS IN DECISIONMAKING ON WELL TRAJECTORY AND MUD WEIGHT PROGRAM

2001 ◽  
Vol 41 (1) ◽  
pp. 609
Author(s):  
X. Chen ◽  
C.P. Tan ◽  
C.M. Haberfield
Keyword(s):  
Stability Analysis ◽  
Case Studies ◽  
In Situ Stress ◽  
Wellbore Stability ◽  
Material Strength ◽  
Stress Regime ◽  
Wellbore Instability ◽  
Well Trajectory

To prevent or minimise wellbore instability problems, it is critical to determine the optimum wellbore profile and to design an appropriate mud weight program based on wellbore stability analysis. It is a complex and iterative decisionmaking procedure since various factors, such as in-situ stress regime, material strength and poroelastic properties, strength and poroelastic anisotropies, initial and induced pore pressures, must be considered in the assessment and determination.This paper describes the methodology and procedure for determination of optimum wellbore profile and mud weight program based on rock mechanics consideration. The methodology is presented in the form of guideline charts and the procedure of applying the methodology is described. The application of the methodology and procedure is demonstrated through two field case studies with different in-situ stress regimes in Australia and Indonesia.

Sign in / Sign up

Export Citation Format

Share Document