Prediction of sonic log and correlation of lithology by comparing geophysical well log data using machine learning principles

Joshi, Dev; Patidar, Atul Kumar; Mishra, Abhipshit; Ghosh, Sayantan; Agarwal, Sugandha; Pandey, Aayush; Dewangan, Bhupesh Kumar; Choudhury, Tanupriya

doi:10.1007/s10708-021-10502-6

Cited by 15 publications

(6 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the success of a tracer study is dependent on using the correct tracer and a suitable technique. Similarly, data analysis through machine learning methods (Joshi et al 2021;Khilrani et al 2021) combined with the results obtained through the tracer test can be integrated with the knowledge of reservoirs gained from other sources to successfully plan secondary and tertiary O&G recovery methods.…”

Section: Discussionmentioning

confidence: 99%

“…Nowadays, forward mathematical modeling, artificial intelligence and machine learning (AI/ML) techniques are being popular for the analysis of recorded data. AI/ML techniques are also used to develop a comprehensive tracer testing plan and amalgamate it along with the petrophysical interpretations done using the abovementioned techniques (Joshi et al 2021;Khilrani et al 2021;Knackstedt et al 2009;Sprunger et al 2021). The general characteristics of the tracer are shown in Table 1.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A review of tracer testing techniques in porous media specially attributed to the oil and gas industry

Patidar

Joshi

Dristant

et al. 2022

J Petrol Explor Prod Technol

Self Cite

View full text Add to dashboard Cite

The significance of the tracer testing technique is widely accepted in reservoir performance analysis in hydrology as well as in hydrocarbon exploration and production. The subsurface reservoir delineation for hydrocarbon exploration and optimum production is one of the most critical aspects of petroleum system analysis. The quality of the reservoir and its performance prediction require extensive knowledge of qualitative reservoir geology, its depositional environment, facies heterogeneity and engineering properties of subsurface formations. Tracer testing is amongst the few techniques available in the oil and gas (O&G) industry, which stands up to these expectations and is successfully used for quantitative determination and analysis of sub-seismic scale structural and stratigraphic heterogeneities. Tracer testing is also being utilized in determining residual oil saturation (Sor) and lateral correlation of reservoir properties in the subsurface. Apart from the O&G industry, the concentration-based applications of tracer testing have been proved in hydrology, geothermal and medical science. A comprehensive review is presented to explain the application of tracer testing technique to investigate porous media, mainly in O&G industry. The type of tracers used, their selection criteria, concentration, and natural versus gradient and qualitative to a quantitative application are discussed in the current review. Generally, two types of tracers (chemical and radioactive) are preferred in the petroleum industry for gas/fluid flow assessment, waterflood optimization and establishing connectivity between multiple wells. The current paper reviews both types of tracer tests, namely single well and inter well, in detail discussing the objectives, calculations, designing, injection, sampling, laboratory analysis and knowledge integration. The preliminary aim was to provide a review of the tracer testing technique used in reservoir evaluation and well-to-well connectivity analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A review of tracer testing techniques in porous media specially attributed to the oil and gas industry

Patidar

Joshi

Dristant

et al. 2022

J Petrol Explor Prod Technol

Self Cite

View full text Add to dashboard Cite

show abstract

“…The correlation coefficient increased from (−0.28) to (−0.61) by using Pearson and Spearman methods, respectively, which reflect a nonlinear relationship between the lithology and DSR. In addition, Figure presents a cross plot between the different parameters with formation tops in addition to the data distribution for each. , The cross plots between the lithology ( Y ) and the different parameters almost show a linear relation except with DSR (×3), which shows a nonlinear relation. In addition, the weakest relationship between the inputs and lithology was found to be in the case of Q where the data are scattered and do not follow a certain trend, which confirms the results from Figure .…”

Section: Methodsmentioning

confidence: 99%

Applications of Different Classification Machine Learning Techniques to Predict Formation Tops and Lithology While Drilling

Ibrahim,

Ahmed,

Elkatatny

2023

ACS Omega

View full text Add to dashboard Cite

Accurate prediction of formation tops and lithology plays a critical role in optimizing drilling processes, cost reduction, and risk mitigation in hydrocarbon operations. Although several techniques like well logging, core sampling, cuttings analysis, seismic surveys, and mud logging are available for identifying formation tops, they have limitations such as high costs, lower accuracy, manpower-intensive processes, and time or depth lags that impede real-time estimation. Consequently, this study aims to leverage machine learning models based on easily accessible drilling parameters to predict formation tops and lithologies, overcoming the limitations associated with traditional methods. Data from two wells (A and B) in the Middle East, encompassing drilling mechanical parameters such as rate of penetration (ROP), drill string rotation (DSR), pumping rate (Q), standpipe pressure (SPP), weight on bit (WOB), and torque, were collected for real-field analysis. Machine learning models including Gaussian naive Bayes (GNB), logistic regression (LR), and linear discriminant analysis (LDA) were trained and tested on the data set from well A, while the data set from well B was utilized for model validation as unseen data. The formations of wells A and B consist of four lithologies, namely, sandstone, anhydrite, carbonate/shale, and carbonates, necessitating the development of multiclass classification models. The drilling parameters, specifically the WOB and ROP, exhibited a strong influence on lithology identification. Among the models, GNB demonstrated exceptional performance in predicting formation lithology from the drilling parameters, achieving accuracy and nearly perfect precision, recall, and F1 score for the different classes. LDA and LR models accurately predicted sandstone and carbonate lithologies, although some misclassifications occurred in approximately 5% of points for anhydrite and around 20% in carbonate/shale formations. During validation, the models demonstrated accuracies of around 0.96, 0.95, and 0.92 for the GNB, LR, and LDA, respectively. The study highlights the efficacy of the developed machine learning models in accurately predicting the formation lithology and tops in real time. This is achieved by utilizing readily available drilling parameters, making the approach highly accurate and cost effective by leveraging existing real-time drilling data.

show abstract

“…Data conditioning is the method of preparing and preprocessing data to ensure that, the data is ready for analysis or modelling. The aim of data conditioning is to make sure that the data is consistent, accurate, and free from errors to answer specific research questions or to develop predictive models [17].…”

Section: Data Conditioningmentioning

confidence: 99%

Identification of Lithology from Well Log Data Using Machine Learning

Rohit,

Manda,

Raj

et al. 2024

EAI Endorsed Trans IoT

Self Cite

View full text Add to dashboard Cite

INTRODUCTION: Reservoir characterisation and geomechanical modelling benefit significantly from diverse machine learning techniques, addressing complexities inherent in subsurface information. Accurate lithology identification is pivotal, furnishing crucial insights into subsurface geological formations. Lithology is pivotal in appraising hydrocarbon accumulation potential and optimising drilling strategies. OBJECTIVES: This study employs multiple machine learning models to discern lithology from the well-log data of the Volve Field. METHODS: The well log data of the Volve field comprises of 10,220 data points with diverse features influencing the target variable, lithology. The dataset encompasses four primary lithologies—sandstone, limestone, marl, and claystone—constituting a complex subsurface stratum. Lithology identification is framed as a classification problem, and four distinct ML algorithms are deployed to train and assess the models, partitioning the dataset into a 7:3 ratio for training and testing, respectively. RESULTS: The resulting confusion matrix indicates a close alignment between predicted and true labels. While all algorithms exhibit favourable performance, the decision tree algorithm demonstrates the highest efficacy, yielding an exceptional overall accuracy of 0.98. CONCLUSION: Notably, this model's training spans diverse wells within the same basin, showcasing its capability to predict lithology within intricate strata. Additionally, its robustness positions it as a potential tool for identifying other properties of rock formations.

show abstract

Prediction of sonic log and correlation of lithology by comparing geophysical well log data using machine learning principles

Cited by 15 publications

References 41 publications

A review of tracer testing techniques in porous media specially attributed to the oil and gas industry

A review of tracer testing techniques in porous media specially attributed to the oil and gas industry

Applications of Different Classification Machine Learning Techniques to Predict Formation Tops and Lithology While Drilling

Identification of Lithology from Well Log Data Using Machine Learning

Contact Info

Product

Resources

About