A new and reliable dual model- and data-driven TOC prediction concept: A TOC logging evaluation method using multiple overlapping methods integrated with semi-supervised deep learning

Zhu, Linqi; Zhang, Zhansong; Zhou, Xueqing; Liu, Weinan; Zhu, Boyuan

doi:10.1016/j.petrol.2020.106944

Cited by 61 publications

(24 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…is confirms the importance of evaluating the ability of the unconventional resources for hydrocarbon generation in a cost-effective manner with high accuracy [4,6].…”

Section: Introductionmentioning

confidence: 56%

“…Hence, the daily oil production rate from currently producing reservoirs considerably declined [1,2]. erefore, recently source rock and unconventional reservoirs attracted significant interest [3,4]. Exploration of unconventional resources is more complicated than the exploration of conventional reservoirs because they are more complex, tight, and impermeable [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

[Retracted] Utilization of Artificial Neural Network in Predicting the Total Organic Carbon in Devonian Shale Using the Conventional Well Logs and the Spectral Gamma Ray

Siddig

Mahmoud

Elkatatny

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Due to high oil and gas production and consumption, unconventional reservoirs attracted significant interest. Total organic carbon (TOC) is a significant measure of the quality of unconventional resources. Conventionally, TOC is measured experimentally; however, continuous information about TOC is hard to obtain due to the samples’ limitations, while the developed empirical correlations for TOC were found to have modest accuracy when applied in different datasets. In this paper, data from Devonian Duvernay shale were used to develop an optimized empirical correlation to predict TOC based on an artificial neural network (ANN). Three wells’ datasets were used to build and validate the model containing over 1250 data points, and each data point includes values for TOC, density, porosity, resistivity, gamma ray and sonic transient time, and spectral gamma ray. The three datasets were used separately for training, testing, and validation. The results of the developed correlation were compared with three available models. A sensitivity and optimization test was performed to reach the best model in terms of average absolute percentage error (AAPE) and correlation coefficient (R) between the actual and predicted TOC. The new correlation yielded an excellent match with the actual TOC values with R values above 0.93 and AAPE values lower than 14%. In the validation dataset, the correlation outperformed the other empirical correlations and resulted in less than 10% AAPE, in comparison with over 20% AAPE in other models. These results imply the applicability of this correlation; therefore, all the correlation’s parameters are reported to allow its use on different datasets.

show abstract

“…is confirms the importance of evaluating the ability of the unconventional resources for hydrocarbon generation in a cost-effective manner with high accuracy [4,6].…”

Section: Introductionmentioning

confidence: 56%

Section: Introductionmentioning

confidence: 99%

[Retracted] Utilization of Artificial Neural Network in Predicting the Total Organic Carbon in Devonian Shale Using the Conventional Well Logs and the Spectral Gamma Ray

Siddig

Mahmoud

Elkatatny

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Conventional hydrocarbon reserves are gradually depleting due to the continuous oil and gas exploitation and the production rates of the current reservoirs dramatically dropped [ 1 , 2 ]. Source rock and unconventional reservoirs have recently attracted interest as a result [ 3 , 4 ]. Since unconventional resources are more complex, tight, and less permeable, unconventional reservoirs exploration is more challenging and demanding in contrast to conventional reservoirs [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Application of Various Machine Learning Techniques in Predicting Total Organic Carbon from Well Logs

Siddig

Ibrahim

Elkatatny

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Unconventional resources have recently gained a lot of attention, and as a consequence, there has been an increase in research interest in predicting total organic carbon (TOC) as a crucial quality indicator. TOC is commonly measured experimentally; however, due to sampling restrictions, obtaining continuous data on TOC is difficult. Therefore, different empirical correlations for TOC have been presented. However, there are concerns about the generalization and accuracy of these correlations. In this paper, different machine learning (ML) techniques were utilized to develop models that predict TOC from well logs, including formation resistivity (FR), spontaneous potential (SP), sonic transit time (Δt), bulk density (RHOB), neutron porosity (CNP), gamma ray (GR), and spectrum logs of thorium (Th), uranium (Ur), and potassium (K). Over 1250 data points from the Devonian Duvernay shale were utilized to create and validate the model. These datasets were obtained from three wells; the first was used to train the models, while the data sets from the other two wells were utilized to test and validate them. Support vector machine (SVM), random forest (RF), and decision tree (DT) were the ML approaches tested, and their predictions were contrasted with three empirical correlations. Various AI methods’ parameters were tested to assure the best possible accuracy in terms of correlation coefficient (R) and average absolute percentage error (AAPE) between the actual and predicted TOC. The three ML methods yielded good matches; however, the RF-based model has the best performance. The RF model was able to predict the TOC for the different datasets with R values range between 0.93 and 0.99 and AAPE values less than 14%. In terms of average error, the ML-based models outperformed the other three empirical correlations. This study shows the capability and robustness of ML models to predict the total organic carbon from readily available logging data without the need for core analysis or additional well interventions.

show abstract

“…However, the detectability of thin deeper layers, as well as their internal heterogeneity and stratification, suffers from strong signal attenuation at sites with a thick, conductive top layer and from rapid decrease in vertical resolution with depth (Comas et al, 2015). Alternatively, relating well-logging parameters to TOC content allow a depth-independent high vertical resolution of carbon content in petroleum geoscience (Passey et al, 1990;Zhu et al, 2020). This, however, requires costly boreholes and downhole equipment and is hence highly impractical for spatial mapping of TOC in near-surface formations.…”

Section: Introductionmentioning

confidence: 99%

Direct‐Push Color Logging Images Spatial Heterogeneity of Organic Carbon in Floodplain Sediments

et al. 2020

View full text Add to dashboard Cite

In soils and sediments, large amounts of total organic carbon (TOC) mark reducing conditions. As dark sediment colors are good predictors for high-TOC zones, they indicate hot spots of biogeochemical turnover and microbial activity. Traditionally, obtaining the sediment color or TOC at depth requires costly core sampling, resulting in poor horizontal resolution and related uncertainty caused by interpolation. We suggest using a direct-push tool for optical screening of the sediment color to acquire multiple high-resolution vertical color profiles and demonstrate its applicability to a biogeochemical transition zone in floodplain sediments, dominated by tufa. We use Gaussian mixture models for a cluster analysis of 35 color logs in the International Commission on Illumination (CIE) L*a*b* color space to identify three colorfacies that differ in lithology and TOC content: a dark colorfacies that agrees well with peat layers, a gray colorfacies associated with clay, and a creamy-brown facies made of autochthonous carbonate precipitates. We test different approaches either to infer the TOC content from color metrics, namely, the lightness and chroma, across all facies, or to identify TOC ranges for each colorfacies. Given the high variability in TOC due to organic carbon specks in the tufa, the latter approach appears more realistic. In our application we map the 3-D distribution of organic matter in a floodplain in distinct facies over 20,000 m 2 down to 12 m depth. While we relate the sediment color only to the TOC content, direct-push color logging may also be used for in situ mapping of other biogeochemically relevant properties, such as the ferric-iron content or sedimentary structure. Plain Language Summary Geologists can say a lot about soils and loose materials in the ground by looking at their color. Dark materials normally contain dead plants, called organic carbon, which are food for bacteria and cause chemical reactions. To get the color of the soil, geologists normally need soil samples, but getting them from depth takes time and money. We test a method of pushing a camera into the ground and recording the color therein. From the recorded color we can say which type of geological material is at which depth and how much organic carbon is there without taking samples everywhere. This can be done very quickly, so that we can do it over a large area and down to the depth of the loose material in the ground, where most of the groundwater flows.

show abstract

A new and reliable dual model- and data-driven TOC prediction concept: A TOC logging evaluation method using multiple overlapping methods integrated with semi-supervised deep learning

Cited by 61 publications

References 41 publications

[Retracted] Utilization of Artificial Neural Network in Predicting the Total Organic Carbon in Devonian Shale Using the Conventional Well Logs and the Spectral Gamma Ray

[Retracted] Utilization of Artificial Neural Network in Predicting the Total Organic Carbon in Devonian Shale Using the Conventional Well Logs and the Spectral Gamma Ray

Application of Various Machine Learning Techniques in Predicting Total Organic Carbon from Well Logs

Direct‐Push Color Logging Images Spatial Heterogeneity of Organic Carbon in Floodplain Sediments

Contact Info

Product

Resources

About