Utilization of adaptive neuro-fuzzy interference system and functional network in prediction of total organic carbon content

This paper presents the application of two artificial intelligence (AI) approaches in the prediction of total organic carbon content (TOC) in Devonian Duvernay shale. To develop and test the models, around 1250 data points from three wells were used. Each point comprises TOC value with corresponding spectral and conventional well logs. The tested AI techniques are adaptive neuro-fuzzy interference system (ANFIS) and functional network (FN) which their predictions are compared to existing empirical correlations. Out of these two methods, ANFIS yielded the best outcomes with 0.98, 0.90, and 0.95 correlation coefficients (R) in training, testing, and validation respectively, and the average errors ranged between 7 and 18%. In contrast, the empirical correlations resulted in R values less than 0.85 and average errors greater than 20%. Out of eight inputs, gamma ray was found to have the most significant impact on TOC prediction. In comparison to the experimental procedures, AI-based models produces continuous TOC profiles with good prediction accuracy. The intelligent models are developed from preexisting data which saves time and costs. Article highlights In contrast to existing empirical correlation, the AI-based models yielded more accurate TOC predictions. Out of the two AI methods used in this article, ANFIS generated the best estimations in all datasets that have been tested. The reported outcomes show the reliability of the presented models to determine TOC for Devonian shale.

Sea Ice Dynamics Drive Benthic Microbial Communities in McMurdo Sound, Antarctica

Climate change is driving dramatic variability in sea ice dynamics, a key driver in polar marine ecosystems. Projected changes in Antarctica suggest that regional warming will force dramatic shifts in sea ice thickness and persistence, altering sea ice-associated primary production and deposition to the seafloor. To improve our understanding of the impacts of sea ice change on benthic ecosystems, we directly compared the benthic microbial communities underlying first-year sea ice (FYI) and multi-year sea ice (MYI). Using two tractable coastal habitats in McMurdo Sound, Antarctica, where FYI (Cape Evans) and MYI (New Harbour) prevail, we show that the structure and composition of the benthic microbial communities reflect the legacy of sea ice dynamics. At Cape Evans, an enrichment of known heterotrophic algal polysaccharide degrading taxa (e.g., Flavobacteriaceae, unclassified Gammaproteobacteria, and Rubritaleaceae) and sulfate-reducing bacteria (e.g., Desulfocapsaceae) correlated with comparatively higher chlorophyll a (14.2±0.8μgg−1) and total organic carbon content (0.33%±0.04), reflecting increased productivity and seafloor deposition beneath FYI. Conversely, at New Harbour, an enrichment of known archaeal (e.g., Nitrosopumilaceae) and bacterial (e.g., Woeseiaceae and Nitrospiraceae) chemoautotrophs was common in sediments with considerably lower chlorophyll a (1.0±0.24μgg−1) and total organic carbon content (0.17%±0.01), reflecting restricted productivity beneath MYI. We also report evidence of a submarine discharge of sub-permafrost brine from Taylor Valley into New Harbour. By comparing our two study sites, we show that under current climate-warming scenarios, changes to sea ice productivity and seafloor deposition are likely to initiate major shifts in benthic microbial communities, with heterotrophic organic matter degradation processes becoming increasingly important. This study provides the first assessment of how legacy sea ice conditions influence benthic microbial communities in Antarctica, contributing insight into sea ice–benthic coupling and ecosystem functioning in a polar environment.

Machine Learning-Based Production Prediction Model and Its Application in Duvernay Formation

The production of a single gas well is influenced by many geological and completion factors. The aim of this paper is to build a production prediction model based on machine learning technique and identify the most important factor for production. Firstly, around 159 horizontal wells were collected, targeting the Duvernay Formation with detailed geological and completion records. Secondly, the key factors were selected using grey relation analysis and Pearson correlation. Then, three statistical models were built through multiple linear regression (MLR), support vector regression (SVR), gaussian process regression (GPR). The model inputs include fluid volume, proppant amount, cluster counts, stage counts, total horizontal lateral length, gas saturation, total organic carbon content, condensate-gas ratio. The model performance was assessed by root mean squared errors (RMSE) and R-squared value. Finally, sensitivity analysis was applied based on best performance model. The analysis shows following conclusions: (1) GPR model shows the best performance with the highest R-squared value and the lowest RMSE. In the testing set, the model shows a R-squared of 0.8 with a RMSE of 280.54 × 104 m3 in the prediction of cumulative gas production within 1st 6 producing months and gives a R-squared of 0.83 with a RMSE of 1884.3 t in the prediction of cumulative oil production within 1st 6 producing months (2) Sensitivity analysis based on GPR model indicates that condensate-gas ratio, fluid volume, and total organic carbon content are the most important features to cumulative oil production within 1st 6 producing months. Fluid volume, Stages, and total organic carbon content are the most significant factors to cumulative gas production within 1st 6 producing months. The analysis progress and results developed in this study will assist companies to build prediction models and figure out which factors control well performance.

Source Rock Characteristic of Sargelu and Kurrachine Formations from the Selected Wells in Northern Iraq

A total of 56 cuttings samples of Sargelu and Kurrachine formations from different wells (Ain Zalah, Baiji, and Jabal Kand) in northern Iraq have been investigated in this study. Both the Sargelu and Kurrachine formations were examined using Rock-Eval pyrolysis to assess the richness of organic matter and thermal maturity level. The Sargelu Formation Have Total Organic Carbon wt.% ranged from 0.22–2.52 wt.%, average 1.26 wt.% in Ain Zalah Well, and between 0.57–8.90 wt.%, average 2.95 wt.% in Baiji Well, and between 0.81–11.80 wt.%, average 5.01wt.% in for Kand Well. It is considered a potential source rock based on total organic carbon content. total organic carbon wt. % in Ain Zalah and Kand in the Kurrachine Formation is considered poor source rock with a total organic carbon content of 0.17, 0.39 wt. %, respectively, while in Baiji Well is considered moderate source rock with total organic carbon content 0.53 wt. %. The Rock-Eval data are not always sufficient to define the kind of organic matter through the use of the van Krevelen diagram because HI and OI are affected by both matrix mineralogy and the kerogen mixture. For accurate assessments of the source rocks, gas chromatography has been relied on, which provides a direct indication of the kerogen type as well as the type of hydrocarbons that kerogen can generate during maturity. Gas chromatography analysis indicates that all selected samples contained type II kerogen. The highest value of the TAS/ (MAS+TAS) ratio was found in Ain Zalah samples (Sargelu Formation), and this result indicates the occurrence of an aromatization process with increasing thermal maturation.