Rock porosity is one of the most significant parameters in fluid-flow simulation in the context of carbonate reservoirs. The hydrocarbon industry uses porosity to assess the production potential of oil and gas in carbonate environments. Traditional methods to determine porosity are limited to discrete measurements and generally demand extra resources associated with careful analysis of logs, rock sampling and laboratory analysis. This paper investigates an alternative to estimate porosity in carbonate rocks using pointwise hyperspectral data and machine learning. The method is contiguous, does not require rock sampling and was validated in various rock plug samples collected from two distinct carbonate outcrops. The samples were analysed in the laboratory to determine ground-truth values for the effective porosity and reflectance in visible and infrared regions of the spectra. The supervised regression methods applied were able to estimate a robust relationship between the effective porosity of carbonate rocks and spectral behaviour in characteristic spectral features of carbonate, hydroxyl, molecular water and Fe/Mn. The results obtained here suggest the soundness of the indirect approach to estimate porosity with most of the models trained achieving a coefficient of determination above 0.8 and mean absolute deviation of less than 2%.
29 July 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
In Petroleum Geology, to assess the hydrocarbon generation potential in source rocks involves the determination of the kerogen type by some destructive method. The usage of such methods is a bottleneck in the process because it is time-consuming, requires specialized tools and personnel, and ends up destroying the rock sample, so it is not possible to do any posterior analysis. This study presents an alternative method for determination of the kerogen type that is fast and non-destructive using hyperspectral data and machine learning techniques. The method is validated using five distinct supervised learning algorithms that were applied to spectral data collected in rock samples from Taubaté Basin, Brazil, of an outcrop whose rocks have a wide range of hydrocarbon generation potential. Cores and samples were collected from the outcrop and had their kerogen type determined by geochemical analyses performed in the laboratory. The robustness of the method is evaluated in two distinct experiments. In the first one, the hyperspectral dataset was collected using a non-imaging spectroradiometer; in the second one, the method uses non-imaging hyperspectral data as training and is tested in hyperspectral images collected. In both experiments, the method was able to establish a relationship between selected spectral features and the kerogen type of the source rocks sampled. The results obtained in this paper are prospective for non-destructive classification of kerogen type (and, consequently, the hydrocarbon generation potential), since most of the models generated achieved accuracy above 0.8 in the validation step and 0.75 in the test step.
1 December 2020 in Rio Oil and Gas Expo and Conference
Oil and gas reservoirs are well studied in petroleum engineering, using seismic data to estimate fluid flow and well placement. However, seismic data cannot capture fractures due to their scale, and fractures may affect rock porosity and permeability. Consequently, rock fracture segmentation and quantification from aerial images of analogous outcrops can input essential information into those studies. This letter presents a new method, named interactive Forest Growing (iFG), for fracture segmentation. The image is initially segmented into superpixels, defining a superpixel graph. The user selects seed superpixels, a path-cost threshold, and fractures are delineated by growing one optimum-path tree from each seed with path costs limited to the selected threshold. iFG considerably increases efficiency while reducing human effort in fracture segmentation compared to pixel-by-pixel manual annotation. We evaluate iFG with three specialists and against an interactive Region Growing (iRG) method using 15 images to measure bias in user interpretations, verify efficiency gain over a similar approach, and generate a dataset with consolidated annotation for future work. The experiments show that iFG reduces user interventions from 19% to 33% compared to iRG, users with more experience in fracture analysis complete segmentation 4–5 times faster, and segmentation effectiveness is independent of user experience since the average F1 scores between users using both methods ranged from 0.966 to 0.979, allowing us to create a consolidated segmentation.