Permeability is a critical parameter for understanding subsurface fluid flow behavior, managing reservoirs, enhancing hydrocarbon recovery, and sequestering carbon dioxide. In general, permeability is measured in the laboratory based on subsurface core samples, calculated from well logs or estimated from well tests. However, laboratory measurements and well tests are expensive, time-consuming, and usually limited to a few core samples or wells in a hydrocarbon field or carbon storage site. Machine-learning techniques are good options for generating a rapid, robust, and cost-effective permeability prediction model because of their strengths to recognize the potential interrelationships between input and output variables. Convolutional neural networks (CNN), as a good pattern recognition algorithm, are widely used in image processing, natural language processing, and speech recognition, but are rarely used with regression problems and even less often in reservoir characterization. We have developed a CNN regression model to estimate the permeability in the Jacksonburg-Stringtown oil field, West Virginia, which is a potential carbon storage site and enhanced oil recovery operations field. We also evaluate the concept of the geologic feature image, which is converted from geophysical well logs. Five variables, including two commonly available conventional well logs (the gamma rays [GRs] and bulk density) and three well-log-derived variables (the slopes of the GR and bulk density curves, and shale content), are used to generate a geologic feature image. The CNN treats the geologic feature image as the input and the permeability as the desired output. In addition, the permeability predicted using traditional backpropagation artificial neural networks, which are optimized by genetic algorithms and particle swarm optimization, is compared with the permeability estimated using our CNN. Our results indicate that the CNN regression model provides more accurate permeability predictions than the traditional neural network.
Volatile organic compounds' (VOCs) effluents, which come from many industries, are triggering serious environmental problems. As an emerging technology, non-thermal plasma (NTP) technology is a potential technology for VOCs emission control. NTP coupled with F-TiO2/γ-Al2O3 is used for toluene removal from a gaseous influent at normal temperature and atmospheric pressure. NTP is generated by dielectric barrier discharge, and F-TiO2/γ-Al2O3 can be prepared by sol-gel method in the laboratory. In the experiment, the different packed materials were packed into the plasma reactor, including γ-Al2O3, TiO2/γ-Al2O3 and F-TiO2/γ-Al2O3. Through a series of characterization methods such as X-ray diffraction, scanning electronic microscopy and Brunner-Emmet-Teller measurements, the results show that the particle size distribution of F-TiO2 is relatively smaller than that of TiO2, and the pore distribution of F-TiO2 is more uniformly distributed than that of TiO2. The relationships among toluene removal efficiency, reactor input energy density, and the equivalent capacitances of air gap and dielectric barrier layer were investigated. The results show that the synergistic technology NTP with F-TiO2/γ-Al2O3 resulted in greater enhancement of toluene removal efficiency and energy efficiency. Especially, when packing with F-TiO2/γ-Al2O3 in NTP reactor, toluene removal efficiency reaches 99% and higher. Based on the data analysis of Fourier Transform Infrared Spectroscopy, the experimental results showed that NTP reactor packed with F-TiO2/γ-Al2O3 resulted in a better inhibition for by-products formation effectively in the gas exhaust.
Photograph of en echelon fracture from Coldstream 1MH well, depth 7,100 ft with an insert of a three-dimensional digital representation of these fractures obtained with NETL's industrial computed tomography scanner.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.