Search

Drilling optimization is essential in constructing an enhanced geothermal system (EGS) and can be facilitated through predicting the rate of penetration (ROP). The ROP evolution along the depth was forecasted by considering the current and previous ROP values as input to a gated recurrent unit (GRU)-based deep learning model. Drilling data was obtained from two geothermal wells in Pohang, South Korea. Multiple data configurations for training and testing were designed from both wells. The proximity of the training section to the target results in improved accuracy in prediction (MAPE smaller than ~ 3%). Furthermore, larger depth spans of ROPs used for training resulted in better prediction outcomes. The model trained with the entire dataset from an adjacent well exhibited well-predicted ROP values for a new drilling hole (MAPE smaller than 5–10%). From the multiple-step forecasting analysis, the error tended to sharply increase as the number of predicted ROP values increased despite a large number of the input sequence (MAPE larger than 20%). Incorporating other drilling data besides ROP evolution did not improve the prediction. By predicting ROP evolution along the depth, the GRU-based model can assist operators in optimizing drilling processes and preparing for upcoming scenarios. The model can serve as a valuable tool for enhancing drilling efficiency and effectively managing operational uncertainties. [ABSTRACT FROM AUTHOR]

Hydraulic stimulation has been a key technique in enhanced geothermal systems (EGS) and the recovery of unconventional hydrocarbon resources to artificially generate fractures in a rock formation. Previous experimental studies present that the pattern and aperture of generated fractures vary as the fracking pressure propagation. The recent development of three-dimensional X-ray computed tomography allows visualizing the fractures for further analysing the morphological features of fractures. However, the generated fracture consists of a few pixels (e.g., 1-3 pixels) so that the accurate and quantitative extract of micro-fracture is highly challenging. Also, the high-frequency noise around the fracture and the weak contrast across the fracture makes the application of conventional segmentation methods limited. In this study, we adopted an encoder-decoder network with a convolutional neural network (CNN) based on deep learning method for the fast and precise detection of micro-fractures. The conventional image processing methods fail to extract the continuous fractures and overestimate the fracture thickness and aperture values while the CNN-based approach successfully detects the barely seen fractures. The reconstruction of the 3D fracture surface and quantitative roughness analysis of fracture surfaces extracted by different methods enables comparison of sensitivity (or robustness) to noise between each method.

The hydraulic permeability is a key parameter for simulating the flow-related phenomenon so that its accurate estimation is crucial in both experimental and numerical simulation studies. 3D pore structure can be readily taken by X-ray computed tomography (CT) and it often serves as a flow domain for pore-scale simulation. However, one encounters the challenges in segmenting the authentic pore structure owing to the finite size of image resolution and segmentation methods. Therefore, the loss of structural information in pore space seems unavoidable to result in the unreliable estimation of permeability. In this study, we propose a novel framework to overcome these limitations by using a flexible ternary segmentation scheme. Given the pore size distribution curve and porosity, three phases of pore, solid, and gray regions are segmented by considering the partial volume effect which holds the composition information of unresolved objects. The resolved objects such as solid and pore phases are taken to equivalently solve Stokes equation while the fluid flow through unresolved objects is simultaneously solved by Stokes-Brinkmann equation. The proposed numerical scheme to obtain the permeability is applied to Indiana limestone and Navajo sandstone. The results show that the computed hydraulic permeability is similar to the experimentally obtained value without being affected by image resolution. This approach has advantages of achieving consistent permeability values, less influenced by segmentation methods.

Enzymatically induced carbonate precipitation (EICP) using urea hydrolysis is a well-known bio-cementation process that not only promotes the precipitation of calcium carbonate (CaCO3) but can provide excess calcium cations for further reaction depending on the substrate constituents and reaction stage. This study presents the EICP recipe to contain sulfate ions in landfill leachate sufficiently using remaining calcium cations and a series of tests were conducted to validate its ability to retain sulfates. The reaction rate for 1 M CaCl2 and 1.5 M urea was identified by controlling the purified urease content and the curing time of the EICP process. The results showed that 0.3 g/L of purified urease produced 46% CaCO3 and reduced sulfate ions by 77% after 3 days of curing. The shear stiffness in EICP-treated sand was enhanced 13 times by CaCO3 precipitation followed by 1.12 times increment due to subsequent precipitation of gypsum (CaSO4·2H2O) crystals implying sulfate containment. A cost-efficient EICP treatment using soybean crude urease instead of lab-grade purified urease exhibited lower sulfate removal efficiency (i.e., 18%) with only nominal formation of gypsum in the EICP-treated sand. The addition of gypsum powder was effective in increasing sulfate removal by 40% when soybean crude urease was used for EICP. [ABSTRACT FROM AUTHOR]