... We conducted aerial magnetic measurements on the tribal land of the Osage Nation in Oklahoma, in an attempt to test the feasibility of rapid aerial detection of undocumented orphaned wells. The distance from the UAV to the ground ranged from 40 m to 100 m during the experiment. The average...

... Detecting microseismic events from Distributed Acoustic Sensing data presents significant challenges, particularly due to the prevalent label imbalance in seismic datasets. Noise data overwhelmingly outnumbers event labels, leading to a high false negative ratio when using conventional deep...

... the interference of noise. The resulting 3D seismic data shows that this method has the potential to accurately identify low-order faults in carbonate reservoirs. carbonate rock sedimentary rock deep learning rock type geology seismic data detection low-order fault geologist neural network machine...

... agreement with the known electrical logging data, and can provide reference for similar deep target detection. sedimentary rock rock type structural geology reservoir characterization economic geology source excitation geological subdiscipline two-side source excitation complex area deep...

... interpretation hypothesis stratigraphic interpretation detection channel belt multiple interpretation hypothesis applied geoscience & energy 10 information Constrained optimization method for seismic stratigraphic analysis Implications for interpretation quality and machine learning applications...

... operations. We used two fiber optic cables installed behind a production casing string of two wells in the field. In this pilot project, each of the two wells served dual roles as both a producer and an injector. To efficiently detect microseismic events from a large amount of the continuous DAS record, we...

... by induced fractures can also be used to create hydraulic fracture images. For DAS-recorded data, one of the challenges of performing reflection imaging regularly is automatically detecting the reflections in microseismic wavefields. The large data volumes of DAS, both temporally and spatially, make...

... compared to geophones. For DAS, universal, automatic workflows for event detection and arrival-picking do not exist, yet. Here, we propose a universally applicable workflow for automatic, real-time event detection and arrival-picking using a Convolutional Neural Network (CNN). In contrast to geophone-based...

... is embedded in an integrated detection and location framework to seamlessly output a highly complete earthquake catalog. The EQCCT enables us to detect and locate 50 times more earthquakes than previously possible. We apply the EQCCT-embedded detection and location workflow to the Culberson and Mentone...

... of subsurface geology and geomechanics. Critical tools for ensuring the stability and safety of CCUS operations are passive source relocation and fault detection, which provide key insights into subsurface structures and fluid migration pathways. However, the implementation of these techniques is challenging...

... of a analystreviewed bulletin has been constructed (Hutchenson et al., 2023). This bulletin provides the starting point for evaluating an automated process to report events in realtime, from phase detection, association of the various phases, location of the events, and determination of magnitudes. A comparison...

... monitoring systems/intelligent wells exploration geophysicist fiber journal figure 3 production monitoring international applied geoscience communication american association interpretation detection optical fiber Hydraulic fracture stage identification and size estimation using distributed...

... by geology experts is time-consuming and uncertain (Fathi et al., 2022, Pham et al 2021). The proposed workflow utilizes computer vision and deep learning techniques to automate the detection of fractures and baffles, significantly reducing cost, time, and human bias. Applying the workflow to The Illinois...

... of seismic events of interest. The novelty of the proposed approach is to address two different problems (i.e., denoising and event detection) using a single network. A convolutional neural network is used to capture the high frequency times series, which is combined with gated recurrent unit networks...

... The current research on time-domain electromagnetic detection methods for well boreholes is proposed based on the magnetic source measurement mode. Compared with magnetic sources, the electrical source measurement mode, both electrical and magnetic signal acquisition can be used. Its measurement...

... geophysicist boulder geological subdiscipline evaluation hyperbola chamber noise american association detection weighting cnn geology society dataset machine learning applied geoscience interpreter energy 10 seeschifffahrt und hydrographie Boulder prediction for offshore windfarm site...

... of magnetic source detection is the geological interface parallel to the coil surface; The best target of electrical source detection is the geological interface parallel to the electrode arrangement. There is a strong correlation between the time-domain electromagnetic response characteristics of borehole...

... We consider the task of channel detection as a regression problem and propose a workflow to identify the complex channels in 3D seismic volumes with complex structure using an end-to-end 3D convolutional neural network. To train the network, we automatically generate a training dataset...

... deep learning reservoir characterization upstream oil & gas artificial intelligence interpretation geophysics american association international neural style transfer figure 3 workflow figure 4 exploration geophysicist detection neural network machine learning joseph jenning...

... designs an automatic velocity spectrum picking method based on object detection, and applies neural network model named FCOS (Fully Convolutional One-Stage Object Detection) (Tian et al., 2019) to implement the automatic velocity spectrum picking. In this method, the velocity spectrum is processed...