查看更多>>摘要：We developed an effective U-Net based deep learning (DL) model for inversion of surface gravity data on a rectangular grid to predict 2-D high-resolution subsurface CO2 distribution along a vertical cross-section due to CO2 leakage through a wellbore within a deep CO2 storage reservoir. We used synthetic data to model two types of CO2 leakage scenarios: one CO2 plume in a shallow aquifer (single plume case), and two plumes present at different depths (double plume case). The 3-D synthetic plume samples were created by sampling among predetermined CO2 plume depths, saturations, and volumes. The corresponding surface gravity data on a rectangular grid were generated by a 3-D forward model. The U-Net model detected 72% of single-plume samples, and one or both plumes in 75% of double-plume samples. Most of the undetected single plumes have small gravity field strengths below the typical noise level of 5 mu Gal. This model generated reproducible, reliable predictions with acceptable errors and demonstrated improved spatial resolution over the conventional least-squares inversion. In contrast to the conventional least-squares inversion, which often overestimates the size of its target and underestimates its density, this U-Net model accurately delineated the boundary of a target. Furthermore, this DL inversion detected deep, small, or low saturation CO2 plumes that are often more difficult to resolve with conventional gravity inversion methods. We note the limitations of this feasibility study, including the use of synthetic data with regular CO2 plume shapes, and the prediction of a 2-D plume cross-section rather than the full 3-D plume, as well, we recognize the lower detection fraction for double-plume scenarios. Nevertheless, this study demonstrates that DL gravity inversion is a promising and potentially superior method to conventional least-squares inversion. Our U-Net based deep learning inversion approach may be adapted for inversion of other types of geophysical data. DL inversion can facilitate near real-time monitoring of geologic carbon sequestration to provide site operators with prompt information about subsurface CO2 distribution for risk management and mitigation.
Prasad, K. N. D.Bansal, A. R.Prakash, OmSingh, A. P....
14页
查看更多>>摘要：We estimated the Curie depth using magnetic anomalies in the tectonically complex central Indian shield. The modified centroid method for the scaling distribution of sources is applied to aeromagnetic data and satellite magnetic data (EMAG2) to estimate the Curie depths. We selected 80% overlapping with a window length of 300 x 300 km(2) for Curie depth estimation. The estimated Curie depths are 22-46 km being shallower in the Bastar craton, northern end of the Aravalli-Delhi fold belt, and eastern part of Central Indian tectonic zone in the Deccan Volcanic Province. Deeper Curie depths are found in the eastern parts of the Aravalli-Delhi fold belt, Deccan Volcanic Province to the south of Tapti basin, parts of the Ganga and Vindhyan basins. The heat flow values estimated from the Curie depths vary from 30 to 90 mW/m(2) being higher are in the northern part covering the Aravalli-Delhi fold belt and the Ganga basin and low heat flow values in the remaining study region. The computed thermal lithospheric thickness ranges 62-120 km, being 62 km thin in the Vindhyan basin, 68 km in the Aravalli-Delhi fold belt, and 73 km in the Bastar craton. We noticed a relatively thick thermal lithospheric thickness of 99 km beneath the foreland Ganga basin and 100 km in the Bundelkhand craton. The thermal lithosphere beneath the Deccan Volcanic Province is found to have a thickness similar to 120 km , which is interpreted as due to the rapid cooling of the lithosphere after Reunion plume activity. Probably, the plume activities in the past could have modified the thermal lithospheric structure beneath central India. The upper mantle in the Deccan Volcanic Province to the south of the Tapti basin and the Aravalli-Delhi fold belt show magnetic character.
查看更多>>摘要：Shear wave imaging has been proposed to detect shallow buried target objects in recent years. However, moderate results have been achieved with limited success since the resultant surface waves hinder the practical applicability of the method. In this paper the influence of surface waves is reduced prior to the image fusion for pipe localization. Field tests were carried out in the Hefei Institute of Public Safety, Tsinghua University. A sensor array was adopted to measure the ground surface vibration in response to the shear wave excitation. The method of connected subgraph traversal is applied to each image to show the suspected depth region of the target pipe. The fused image is subsequently obtained by extracting and fusing the suspected feature regions from the sequence imaging results and attenuating them with equal weighting. The image is finally analyzed to identify the burial depth. Furthermore, the effect of different sensor types and the interference effect of ambient noise on the imaging results are investigated experimentally. Test results show good agreement between the detected and actual depth of the buried pipeline.
查看更多>>摘要：Surface wave tomography has been widely used to determine shear wave velocities by inverting surface wave dispersion curves. Conventional least-squares inversions strongly depend on an initial model and Monte Carlo inversion algorithms are usually time-consuming. In this study, we apply a deep neural network (DNN) to surface wave dispersion curves to investigate whether the initial model can be relaxed and whether reliable shear velocity models can be constructed. By applying our method to synthetic and field data, our results show that: (1) by constructing a well-trained DNN model from the global continental CRUST1.0 data, the DNN approach is effective and efficient to determine shear velocity structures using Rayleigh wave dispersion curves; (2) using the well-trained DNN model, no prior model is required, relaxing the requirement of an initial model; (3) the welltrained DNN model can be used to construct pseudo 3D seismic models across different continental areas.
NSTL
Elsevier