The prediction of subsurface properties such as velocity, density, porosity, and water saturation has been the main focus of petroleum geosciences. Advanced methods such as Full Waveform Inversion (FWI), Joint Migration Inversion (JMI) and ML-Rock Physics are able to produce better predictions than their predecessors, but they still require tedious manual interpretation that is prone to human error. The research on these methods remains open as they suffer from technical limitations. As computing resources are becoming cheaper, the use of a single deep-generative adversarial network is feasible in predicting all these properties in a completely data-driven manner. In our proposed method of multiscale pix2pix applied to SEG SEAM salt data, we have managed to map from one input, which is seismic post-stack data, to several outputs of reservoir and elastic properties such as porosity, velocity, and density by using only one trained model and without having to manually interpret or pre-process the input data. With 90% accuracy of the results in the synthetic data testing, the method is worthy of being explored by the petroleum geoscience fraternity.

No abstract

No abstract

This reference is for an abstract only. A full paper was not submitted for this conference. Abstract The time-domain Controlled Source Electromagnetic (tCSEM) method is emerging as a practical tool for oil and gas exploration on land and shallow marine environments (Wright et al., 2002; Ziolkowski et al., 2007). In particular, it can overcome the airwave interference problem faced by frequency-domain CSEM method in shallow water (Weiss, 2007). We have used a 1D broadband tCSEM inversion technique developed in-house. The forward problem is solved using the algorithm of Edwards (1997) while the inverse problem is solved using a variety of nonlinear parameter estimation methods (Meju, 1992, 1994). The inversion method generates either blocky sharp-boundary model or the smoothest model that fits the data recorded for different offsets and various transient times. In this work, a layered-earth resistivity model was constructed using the local borehole resistivity log and served as the test model (ground-truth). The parameters of this model were systematically varied and used to generate forward model responses enabling us to determine the effect of target depth, thickness and resistivity variations. The synthetic data for the ground-truth model were finally inverted to test the detection capability of tCSEM. The aim of our research was to evaluate the applicability of tCSEM technology in East Malaysia environment by studying the effect of target and water depth, target thickness, target resistivity variation, and target detection limits using a combined numerical modelling and inversion approach. The results of modeling and inversion studies suggest that the tCSEM method is capable of detecting hydrocarbon reservoirs in East Malaysia environment. The inversion responses become more significant when dealing with thick, strong resistivity, and shallow marine hydrocarbon target. From the case of target depth variation, the inversion responses capable to distinguish hydrocarbon target at difference depth. From this study, we capable to investigate in detail about the strength and limitation of this method in East Malaysia environment and this beneficial information can become a guideline for future feasibility study and tCSEM survey planning. Furthermore, this method also can be used as an alternative method to provide technical solution and reduce exploration risk especially in shallow marine environment.

Submitted Abstract The aim in characterizing reservoir on seismic is to be able to precisely assess rock and fluid properties from seismic data. Despite several approaches available, geoscientists still facing issue to accurately characterize the elastic & reservoir properties from seismic. This mainly because of the implementation of simplified linearized algorithms and assumptions which unable to fully address problem with non-linearity and non-uniqueness solution. Besides, the conventional approaches also typically take a very long turnaround time due to extensive computational works. Hence, implementation of deep learning-based seismic inversion with incorporation of a generalized rock physics knowledge for elastic properties prediction perhaps might be able to address the issues. The proposed approach consists of 4 main phases. The first phase is to develop rock physics understanding based on in-situ available reference well data. In the next phase, realistic synthetic dataset library at various pseudo well location is generated that mimic the actual subsurface reservoir condition and the corresponding seismic data from those pseudos well library is subsequently simulated. The third phase is to implement U-net deep learning network architecture with residual blocks of ResNet-18 for training, validation, and testing, utilizing synthetic data library generated in the previous phase. The fourth phase is to apply the pre-trained predictive network model on the actual seismic dataset as input for rock properties estimation. The robustness of the proposed approach is first evaluated based on synthetic dataset. Exceptionally good coefficient cross-correlation is obtained after evaluation on the predicted and true elastic properties; while results on the blind test dataset are slightly less compared to the training performance. This shows that the implemented model architecture with specially designed residual blocks can generalize quite well. The network model able to qualitatively distinguish the properties variation and capture the background trend of each elastic property. Besides, the proof-of-concept exercise also is successfully verified on a fluvial dominated field in Malay basin. Qualitatively, the predictive network model able to capture the background trend with some minor overfitting and identify the relative deviation of the elastic properties. The promising results are also comparable with results produced from commercial software, yet with faster turn-around time and more efficient workflow. In this work, a new approach of deep learning-based seismic inversion is introduced for elastic properties prediction which incorporates a generalized rock physics knowledge and a complex deep learning networks architecture of U-Net with residual block ResNet-18.