No abstract

Data limitation and sparsity are considered the main source of non-uniqueness and ill-posedness in elastic property prediction on seismic data using Deep Learning (DL). The ill-posed regression problem can be solved by conducting adequate pre-processing steps through data augmentation, feature engineering and feature selection. In this paper, we develop a novel technique of reshaping the input data into various multi-dimensional shapes before using the data as an input for the DL model. This strategy can increase the spatial context and temporal data coverage which is important for regularizing the DL model during training process. We also investigate the model performance between a Convolutional Neural Network (CNN) and a Recurrent Neural Network (RNN), specifically the Long-Short Term Memory (LSTM) architecture on 2D synthetic seismic data. Our findings show that using the newly developed feature augmentation and input reshaping strategy with a simple LSTM model can help improve the elastic property prediction on sparse well data. We demonstrate the robustness and effectiveness in terms of visual inspection and relative accuracy measure of the proposed method by using the SEG SEAM Interpretation Challenge dataset Phase I and comparing our results with Mustafa et al.'s (2021) work.

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.