Objectives/Scope: The performance of ML-based rock properties prediction from seismic with limited and sparse well data is very often inadequate. To address this limitation, we propose a novel automatic well log regularization (ALR) method with specially designed feature augmentation strategy to improve the prediction accuracy. The effectiveness of ALR method is showcased on field data in Malay basin where we successfully predict elastic logs with 30% higher accuracy, while using only 28% less training dataset. Methods, Procedures, Process: The ALR workflow (Figure 1): (1) feature selection and augmentation; (2) training and prediction and (3) prediction optimizations. The workflow starts with predicting any logs type which are available at training but not in blind wells using standard ML workflow for all blind wells (Step 1-2). Then, these intermediately predicted logs at blind well were jointly used as input features together with seismic-derived attributes using a specially designed feature augmentation strategy (Step 3). Finally, Step 1and 2 are then repeated to predict the elastic logs using these augmented input features. Results, Observations, Conclusions: The ALR method was applied on an oil/gas field data in Malay basin to predict elastic logs (AI and SI) at five blind wells from seismic data only and compared to the standard ML workflow. Two wells were used as training (28% of all data). The prediction performance of standard ML workflow (Figure 2a) is poor and can only capture general mean values of the actual AI/SI logs. The results of ALR workflow (Figure 2b) shows 30% better prediction performance compared to the standard ML workflow. In general, the background and high-resolution trend are well captured, and the overall prediction performance is improved using the new proposed prediction method. There are conceivably two explanations for this result: a) the background (low frequency) trend of the well log is properly reconstructed in ALR using only using seismic data. This could mainly lie in the ability of augmented features in better learning the uncertain reflection-reception relationship between seismic data and elastic logs, as well as the spatial/time-varying property of seismic data; (b) The ability to learn meaningful nonlinear feature relationship between input (feature) and output (label) variables with little or no supervision seems to work properly using specially designed feature augmentation. Novel/Additive Information: The ALR method is an ML-based pseudo log generation from seismic data using specially designed feature augmentation strategy. The novel ALR implementation relaxes the requirement of having a massive amount of high-quality labeled data for training and can therefore be applied in areas with limited well data information. ALR method is proven to be highly accurate for direct elastic logs prediction and can potentially be extended to estimate petrophysical properties from seismic data.

Submitted Abstract Objectives/Scope The prediction of fluid parameter related to hydrocarbon presence using seismic data has often been limited by the performance of probability density function in estimating fluid properties from seismic inversion results. A novel fluid bulk modulus inversion (fBMI) is a pre-stack seismic inversion technique that has been developed to allow a direct estimation of pore fluid bulk modulus (Kf) from seismic data. Real data application in Malay basin showcases that Kf volume can be used to pinpoint areas with high probability of hydrocarbon presence. Methods, Procedures, Process The fluid term AVO reflectivity (Russell et al., 2011) is used as the basis of our formulation and has been extended to allow direct estimation of pore fluid bulk modulus, shearmodulus, porosity parameter and density through standard least-square inversion. The novel formulation is able to relax the dependency of fluid terms on the porosity. To demonstrate this, verifications were made against standard linear AVO approximations. Our observation shows that the young tertiary basins such as the Malay basin the fluid bulk modulus values have a big contrast between hydrocarbon saturated and water bearing reservoirs with a minimum of 60% ratio difference. The inverted fluid bulk modulus volume provides thus a direct assessment of areas with high probability of hydrocarbon saturation. Results, Observations, Conclusions In this paper, the fBMI technique is showcased on a field in the Malay basin. The outcome is demonstrated on a well panel analysis for four wells located across the study area (Figure 1). The inverted fluid bulk modulus extracted along a horizon representing the top of target reservoir is shown in Figure 2b. The blue color indicates high bulk modulus corresponds to water-bearing zone, while the yellow-red color range corresponding to low hydrocarbon-bearing zones. The areas of low fluid bulk modulus values at the north-western region are calibrated to known production zones in that region. fBMI shows areas that delineate high probability of hydrocarbon presence and provides a quantitative measure in terms of fluid parameter directly related to the presence of hydrocarbon saturations. Figure 1: Comparison analysis of water saturation (blue curve) and fluid bulk modulus (red curve) of well log data in the Malay basin. Black strips indicate the coal intervals. Figure 2: a) Inverted acoustic impedance extracted from the top reservoir horizon of a field in the Malay basin. b) The corresponding fluid bulk modulus values from fBMI. Novel/Additive Information The fBMI is a new four parameters linear amplitude-versus-offset inversion technique that provides quantitative fluid parameter directly related to fluid bulk modulus from seismic data. It is utilized as a tool for direct hydrocarbon prospect assessment to differentiate gas, oil, condensate and water.