Synthetic Sonic Log Generation With Machine Learning: A Contest Summary From Five Methods

Abstract

Compressional and shear sonic traveltime logs (DTC and DTS, respectively) are crucial for subsurface characterization and seismic-well tie. However, these two logs are often missing or incomplete in many oil and gas wells. Therefore, many petrophysical and geophysical workflows include sonic log synthetization or pseudo-log generation based on multivariate regression or rock physics relations. Started on March 1, 2020, and concluded on May 7, 2020, the SPWLA PDDA SIG hosted a contest aiming to predict the DTC and DTS logs from seven “easy-to-acquire” conventional logs using machine-learning methods (GitHub, 2020). In the contest, a total number of 20,525 data points with half-foot resolution from three wells was collected to train regression models using machine-learning techniques. Each data point had seven features, consisting of the conventional “easy-to-acquire” logs: caliper, neutron porosity, gamma ray (GR), deep resistivity, medium resistivity, photoelectric factor, and bulk density, respectively, as well as two sonic logs (DTC and DTS) as the target. The separate data set of 11,089 samples from a fourth well was then used as the blind test data set. The prediction performance of the model was evaluated using root mean square error (RMSE) as the metric, shown in the equation below: RMSE=sqrt(1/2*1/m* [∑_(i=1)^m▒〖(〖DTC〗_pred^i-〖DTC〗_true^i)〗^2 + 〖(〖DTS〗_pred^i-〖DTS〗_true^i)〗^2 ] In the benchmark model, (Yu et al., 2020), we used a Random Forest regressor and conducted minimal preprocessing to the training data set; an RMSE score of 17.93 was achieved on the test data set. The top five models from the contest, on average, beat the performance of our benchmark model by 27% in the RMSE score. In the paper, we will review these five solutions, including preprocess techniques and different machine-learning models, including neural network, long short-term memory (LSTM), and ensemble trees. We found that data cleaning and clustering were critical for improving the performance in all models.

A Dataset of 3D Structural and Simulated Transport Properties of Complex Porous Media

“…Quantification of electrical behavior in porous media has supported advancements in petroleum reservoir characterization 46 , 47 , CO 2 monitoring in carbon capture and storage 48 , hydrogeology 49 , mineral exploration 50 , and battery development 51 . In these composite systems, electrical conductivity measurements aid in inferring the composition of the material and its phase distributions.…”

Reducing the Uncertainty of Multi-Well Petrophysical Interpretation from Well Logs via Machine-Learning and Statistical Models

“…To perform more accurate reservoir characterization, many machine-learning methods have been previously proposed for lithology identification, depth matching, formation property estimation, and well-log correlation in carbonate and clastic reservoirs (Gashler, 2008;Bestagini et al, 2017;Sidahmed et al, 2017;Shashank and Mahapatra, 2018;Bennis and Torres-Verdín, 2019;Brazell et al, 2019;Liang et al, 2019;Shao et al, 2019;Yu et al, 2021). Compared to petrophysical model-based methods, e.g., Timur-Coats equation and Windland's equation (Leverett, 1941;Timur, 1968), machine-learning approaches obtain better results by fitting more complex relationships between well logs and formation properties.…”

Unveiling the Feasibility of Coalbed Methane Production Adjustment in Area L through Native Data Reproduction Technology: A Study

“…Yu et al found that data cleaning and clustering were critical for improving the performance in all models. However, it was also found that it was necessary to adopt median filtering for input logs to alleviate the aliasing problem caused by data interpolation and eliminate outliers [15].…”