Prediction of seismic P-wave velocity using machine learning

Abstract

Abstract. Measurements of seismic velocity as a function of depth are generally restricted to borehole locations and are therefore sparse in the world's oceans. Consequently, in the absence of measurements or suitable seismic data, studies requiring knowledge of seismic velocities often obtain these from simple empirical relationships. However, empirically derived velocities may be inaccurate, as they are typically limited to certain geological settings, and other parameters potentially influencing seismic velocities, such as depth to basement, crustal age, or heat flow, are not taken into account. Here, we present a machine learning approach to predict the overall trend of seismic P-wave velocity (vp) as a function of depth (z) for any marine location. Based on a training dataset consisting of vp(z) data from 333 boreholes and 38 geological and spatial predictors obtained from publicly available global datasets, a prediction model was created using the random forests method. In 60 % of the tested locations, the predicted seismic velocities were superior to those calculated empirically. The results indicate a promising potential for global prediction of vp(z) data, which will allow the improvement of geophysical models in areas lacking first-hand velocity data.

Estimating Compressional Velocity and Bulk Density Logs in Marine Gas Hydrates Using Machine Learning

“…We use six supervised machine learning algorithms and compare the accuracy and error for each algorithm using R 2 and the mean absolute percentage error (MAPE). We selected these algorithms as they have been used previously in geoscience applications [27,[30][31][32]. Some machine learning algorithms have hyperparameters that can be tuned to predict outputs with the highest accuracy and least error.…”

“…Similarly, Farfour, and Mesbah; Ismail et al; and Ramya et al [17][18][19] used artificial neural networks to interpret subsurface features such as gas chimneys, channels, and hydrocarbon-saturated rocks using marine seismic data. Dumke and Berndt [32] used V p logs, local geological information (such as water depth and distance to the basement), and the random forest algorithm to predict subseafloor V p trends worldwide. In a more related study conducted in an Arctic permafrost region, Singh et al [27] used a variety of different machine learning algorithms and well log combinations to predict gas hydrate saturation.…”

Machine-learning models to predict P- and S-wave velocity profiles for Japan as an example

“…ML algorithms are well suited for making regression models on complex data-driven problems. Researchers have studied V P or V S estimation based on ML (e.g., Singh and Kanli, 2016;Paul et al, 2018;Anemangely et al, 2019;Dumke and Berndt, 2019;Wang and Peng, 2019;Zhang et al, 2020). In particular, Dumke and Berndt (2019) used the Random Forest (RF) regression algorithm to estimate V P as a function of depth on global marine locations.…”

“…Researchers have studied V P or V S estimation based on ML (e.g., Singh and Kanli, 2016;Paul et al, 2018;Anemangely et al, 2019;Dumke and Berndt, 2019;Wang and Peng, 2019;Zhang et al, 2020). In particular, Dumke and Berndt (2019) used the Random Forest (RF) regression algorithm to estimate V P as a function of depth on global marine locations. They used data from 333 boreholes and considered 38 geological variables, such as site coordinates, sediment thickness, and depth below the seafloor.…”

Prediksi Kecepatan Gelombang Geser (Vs) Menggunakan Machine Learning Di Sumur X

“…Namun, data terkait kecepatan gelombang geser tersebut tidak tersedia untuk semua sumur, terutama pada sumur tua karena memerlukan biaya yang tinggi (Akhundi dkk., 2014). Mengingat pentingnya data kecepatan gelombang geser untuk karakterisasi reservoir, maka sangat penting untuk memperkirakan parameter ini menggunakan data logging di sumur lainnya (Dumke & Berndt, 2019).…”