Receiver functions, an important tool in understanding sub-surface interfaces, can be analysed through carefully implemented neural networks. We demonstrate this approach. Previously, we introduced our receiver function tool set, Pythonic Global Lithospheric Imaging using Earthquake Recordings (PyGLImER). PyGLImER enables us to: [1] create a database of teleseismic event displacement records at worldwide seismic stations, [2] compute receiver functions from these records, and [3] compute volumetric common conversion point (CCP) stacks from the receiver functions and their conversion points. CCP stacking is a standard tool to image the subsurface using receiver functions. The CCP stacks represent rich but large, three-dimensional volumes of data that contain information about discontinuities in Earth’s crust and upper mantle. One goal of the interpretation of CCPs is the identification of such discontinuities. Automated picking routines reduce discontinuities to singular peaks and troughs, thus discarding the wealth of information available over the whole depth range, such as integrated discontinuity impedance and regional geometry. However, the obvious alternative, manual picking, is not feasible for large data volumes. Here, we explore the possibility of fully-automated segmentation of 3D CCP volumes through the application of image processing routines and machine learning to successive volume cross-sections. With our picking tool, we manually label discontinuities in CCP slices to serve as training and validation sets.We use these labeled datasets as input to train a convolutional neural network (CNN) to perform pixel-wise identifications in subsurface images. When applied to all slices of the CCP stack, the CNN outputs a fully-segmented 3D model, which furnishes quantitative exploration of subsurface discontinuity morphology. Specifically, we can investigate the thickness/width, intensity, and topography of discontinuities across continents. This information has the potential to improve our understanding of, e.g., mantle transition zone phase transitions and, therefore, mantle dynamics.

Over the last decades, the receiver function technique has been widely used to image sharp discontinuities in elastic properties of the solid Earth at regional scales. To date, very few studies have attempted to use receiver functions for global imaging. One such endeavour has been pursued through the project “Global Lithospheric Imaging using Earthquake Recordings” (GLImER). Building on the advances of GLImER, we have developed PyGLImER - a Python-based software suite capable of creating global images from both P-to-S and S-to-P converted waves via a comprehensive receiver function workflow. This workflow creates a database of receiver functions by downloading seismograms from selected earthquakes and analysing the data via a series of steps that include pre-processing, quality control, deconvolution, and stacking. The stacking can be performed for common conversion points or single stations. All steps leading to the creation of receiver functions are automated. To visualise the generated stacks, the user can choose the desired survey area in a graphical user interface, and then explore the selected region either through 2D cross-sections or a 3D volume. By incorporating results from two independent seismic phases, we can combine the advantages of both phases for imaging different discontinuities. This results in an increased robustness and resolution of the final image. For example, we can use constraints from S receiver function images, which are multiple-free but relatively low resolution, to differentiate between real lithospheric/asthenospheric structures and multiple-induced artefacts in higher-resolution P receiver function images. Our preliminary results agree with those from recent regional and global studies, confirming the workflowís robustness. They also indicate that the new workflow combining P and S receiver functions has the potential to resolve global lithospheric discontinuities such as the lithosphere-asthenosphere boundary (LAB) or the midlithospheric discontinuity (MLD) more reliably than approaches using only one type of incident phase. PyGLImER will be distributed as open-source software, providing an easily accessible tool to rapidly generate high-resolution images of structures in the lithosphere and asthenosphere over large scales.