Recent advancement in machine learning have provided new paradigms for scientists and engineers to solve challenging problems. Here we apply a new strategy in machine learning (physics-informed neural networks (PINNs)) to seismic imaging, that takes advantage of the governing physical laws to complement the limited data available (seismograms). We design synthetic seismic imaging experiments and demonstrate that PINNs provides a computationally simple and efficient alternative to traditional seismic inversion solvers. The method proposed in this study can be naturally extended to other geophysical data inversions based on a similar framework.

Recovering ancient records of Earth's magnetic field is challenging because the magnetization in rocks is often reset by heating during tectonic burial over their long and complex geological histories. We show that rocks from the Isua Supracrustal Belt in West Greenland have experienced three thermal events throughout their geological history. The first event was the most significant, and heated the rocks up to 550°C 3.7-billion-years-ago. The subsequent two events did not heat the rocks in the northernmost part of the area above 380°C. We use multiple lines of evidence to test this claim, including paleomagnetic field tests, the metamorphic mineral assemblages across the area, and the temperatures at which radiometric ages of the observed mineral populations are reset. We use these lines of evidence to argue that an ancient, 3.7 billion year old record of Earth's magnetic field may be preserved in the banded iron formations in the northernmost part of the field area. The magnetization was acquired during mineral transformation associated with the first thermal event and therefore only a lower limit on the strength of the ancient magnetic field was constrained. However, we are able to conclude that the ancient magnetic field was likely comparable with the strength of Earth's magnetic field today.

Plate tectonic theory is the framework that describes everything from the formation of the continents billions of years ago to natural disasters such as volcanoes, earthquakes, and tsunamis today. Even climate change estimates over geologic timescales rely on accurate plate tectonic reconstructions to understand the paleo-oceans. Despite the intricate links between plate tectonics and life on Earth, exactly what makes a plate “plate-like” is debated. In other words, what properties define the transition from the rigid plate, or lithosphere, to the weaker, convecting asthenosphere, and where does this transition occur? Classically, the lithosphere-asthenosphere boundary is defined thermally, with a gradual transition from the cold conductively cooling lithosphere to the warmer, convecting asthenosphere beneath. Overall, lithospheric thickening with age is observed beneath the oceans and toward the continental interiors suggesting that temperature and conductive cooling play a first-order role in controlling lithospheric thickness. However, within any given tectonic age interval a wide range of lithospheric thicknesses have been reported. Observations of sharp changes with depth in seismic wave speed and strong anomalies in seismic wave speed and electrical resistivity are similarly inconsistent with the smooth variations predicted by simple conductive cooling. Other properties or processes must define the tectonic plate. The lithosphere may be relatively dehydrated, which would enhance its strength. In contrast, asthenospheric hydration could make it relatively weak and also reduce its melting temperature. A small amount of partial melt beneath the plate in the asthenosphere may exist, which could further ease convection and therefore define the plate. Melt provides a simple explanation for a host of observations with large implications for plate tectonics, mantle dynamics, and Earth's evolution. So far reports of melt are variable in location and character. The variability in lithospheric thickness and also melt location and character suggests that the lithosphere-asthenosphere boundary is likely dynamic and dictated by mantle dynamics including melt generation and migration.

Plate tectonic theory holds that the horizontal movement of tectonic plates drives crustal thickening and the formation of mountain ranges where plates collide, and crustal thinning in rift basins where plates diverge. The dominance of this process, however, obscures a key secondary source of topographic variation caused by density variations within the underlying mantle. In this study, we compile two new databases. The first is a global compilation of crustal thickness and seismic velocity measurements obtained from seismic experiments. The second is a compilation of laboratory analyses of seismic velocity in crustal rocks as a function of temperature, pressure and density. We combine these data sets to accurately map that component of continental topography caused by crustal thickness and density variations and use it to isolate the secondary, residual component supported by the mantle. We find that a substantial proportion of topography is supported by the temperature and chemical structure of the mantle and is manifest as topographic swells and basins that can occur within interiors of tectonic plates, have amplitudes of up to 2 km, and length scales ranging from hundreds to thousands of kilometers. Independent geologic evidence suggests that some of these topographic features developed over million-year time scales.