Variational autoencoders can be leveraged to provide an effective method of inversion that is both accurate and computationally efficient.
Fiber-optic cables can provide a wealth of detailed data on subsurface vibrations from a wide range of sources. Machine learning offers a means to make sense of it all.
A new algorithm suggests that only a small fraction of meteorites present on the White Continent’s surface have been recovered to date.
A new study evaluated the performance of emerging deep learning models for earthquake detection, phase identification, and phase picking.
By establishing a machine-driven approach to interpreting seismic observations of carbon dioxide injection, researchers hope to improve tracking of carbon capture and sequestration projects.
To commemorate the 400th anniversary of the Pilgrims’ crossing, a ship guided by an AI captain will embark on the same journey, doing science along the way.
Researchers applied machine learning algorithms to several distinct chemical compositions of Mars and suggest that these algorithms could be a powerful tool to map the planet’s surface on a large scale.
A novel approach to weather forecasting uses convolutional neural networks to generate exceptionally fast global forecasts based on past weather data.
By using data from two lightning-spotting satellites, researchers measure explosions of thousands of small meteors and create a database that could help the planetary defense community.
The forecasting tool IceNet promises to be a useful tool for evaluating sea ice loss in the Arctic. But ethical and logistic considerations have to be taken before scientific and Indigenous communities start working together.