Gully erosion is the most severe form of soil erosion, and it can seriously impact agricultural fields, contributing to sediment loss and nutrient runoff into waterways. In a new study, University of Illinois Urbana-Champaign researchers use a new AI-driven approach that combines machine learning with an interpretability tool to enhance the prediction of gully formation and understanding of these models. They tested the methodology on land in Jefferson County, Illinois. 

A new study led by researchers from the Guangzhou Institute of Geochemistry of the Chinese Academy of Sciences, along with international collaborators, reveals that deeply subducted carbonates can cause significant variations in the redox states of Earth's mantle. This process influences the formation of sublithospheric diamonds and plays a role in the long-term evolution of cratons—ancient stable parts of the continental lithosphere.

An artificial intelligence technique for detecting DNA fragments shed by tumors and circulating in a patient’s blood, developed by Johns Hopkins Kimmel Cancer Center investigators, could help clinicians more quickly identify and determine if pancreatic cancer therapies are working.

As extreme weather events become more common, researchers are turning to higher- quality information. However, interpreting these massive datasets presents another set of challenges, such as maintaining accuracy and keeping costs down. Paris Perdikaris of the University of Pennsylvania and collaborators at Microsoft Research have created Aurora, a low-cost model that can predict a wide range of environmental events.

Astronomers have witnessed for the first time a violent cosmic collision in which one galaxy pierces another with intense radiation. Their results, published today in Nature, show that this radiation dampens the wounded galaxy’s ability to form new stars. This new study combined observations from both the European Southern Observatory’s Very Large Telescope (ESO’s VLT) and the Atacama Large Millimeter/submillimeter Array (ALMA), revealing all the gory details of this galactic battle.

SeaSplat is an image-analysis tool that cuts through the ocean’s optical effects to generate images of underwater environments reveal an ocean scene’s true colors. Researchers paired the color-correcting tool with a computational model that converts images of a scene into a three-dimensional underwater “world” that can be explored virtually.