A new book examines how fiber-optic cables installed in boreholes can monitor seismic activity, fluid flow, subsurface temperatures, and more.
machine learning & AI
Posted inEditors' Highlights
Machine Learning Enhances Image Analysis in Biogeosciences
Machine learning can enhance our ability to identify communities of microorganisms and how they change in response to climate change over time.
Posted inEditors' Vox
Unlocking the Power of Synthetic Aperture Radar for Geosciences
Due to its unique ability to monitor Earth’s surface, Synthetic Aperture Radar plays a pivotal role in revolutionizing the geosciences.
Posted inEditors' Vox
What’s On the Horizon for Open Access Geoscience Books?
On the first anniversary of their partnership, AGU and the Geological Society of London reflect on the GeoHorizons series and why open access books are valuable for the geoscience community.
Posted inResearch Spotlights
Machine Learning Could Improve Extreme Weather Warnings
A deep learning technique could reduce the error in 10-day weather forecasts by more than 90%, allowing communities to better prepare for extreme events such as heat waves.
Posted inEditors' Highlights
Forecasting Caldera Collapse Using Deep Learning
A deep learning model trained with geophysical data recorded during the well-documented 2018 Kilauea volcano eruption, Hawaii, predicts recurrent caldera collapse events.
Posted inOpinions
Cultivating Trust in AI for Disaster Management
Artificial intelligence applied in disaster management must be reliable, accurate, and, above all, transparent. But what does transparency in AI mean, why do we need it, and how is it achieved?
Posted inResearch Spotlights
Physics Meets Machine Learning for Better Cyclone Predictions
A new hybrid modeling approach combines physics-based and machine learning models to extend—and improve—path and intensity predictions of tropical cyclones.
Posted inEditors' Highlights
Equation Discovery for Subgrid-Scale Closures
Machine learning can discover closure equations for fluid simulations. A new study finds that common algorithms rediscover known, unstable closures, which can be stabilized with higher-order terms.
Posted inNews
New Model Can Better Predict Areas Vulnerable to Forest Fires in India
Researchers incorporated local atmospheric parameters and terrain data to more accurately estimate the probability of fire in a specific area.