Toxic particulate matter has decreased by about a third over the past decade, but levels are still above what’s considered healthy.
machine learning & AI
Posted inEditors' Highlights
Learning from Climate Simulations for Global Seasonal Forecast
A probabilistic deep learning methodology that learns from climate simulation big data offers advantageous seasonal forecasting skill and crucial climate model diagnosis information at a global scale.
Posted inResearch Spotlights
Algorithm Detects Thousands of Missing Levees from U.S. Database
An existing levee database accounts for just one fifth of the country’s actual total levee count, limiting the study of how these embankments affect riparian ecosystem health in the United States.
Posted inEditors' Vox
The Big Data Revolution Unlocks New Opportunities for Seismology
The field of seismology is entering a new era where our understanding of earthquakes and the solid earth is increasingly driven by new Big Data experiments and algorithms.
Posted inEditors' Highlights
Using Artificial Intelligence to Study Convection
Machine learning techniques are used to examine relationships between the large-scale state of the atmosphere, the convection total area, and the degree of organization in northern Australia.
Posted inNews
Monitoring Earthquakes at the Speed of Light
New research uses gravity and a machine learning model to instantaneously estimate the magnitude and location of large earthquakes.
Posted inEditors' Highlights
Machine Learning Helps See into a Volcano’s Depths
How big might future volcanic eruptions be? Crystals carry information to answer this and machine learning methods can visualize and interpret this multidimensional data.
Posted inEditors' Vox
Understanding and Utilizing the Fractured Earth
The prediction of flow and transport in fractured rock is one of the great challenges in the Earth and energy sciences with far-reaching economic and environmental impacts.
Posted inResearch Spotlights
Testing a Machine Learning Approach to Geophysical Inversion
Variational autoencoders can be leveraged to provide an effective method of inversion that is both accurate and computationally efficient.
Posted inEditors' Highlights
Corrective Machine Learning for Improving Climate Models
A machine-learned correction enables an efficient coarse-grid global atmosphere model to better track the weather and time-mean precipitation of an expensive fine-grid ‘digital twin’ reference model.