一种处理卫星气溶胶观测数据的新方法提高了模拟精度，有望为天气和气候预报带来助益。
machine learning & AI
Posted inNews
U.S. River Sediment Transport Is Becoming “Burstier”
The time frame in which U.S. rivers move most of their sediment has compressed significantly, which could have implications for water treatment, aquatic habitats, erosion, and harmful algal blooms.
Posted inScience Updates
The AI Upgrade Helping Perseverance Work Smarter on Mars
The rover’s On Board Planner software uses artificial intelligence to reduce wasted time and energy by making on-the-spot scheduling decisions.
Posted inEditors' Vox
Opening Access to Earth Observation Data for Disaster Mitigation
A new open access book explores how data from the latest ground-based, airborne, and space-based remote sensing observations inform and improve disaster resilience.
Posted inResearch Spotlights
Using Machine Learning Techniques for Polar Vortex Predictions
A new model accurately reproduces aspects of polar vortex behavior, extracting indicators of imminent vortex collapse and accompanying frigid weather in North America and Europe.
Posted inScience Updates
Reliable AI Sea Ice Forecasts Depend on Sustained Observations
Sea ice is a fundamental regulator of Earth’s climate and an increasingly urgent forecast target itself. Can we trust the AI systems now being built to predict it?
Posted inResearch Spotlights
Scientists Zero In on Tiny Particles to Improve Weather and Air Quality Forecasts
A new method for handling satellite aerosol observations boosts simulation accuracy, with potential benefits for weather and climate forecasting.
Posted inEditors' Vox
How Can We Make Better Decisions About What Lies Underground?
Geophysical data offer incomplete clues about the subsurface. Bayesian inversion turns them into plausible scenarios and shows which uncertainties matter for real-world decisions.
Posted inEditors' Highlights
Streamflow From Generative AI
The trifecta of predicting, assimilating, and downscaling streamflow has arrived with generative diffusion AI models.
Posted inOpinions
A Hybrid Approach for Revealing Headwater Hydrology
Coordinated work to compile existing data and apply models pairing physical understanding with machine learning could substantially improve streamflow predictions for little-known headwater basins.