GPU-optimized ocean modeling achieves decade-long simulations in a day, enabling mesoscale-resolving climate simulations that open new opportunities for long-term planning in a changing climate.
machine learning & AI
A Two-Step Approach to Training Earth Scientists in AI
Researchers learned machine learning methods during a boot camp, then applied their new knowledge to real-world research problems during a hackathon.
Calibrating Climate Models with Machine Learning
Using machine learning, researchers automatically calibrate a comprehensive climate model, improving simulations of difficult features and taking steps toward more reliable climate projections.
Machine Learning Provides a New Perspective of Low-level Clouds
Low-level clouds over the oceans, extensively studied for their role in climate change, are re-examined from a new perspective that applies machine learning to radar observations.
Using Algorithms to Help Find Life on Icy Ocean Worlds
Scientists could use machine learning to analyze atmospheric samples in order to help identify microbes on frozen moons. They’re testing the concept using bottles of brine and smelly bacteria.
Listening to Groundwater Dynamics
Deep learning from shallow passive seismic data reveals groundwater table depth information in space and time.
Particulate Pollution and its Climate Impacts During the COVID-19 Pandemic
The impacts of COVID-19 on short-lived pollutants highlight the predominant influence of the transportation sector and the resulting changes in regional climates and ecosystems.
Mercury’s Hollows may be Young and Active
The first machine learning-derived global-scale survey of Mercury’s hollows suggests they are young features that may be active and will continue to evolve.
Fast Adept Sea Ice Forecasts
Artificial intelligence facilitates an efficient, skillful surrogate of a coupled Arctic sea ice prediction model using generative diffusion.