The new graph convolutional recurrent neural network (GCRNN) will enable water utilities to forecast water use, even if some sensors fail.
Hurricane winds can lead to coast downwelling, which brings warmer surface water near the coast and can contribute to the intensification of the landfalling hurricane.
Lo uses her background in atmospheric sciences to forecast pollen concentrations.
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.
New research indicates climate change may thin the mixed layer and contribute to a reduction of sea surface temperature anomalies.
An analysis of the impact of targeted observations from the Geostationary Interferometric Infrared Sounder at high-temporal resolution on forecasts for Typhoon Maria in 2018.
Improvements in our ability to forecast oceanic conditions weeks to months in advance will help communities, industries, and other groups prepare amid a changing climate.
A new way of representing microphysical uncertainty in convective-scale data assimilation reduces biases in model states and improves the accuracy of short-term precipitation forecasts.
The pioneering use of satellite-based synthetic aperture radar to characterize tropical cyclones in near-real time has provided a crucial new tool with which to forecast powerful storms.
The assessment of space weather event forecasts would benefit from more nuanced approaches that take account of event intensities peaking near the thresholds used to identify such events.