Automated Machine Learning liberates domain scientists from selecting learners and hyperparameters and discovers the importance of atmospheric trace gases for improving surface PM2.5 estimates.
Jiwen Fan
Editor, Journal of Advances in Modeling Earth Systems
Posted inEditors' Highlights
Examining Aerosol-Cloud-Climate Interactions at a Large Scale
A new numerical setup demonstrates that aerosols could affect clouds, and hence the radiation budget, thousands of kilometers from their location.
Posted inEditors' Highlights
A Significant Advancement in Modeling the Global Methane Cycle
The capability to fully model the global methane cycle advances the international climate science community’s ability of providing essential evidence to underpin climate mitigation policy.
Posted inEditors' Highlights
Advanced Real-Time Prediction of Storms With 30-Second Refresh
A new-generation weather radar and a massive supercomputing system enables forecasts of storms refreshed every 30 seconds, a significant development in severe weather prediction.
Posted inEditors' Highlights
Accurate and Fast Emulation With Online Machine-Learning
Online training produces more accurate and stable machine-learned models than classic offline learning from big data sets.
Posted inEditors' Highlights
Machine Learning Emulation of Atmospheric Radiative Transfer
Using machine learning to represent sub-grid processes in weather and climate models holds promise, but also faces challenges. Incorporating physical knowledge can help.
Posted inEditors' Highlights
Modeling Entrainment with Machine Learning
Researchers present a new approach to modeling the stochastic mixing process of convection using a machine learning technique.
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 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.
Posted inEditors' Highlights
A New Way to Represent Microphysical Uncertainty
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.