• About
  • Special Reports
  • Topics
    • Climate
    • Earth Science
    • Oceans
    • Space & Planets
    • Health & Ecosystems
    • Culture & Policy
    • Education & Careers
    • Opinions
  • Projects
    • ENGAGE
    • Third Pod from the Sun
    • Eos en Español
    • Eos 简体中文版
    • Print Archive
  • Newsletter
  • Submit to Eos
  • AGU.org
  • AGU Publications
    • AGU Journals
    • Editors’ Highlights
    • Editors’ Vox
  • Career Center
  • AGU Blogs
  • Join AGU
  • Give to AGU
  • About
  • Special Reports
  • Topics
    • Climate
    • Earth Science
    • Oceans
    • Space & Planets
    • Health & Ecosystems
    • Culture & Policy
    • Education & Careers
    • Opinions
  • Projects
    • ENGAGE
    • Third Pod from the Sun
    • Eos en Español
    • Eos 简体中文版
    • Print Archive
  • Newsletter
  • Submit to Eos
Skip to content
Eos

Eos

Science News by AGU

Sign Up for Newsletter

Jiwen Fan

Editor, Journal of Advances in Modeling Earth Systems

Bar graphs from the paper
Posted inEditors' Highlights

Unleashing the Power of AutoML for Atmospheric Research

by Jiwen Fan 16 March 202315 March 2023

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.

Schematic representation of the model setup developed in this paper
Posted inEditors' Highlights

Examining Aerosol-Cloud-Climate Interactions at a Large Scale

by Jiwen Fan 7 March 202316 March 2023

A new numerical setup demonstrates that aerosols could affect clouds, and hence the radiation budget, thousands of kilometers from their location.

Diagram showing the global mean full-cycle methane budget.
Posted inEditors' Highlights

A Significant Advancement in Modeling the Global Methane Cycle

by Jiwen Fan 8 September 202213 March 2023

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.

Four radar reflectivity diagrams.
Posted inEditors' Highlights

Advanced Real-Time Prediction of Storms With 30-Second Refresh

by Jiwen Fan 19 August 202228 September 2022

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.

Four world maps showing the simulation of surface ozone by an offline-trained and online-trained machine learning (ML) solver.
Posted inEditors' Highlights

Accurate and Fast Emulation With Online Machine-Learning

by Jiwen Fan 16 August 202220 December 2022

Online training produces more accurate and stable machine-learned models than classic offline learning from big data sets.

Graphs showing the vertical profiles of the error in shortwave downwelling flux, upwelling flux, and heating rates computed from fluxes.
Posted inEditors' Highlights

Machine Learning Emulation of Atmospheric Radiative Transfer

by Jiwen Fan 2 August 202213 February 2023

Using machine learning to represent sub-grid processes in weather and climate models holds promise, but also faces challenges. Incorporating physical knowledge can help.

Two Paluch diagrams, one showing a large-eddy simulation and one showing the new machine learning model.
Posted inEditors' Highlights

Modeling Entrainment with Machine Learning

by Jiwen Fan 27 July 20226 January 2023

Researchers present a new approach to modeling the stochastic mixing process of convection using a machine learning technique.

Diagram showing the three barriers in seasonal forecast and the Conditional Generative Forecasting methodology developed to tackle these three barriers.
Posted inEditors' Highlights

Learning from Climate Simulations for Global Seasonal Forecast

by Jiwen Fan 23 June 202222 December 2022

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.

Maps of time-mean precipitation pattern error for 40-day simulations with three configurations of a global atmospheric model with a coarse 200-km grid.
Posted inEditors' Highlights

Corrective Machine Learning for Improving Climate Models

by Jiwen Fan 15 March 20225 January 2023

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.

Series of charts from the paper by Feng et al.
Posted inEditors' Highlights

A New Way to Represent Microphysical Uncertainty

by Jiwen Fan 2 November 202111 August 2022

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.

Posts navigation

1 2 Older posts

Features from AGU Journals

RESEARCH SPOTLIGHTS
Earth’s Future
“How to Build a Climate-Resilient Water Supply”
By Rachel Fritts

EDITORS' HIGHLIGHTS
AGU Advances
“How Do Atmospheric Rivers Respond to Extratropical Variability?”
By Sarah Kang

EDITORS' VOX
Reviews of Geophysics
“Rare and Revealing: Radiocarbon in Service of Paleoceanography”
By Luke C. Skinner and Edouard Bard

About Eos
ENGAGE
Awards
Contact

Advertise
Submit
Career Center
Sitemap

© 2023 American Geophysical Union. All rights reserved. Proudly powered by Newspack by Automattic