Journal of Advances in Modeling Earth Systems 2025

21 papers
In 2025, the Journal of Advances in Modeling Earth Systems published 21 papers focusing on the integration of machine learning with traditional geophysical modeling. A primary research trend involved the development of hybrid systems, such as atmosphere-ocean models that combine physics-based simulations with machine learning for extended-range predictions. Studies also emphasized artificial intelligence in data assimilation, utilizing backpropagation and differentiable numerical models to improve weather forecasting frameworks. Atmospheric research during this period addressed cloud dynamics and microphysics, including high-resolution modeling of low cloud feedbacks and probabilistic approaches to aerosol-cloud interactions. Oceanography was represented through the use of Fourier Neural Operators for ocean emulation. Prolific contributors to the volume included Caroline Muller, Liran Peng, and Michael S. Pritchard. Collectively, the research highlighted a shift toward using large-scale ensembles and neural networks to refine parameterization design and improve the calibration of weather model forecasts.

Top Research Directions

The 15 research directions with Journal of Advances in Modeling Earth Systems 2025 papers, ranked by paper count, next to 2024. Share is the fraction of the edition’s papers in the direction.

#Direction20252024Share 2025Share 20242024 rank
1Probabilistic Forecasting and Uncertainty Quantification in Deep Learning219.5%5.3%13
2Accelerating Molecular Simulations with Physics-Informed Machine Learning104.8%0.0%—
3Bridging the Cross-Language Gap in Scientific Machine Learning104.8%0.0%—
4Bridging the GPU Acceleration Gap for Complex Algorithms104.8%0.0%—
5Bridging the Subseasonal Weather Predictability Gap104.8%0.0%—
6Coarse Grained Representations for Macromolecular Dynamics104.8%0.0%—
7Efficient Rare Event Estimation for Safety Critical Systems104.8%0.0%—
8Isolating Forced Climate Signals from Internal Variability Noise104.8%0.0%—
9Neural Emulators for Scaling Weather and Climate Models134.8%15.8%1
10Physics Informed Surrogate Modeling and Model Order Reduction104.8%0.0%—
11Reservoir Computing with Fixed Recurrent Dynamics104.8%0.0%—
12Sample Efficient Learning for Specialized Domains104.8%0.0%—
13Single Loop Stochastic Bilevel Optimization104.8%0.0%—
14The Challenge of Geographic Generalizability in Empirical Research104.8%0.0%—
15Why Prescribed Boundary Conditions Fail in Climate Modeling104.8%0.0%—

Download all directions as CSV

Institutions

Institutions credited by Journal of Advances in Modeling Earth Systems 2025 papers: a paper credits every institution named in its affiliations, once. 34 institutions share 8 credited papers.

#InstitutionPapersShare20242024 rank
1Argonne National Laboratory 225.0%0—
2Pennsylvania State University 225.0%0—
301cyfxe35 112.5%0—
4045s99b94 112.5%0—
505k0zs997 112.5%134
6AGH University of Krakow 112.5%0—
7ARC Centre of Excellence for Climate Extremes 112.5%0—
8Columbia University 112.5%0—
9Cooperative Institute for Research in Environmental Sciences 112.5%17
10Google (United States) 112.5%22
11Harvard University 112.5%0—
12Helmholtz-Zentrum Hereon 112.5%0—
13Intel (United States) 112.5%0—
14Lawrence Berkeley National Laboratory 112.5%0—
15Massachusetts Institute of Technology 112.5%131
16Microsoft (United States) 112.5%18
17National Aeronautics and Space Administration 112.5%0—
18Nvidia (United States) 112.5%24
19Pacific Northwest National Laboratory 112.5%0—
20Scripps Institution of Oceanography 112.5%25
21Stanford Medicine 112.5%0—
22Stony Brook University 112.5%0—
23Texas A&M University 112.5%0—
24Tsinghua University 112.5%125
25University of California San Diego 112.5%23
26University of California System 112.5%0—
27University of California, Berkeley 112.5%0—
28University of California, Irvine 112.5%132
29University of California, Santa Cruz 112.5%127
30University of Chicago 112.5%116

Download all institutions as CSV

About this data

Papers. Journal of Advances in Modeling Earth Systems 2025 lists 21 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers. Comparisons with 2024 use shares, since the edition went from 19 to 21 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 8 of 21 papers (38.1%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-22 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Journal of Advances in Modeling Earth Systems 2025”, https://lacuna.tiptreesystems.com/venue/journal-of-advances-in-modeling-earth-systems/2025.

Top Authors

AuthorPapers
Caroline Muller3
Troy Arcomano2
Chris Budd1
Duncan Watson-Parris1
Michel Tsamados1
Niklas Boers1
Terry O'Kane1

Impactful Papers

Papers from Journal of Advances in Modeling Earth Systems 2025 that shaped research clusters.

Influential

Papers

Title
4D‐Var Using Hessian Approximation and Backpropagation Applied to Automatically Differentiable Numerical and Machine Learning Models
ADAF: An Artificial Intelligence Data Assimilation Framework for Weather Forecasting
An Assessment of Representing Land‐Ocean Heterogeneity via CAPE Relaxation Timescale in the Community Atmospheric Model 6 (CAM6)
Assessing CO2 Fluxes for European Peatlands in ORCHIDEE‐PEAT With Multiple Plant Functional Types
Hyperbolicity and Southern Hemisphere Persistent Synoptic Events
Immersion Freezing in Particle‐Based Aerosol‐Cloud Microphysics: A Probabilistic Perspective on Singular and Time‐Dependent Models
Intensity Oscillations of Tropical Cyclones: Surface Versus Mid and Upper Tropospheric Processes
LUCIE: A Lightweight Uncoupled Climate Emulator With Long‐Term Stability and Physical Consistency
Navigating the Noise: Bringing Clarity to ML Parameterization Design With O(100) Ensembles
Ocean Emulation With Fourier Neural Operators: Double Gyre
Postprocessing East African Rainfall Forecasts Using a Generative Machine Learning Model
Prediction Beyond the Medium Range With an Atmosphere‐Ocean Model That Combines Physics‐Based Modeling and Machine Learning
PseudospectralNet: Toward Hybrid Atmospheric Models for Climate Simulations
Resolving Low Cloud Feedbacks Globally With E3SM High‐Res MMF: Agreement With LES but Stronger Shortwave Effects
Revisiting Machine Learning Approaches for Short‐ and Longwave Radiation Inference in Weather and Climate Models
Scale‐Aware Parameterization of Cloud Fraction and Condensate for a Global Atmospheric Model Machine‐Learned From Coarse‐Grained Kilometer‐Scale Simulations
Sensitivity of Self‐Aggregation and the Key Role of the Free Convection Distance
Sensitivity to Sea Ice Thickness Parameters in a Coupled Ice‐Ocean Data Assimilation System
SuperdropNet: A Stable and Accurate Machine Learning Proxy for Droplet‐Based Cloud Microphysics
The Impact of Internal Variability on Benchmarking Deep Learning Climate Emulators
Toward Calibrated Ensembles of Neural Weather Model Forecasts