How can the otherwise notorious asphaltenes help achieve solid-phase bitumen for midstream transportation? Just out—Powder bed coating of bitumen with asphaltenes to obtain solid prills for midstream transportation. Sarbajit Banerjee @Was_Zahpp Cenovus Energy authors.elsevier.com/a/1dAaU3iH4EQv0

Check out MEDIDA, Model Error Discovery with Interpretability and Data-assimilation. Our (with Pedram Hassanzadeh, Ashesh Chattopadhyay) published in the special issue of Chaos, theory-informed & data-driven approaches to advance climate sciences. 🧵 aip.scitation.org/doi/10.1063/5.…

📢Discover interpretable closures for Earth system processes! Our work unveils analytically derivable gradient model using equation discovery. Include physics-informed approaches in loss function to effectively represents small-scale processes. [Arxiv: arxiv.org/abs/2306.05014]

📢Discover interpretable closures for Earth system processes! Our work is out Pedram Hassanzadeh @laurezanna Ashesh Chattopadhyay Rambod Mojgani Yifei GUAN [Arxiv: arxiv.org/abs/2306.05014]

Karan Jakhar concluded the talks with his presentation about using machine learning to better represent small-scale processes in climate models DataWave

LEAP welcomes Karan Jakhar to our ML Journal Club tomorrow! Tune in THURSDAY, 8/31 @ 3:30pm (EDT): bit.ly/45rhIl1 #climate #physics #ML #AI #climateadaptation Columbia University Columbia Climate School Columbia Engineering U.S. National Science Foundation Rice University

Our new article about Model Hierarchies for the Climate System is out now! With a special focus on the influence of machine learning/artificial intelligence and climate change impacts agupubs.onlinelibrary.wiley.com/doi/10.1029/20… #climate #ML #AI #ClimateModels #ClimateChangeImpacts

Machine learning vs Taylor expansion: Check out our new paper "Learning Closed-Form Equations for Subgrid-Scale Closures From High-Fidelity Data: Promises and Challenges" led by Karan Jakhar + Yifei GUAN Rambod Mojgani Ashesh Chattopadhyay agupubs.onlinelibrary.wiley.com/doi/full/10.10… DataWave

Excited that our paper on uncertainty quantification of subgrid-scale parameterizations for gravity waves has been published! Work with Aditi Sheshadri funded by DataWave agupubs.onlinelibrary.wiley.com/doi/10.1029/20…

Machine learning can produce analytically derivable SGS parameterizations using physics-informed metrics. Join us for the AGU talk on Thursday morning. Pedram Hassanzadeh Yifei GUAN

We are very excited to announce our AGU 2025 session has been accepted! Join us in New Orleans, December 15–19, 2025, for session NG005: “Developments in Machine Learning Across Earth System Modeling: Subgrid-Scale Parameterizations, Emulation and Hybrid Modeling”. - You can

Join our invited speakers - Ching-Yao Lai (Stanford - Yao Lai), Sophie Abramian (Columbia), and Adam Subel (NYU) - at our #AGU25 session NG005, "Developments in Machine Learning Across Earth System Modeling: Subgrid-Scale Parameterizations, Emulation and Hybrid Modeling".