Zobrazeno 1 - 10
of 709
pro vyhledávání: '"HARRINGTON, PETER"'
Autor:
Xu, Shaoming, Renganathan, Arvind, Khandelwal, Ankush, Ghosh, Rahul, Li, Xiang, Liu, Licheng, Tayal, Kshitij, Harrington, Peter, Jia, Xiaowei, Jin, Zhenong, Nieber, Jonh, Kumar, Vipin
Streamflow, vital for water resource management, is governed by complex hydrological systems involving intermediate processes driven by meteorological forces. While deep learning models have achieved state-of-the-art results of streamflow prediction,
Externí odkaz:
http://arxiv.org/abs/2410.14137
Autor:
Subramanian, Shashank, Rrapaj, Ermal, Harrington, Peter, Chheda, Smeet, Farrell, Steven, Austin, Brian, Williams, Samuel, Wright, Nicholas, Bhimji, Wahid
Generative AI, in particular large transformer models, are increasingly driving HPC system design in science and industry. We analyze performance characteristics of such transformer models and discuss their sensitivity to the transformer type, parall
Externí odkaz:
http://arxiv.org/abs/2410.00273
Autor:
Pathak, Jaideep, Cohen, Yair, Garg, Piyush, Harrington, Peter, Brenowitz, Noah, Durran, Dale, Mardani, Morteza, Vahdat, Arash, Xu, Shaoming, Kashinath, Karthik, Pritchard, Michael
Storm-scale convection-allowing models (CAMs) are an important tool for predicting the evolution of thunderstorms and mesoscale convective systems that result in damaging extreme weather. By explicitly resolving convective dynamics within the atmosph
Externí odkaz:
http://arxiv.org/abs/2408.10958
Huge Ensembles Part I: Design of Ensemble Weather Forecasts using Spherical Fourier Neural Operators
Autor:
Mahesh, Ankur, Collins, William, Bonev, Boris, Brenowitz, Noah, Cohen, Yair, Elms, Joshua, Harrington, Peter, Kashinath, Karthik, Kurth, Thorsten, North, Joshua, OBrien, Travis, Pritchard, Michael, Pruitt, David, Risser, Mark, Subramanian, Shashank, Willard, Jared
Studying low-likelihood high-impact extreme weather events in a warming world is a significant and challenging task for current ensemble forecasting systems. While these systems presently use up to 100 members, larger ensembles could enrich the sampl
Externí odkaz:
http://arxiv.org/abs/2408.03100
Autor:
Mahesh, Ankur, Collins, William, Bonev, Boris, Brenowitz, Noah, Cohen, Yair, Harrington, Peter, Kashinath, Karthik, Kurth, Thorsten, North, Joshua, OBrien, Travis, Pritchard, Michael, Pruitt, David, Risser, Mark, Subramanian, Shashank, Willard, Jared
In Part I, we created an ensemble based on Spherical Fourier Neural Operators. As initial condition perturbations, we used bred vectors, and as model perturbations, we used multiple checkpoints trained independently from scratch. Based on diagnostics
Externí odkaz:
http://arxiv.org/abs/2408.01581
Autor:
Willard, Jared D., Harrington, Peter, Subramanian, Shashank, Mahesh, Ankur, O'Brien, Travis A., Collins, William D.
Publikováno v:
23rd Conference on Artificial Intelligence for Environmental Science. Jan 2024. Abstract #437874
The rapid rise of deep learning (DL) in numerical weather prediction (NWP) has led to a proliferation of models which forecast atmospheric variables with comparable or superior skill than traditional physics-based NWP. However, among these leading DL
Externí odkaz:
http://arxiv.org/abs/2404.19630
Autor:
Brenowitz, Noah D., Cohen, Yair, Pathak, Jaideep, Mahesh, Ankur, Bonev, Boris, Kurth, Thorsten, Durran, Dale R., Harrington, Peter, Pritchard, Michael S.
Since the weather is chaotic, forecasts aim to predict the distribution of future states rather than make a single prediction. Recently, multiple data driven weather models have emerged claiming breakthroughs in skill. However, these have mostly been
Externí odkaz:
http://arxiv.org/abs/2401.15305
Hydrodynamical cosmological simulations are a powerful tool for accurately predicting the properties of the intergalactic medium (IGM) and for producing mock skies that can be compared against observational data. However, the need to resolve density
Externí odkaz:
http://arxiv.org/abs/2308.02637
Publikováno v:
Transactions on Machine Learning Research. November 2023
Neural operators have proven to be a promising approach for modeling spatiotemporal systems in the physical sciences. However, training these models for large systems can be quite challenging as they incur significant computational and memory expense
Externí odkaz:
http://arxiv.org/abs/2306.10619
Autor:
Subramanian, Shashank, Harrington, Peter, Keutzer, Kurt, Bhimji, Wahid, Morozov, Dmitriy, Mahoney, Michael, Gholami, Amir
Publikováno v:
NeurIPS 2023
Pre-trained machine learning (ML) models have shown great performance for a wide range of applications, in particular in natural language processing (NLP) and computer vision (CV). Here, we study how pre-training could be used for scientific machine
Externí odkaz:
http://arxiv.org/abs/2306.00258