Scalable Climate Data Analysis: Balancing Petascale Fidelity and Computational Cost

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Panta, Aashish, Gooch, Amy, Scorzelli, Giorgio, Taufer, Michela, Pascucci, Valerio
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915400237711360
author Panta, Aashish
Gooch, Amy
Scorzelli, Giorgio
Taufer, Michela
Pascucci, Valerio
author_facet Panta, Aashish
Gooch, Amy
Scorzelli, Giorgio
Taufer, Michela
Pascucci, Valerio
contents The growing resolution and volume of climate data from remote sensing and simulations pose significant storage, processing, and computational challenges. Traditional compression or subsampling methods often compromise data fidelity, limiting scientific insights. We introduce a scalable ecosystem that integrates hierarchical multiresolution data management, intelligent transmission, and ML-assisted reconstruction to balance accuracy and efficiency. Our approach reduces storage and computational costs by 99\%, lowering expenses from \$100,000 to \$24 while maintaining a Root Mean Square (RMS) error of 1.46 degrees Celsius. Our experimental results confirm that even with significant data reduction, essential features required for accurate climate analysis are preserved. Validated on petascale NASA climate datasets, this solution enables cost-effective, high-fidelity climate analysis for research and decision-making.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08006
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scalable Climate Data Analysis: Balancing Petascale Fidelity and Computational Cost
Panta, Aashish
Gooch, Amy
Scorzelli, Giorgio
Taufer, Michela
Pascucci, Valerio
Atmospheric and Oceanic Physics
Human-Computer Interaction
The growing resolution and volume of climate data from remote sensing and simulations pose significant storage, processing, and computational challenges. Traditional compression or subsampling methods often compromise data fidelity, limiting scientific insights. We introduce a scalable ecosystem that integrates hierarchical multiresolution data management, intelligent transmission, and ML-assisted reconstruction to balance accuracy and efficiency. Our approach reduces storage and computational costs by 99\%, lowering expenses from \$100,000 to \$24 while maintaining a Root Mean Square (RMS) error of 1.46 degrees Celsius. Our experimental results confirm that even with significant data reduction, essential features required for accurate climate analysis are preserved. Validated on petascale NASA climate datasets, this solution enables cost-effective, high-fidelity climate analysis for research and decision-making.
title Scalable Climate Data Analysis: Balancing Petascale Fidelity and Computational Cost
topic Atmospheric and Oceanic Physics
Human-Computer Interaction
url https://arxiv.org/abs/2507.08006