TemperatureGAN: Generative Modeling of Regional Atmospheric Temperatures

Emmanuel Balogun, Ram Rajagopal, Arun Majumdar
6/29/2023
cs.LGphysics.ao-phstat.ML

Official code: ebalogun01/TemperatureGAN (5 stars, MIT, last commit 2025-01-23).

Abstract

Stochastic generators are useful for estimating climate impacts on various sectors. Projecting climate risk in various sectors, e.g. energy systems, requires generators that are accurate (statistical resemblance to ground-truth), reliable (do not produce erroneous examples), and efficient. Leveraging data from the North American Land Data Assimilation System, we introduce TemperatureGAN, a Generative Adversarial Network conditioned on months, locations, and time periods, to generate 2m above ground atmospheric temperatures at an hourly resolution. We propose evaluation methods and metrics to measure the quality of generated samples. We show that TemperatureGAN produces high-fidelity examples with good spatial representation and temporal dynamics consistent with known diurnal cycles.

View on arXivView PDF

Code Implementations(1)

ebalogun01/TemperatureGANOfficial
MIT

Generative Modelling of Regional Atmospheric Temperatures

51PythonJun 8, 20241 years agoMIT

Similar Papers

Uncertainty-Aware Hourly Air Temperature Mapping at 2 km Resolution via Physics-Guided Deep Learning

83% match2025

WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion

82% match1 repo302025

Generative Adversarial Models for Extreme Geospatial Downscaling

82% match1 repo42024

Precipitation Nowcasting Using Physics Informed Discriminator Generative Models

81% match2024

Advancing Heatwave Forecasting via Distribution Informed-Graph Neural Networks (DI-GNNs): Integrating Extreme Value Theory with GNNs

81% match2024

Diffusion-Based Joint Temperature and Precipitation Emulation of Earth System Models

81% match2024

Cite this paper

@article{balogun2023temperaturegan,
  title  = {TemperatureGAN: Generative Modeling of Regional Atmospheric Temperatures},
  author = {Emmanuel Balogun and Ram Rajagopal and Arun Majumdar},
  year   = {2023},
  eprint = {2306.17248},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.17248v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.17248.svg)](https://codeofpaper.com/paper/2306.17248)

Discussion