TemperatureGAN: Generative Modeling of Regional Atmospheric Temperatures
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912077107429376 |
|---|---|
| author | Balogun, Emmanuel Rajagopal, Ram Majumdar, Arun |
| author_facet | Balogun, Emmanuel Rajagopal, Ram Majumdar, Arun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_17248 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | TemperatureGAN: Generative Modeling of Regional Atmospheric Temperatures Balogun, Emmanuel Rajagopal, Ram Majumdar, Arun Machine Learning Atmospheric and Oceanic Physics 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. |
| title | TemperatureGAN: Generative Modeling of Regional Atmospheric Temperatures |
| topic | Machine Learning Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2306.17248 |