TemperatureGAN: Generative Modeling of Regional Atmospheric Temperatures
This work addresses the need for accurate and reliable stochastic generators for climate impact projections in sectors like energy systems, though it appears incremental as it applies an existing GAN framework to a new domain-specific dataset.
The authors tackled the problem of generating realistic regional atmospheric temperature data for climate risk assessment by introducing TemperatureGAN, a conditional Generative Adversarial Network, which produced high-fidelity examples with good spatial and temporal accuracy.
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.