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.

翻译：随机生成器对于评估气候对各领域的影响具有重要价值。在能源系统等不同领域进行气候风险预测时，需要生成器具备准确性（与真实数据统计特征相似）、可靠性（不产生错误样本）和高效性。基于北美陆面数据同化系统的数据，我们提出了TemperatureGAN——一种以月份、地理位置和时间段为条件的生成对抗网络，用于生成每小时分辨率、距地面2米处的大气温度。我们提出了评估方法与指标来衡量生成样本的质量。实验表明，TemperatureGAN能够生成高保真度的样本，其空间表征良好，且时间动态变化与已知的昼夜循环规律一致。