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, regions, and time periods, to generate 2 m 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.

This article examines the origins of national electrification in Chile, situating its technocratic promoters within a broad trend – unfolding across Latin America – toward the ‘rational’ management and conservation of natural resources by the state. It surveys the early history of Chilean electrification (1890s–1940s) to show how conservationist thinking flowed through discussions and debates among engineers about the proper uses of the country's waters. These ideas eventually shaped the 1943 national electrification plan, which focused on hydropower. The article sheds new light on the history of Chile's technocracy, the relationship between perceptions of the environment and development planning, and the political and economic debates over national electrification. It also shows how the conservationist dilemma of using versus preserving natural resources operated within a utilitarian and highly technical framework for thinking about nature's bounty. The article thus contributes to recent historical scholarship on conservation and environmental technocrats in Latin America.