Keyhan Gavahi

Drought, a potent natural climatic phenomenon, significantly challenges hydropower systems, bearing adverse consequences for economies, societies, and the environment. This study delves into the profound impact of drought on hydropower generation (HG) in the United States, revealing a robust correlation between hydrologic drought and hydroelectricity generation. Our analysis of the period from 2003 to 2020 for the Contiguous United States (CONUS) indicates that drought events led to a considerable decline in hydroelectricity generation, amounting to approximately 300 million MWh, and resulting in an estimated loss of $28 billion to the sector. Moreover, our findings highlight the adverse environmental effect of drought-induced HG reductions, which are often compensated by increased reliance on natural gas usage, which led to substantial emissions of carbon dioxide (CO₂), sulfur dioxide (SO₂), and nitrogen oxide (NO _X ), totaling 161 700 kilotons, 1199 tons, and 181 977 tons, respectively. In addition to these findings, we assess the state-level vulnerability of hydropower to drought, identifying Washington and California as the most vulnerable states, while Nevada exhibits the least vulnerability. Overall, this study enhances understanding of the multifaceted effects of drought on hydropower, which can assist in informing policies and practices related to drought management and energy production.

Droughts are among the most devastating natural hazards, occurring in all regions with different climate conditions. The impacts of droughts result in significant damages annually around the world. While drought is generally described as a slow‐developing hazardous event, a rapidly developing type of drought, the so‐called flash drought has been revealed by recent studies. The rapid onset and strong intensity of flash droughts require accurate real‐time monitoring. Addressing this issue, a Generative Adversarial Network (GAN) is developed in this study to monitor flash droughts over the Contiguous United States (CONUS). GAN contains two models: (a) discriminator and (b) generator. The developed architecture in this study employs a Markovian discriminator, which emphasizes the spatial dependencies, with a modified U‐Net generator, tuned for optimal performance. To determine the best loss function for the generator, four different networks are developed with different loss functions, including Mean Absolute Error (MAE), adversarial loss, a combination of adversarial loss with Mean Square Error (MSE), and a combination of adversarial loss with MAE. Utilizing daily datasets collected from NLDAS‐2 and Standardized Soil Moisture Index (SSI) maps, the network is trained for real‐time daily SSI monitoring. Comparative assessments reveal the proposed GAN's superior ability to replicate SSI values over U‐Net and Naïve models. Evaluation metrics further underscore that the developed GAN successfully identifies both fine‐ and coarse‐scale spatial drought patterns and abrupt changes in the SSI temporal patterns that is important for flash drought identification.