Data augmentation with generative adversarial networks (GANs) has been popular for class imbalance problems, mainly for pattern classification and computer vision-related applications. Extreme value forecasting is a challenging field that has various applications from finance to climate change problems. In this study, we present a data augmentation framework for extreme value forecasting. In this framework, our focus is on forecasting extreme values using deep learning models in combination with data augmentation models such as GANs and synthetic minority oversampling technique (SMOTE). We use deep learning models such as convolutional long short-term memory (Conv-LSTM) and bidirectional long short-term memory (BD-LSTM) networks for multistep ahead prediction featuring extremes. We investigate which data augmentation models are the most suitable, taking into account the prediction accuracy overall and at extreme regions, along with computational efficiency. We also present novel strategies for incorporating data augmentation, considering extreme values based on a relevance function. Our results indicate that the SMOTE-based strategy consistently demonstrated superior adaptability, leading to improved performance across both short- and long-horizon forecasts. Conv-LSTM and BD-LSTM exhibit complementary strengths: the former excels in periodic, stable datasets, while the latter performs better in chaotic or non-stationary sequences.

A huge fire tore through an online retailer's warehouse in St. Petersburg Saturday with video showing intense flames and thick black smoke rising into the sky (CREDIT: Reuters). Seen from up here, in the cockpit of a French air force surveillance plane flying over neighboring Romania, the snow-dusted landscapes look deceptively peaceful. The dead from Russia's war, the shattered Ukrainian towns and mangled battlefields, aren't visible to the naked eye through the clouds. But French military technicians riding farther back in the aircraft, monitoring screens that display the word "secret" when idle, have a far more penetrating view. With a powerful radar that rotates six times every minute on the fuselage and a bellyful of surveillance gear, the plane can spot missile launches, airborne bombing runs and other military activity in the conflict.

Prediction of dynamic environmental variables in unmonitored sites remains a long-standing challenge for water resources science. The majority of the world's freshwater resources have inadequate monitoring of critical environmental variables needed for management. Yet, the need to have widespread predictions of hydrological variables such as river flow and water quality has become increasingly urgent due to climate and land use change over the past decades, and their associated impacts on water resources. Modern machine learning methods increasingly outperform their process-based and empirical model counterparts for hydrologic time series prediction with their ability to extract information from large, diverse data sets. We review relevant state-of-the art applications of machine learning for streamflow, water quality, and other water resources prediction and discuss opportunities to improve the use of machine learning with emerging methods for incorporating watershed characteristics into deep learning models, transfer learning, and incorporating process knowledge into machine learning models. The analysis here suggests most prior efforts have been focused on deep learning learning frameworks built on many sites for predictions at daily time scales in the United States, but that comparisons between different classes of machine learning methods are few and inadequate. We identify several open questions for time series predictions in unmonitored sites that include incorporating dynamic inputs and site characteristics, mechanistic understanding and spatial context, and explainable AI techniques in modern machine learning frameworks.

Fox News correspondent Chad Pergram has the latest on the Biden admin's response to the Russia-Ukraine conflict on'Special Report.' Fighting continues over Ukraine's Zmiinyi Island, also known as Snake Island, as Russia looks to reinforce its troops on the small body of land located just off the southwest Ukrainian coastline in the Black Sea, officials warned Wednesday. The island became a symbol of Ukraine's resistance immediately following Russia's invasion in late February after Ukrainian soldiers famously stood up to a Russian warship. The United Kingdom's defense ministry warned that Russia is "repeatedly trying to reinforce its exposed garrison" located on the island. Snake Island, though tiny, has proven strategically important in Ukraine's war against Russia as it is located roughly 30 miles from Ukraine's most southern region.