Gridded datasets provide spatially and temporally consistent runoff estimates that serve as reliable sources for assessing water resources from regional to global scales. This study presents LSTM-REG, a regional gridded runoff dataset for northwest Russia based on Long Short-Term Memory (LSTM) networks. LSTM-REG covers the period from 1980 to 2016 at a 0.5° spatial and daily temporal resolution. LSTM-REG has been extensively validated and benchmarked against GR4J-REG, a gridded runoff dataset based on a parsimonious regionalization scheme and the GR4J hydrological model. While both datasets provide runoff estimates with reliable prediction efficiency, LSTM-REG outperforms GR4J-REG for most basins in the independent evaluation set. Thus, the results demonstrate a higher generalization capacity of LSTM-REG than GR4J-REG, which can be attributed to the higher efficiency of the proposed LSTM-based regionalization scheme. The developed datasets are freely available in open repositories to foster further regional hydrology research in northwest Russia.

При проектировании дорожного водоотвода на малых лесных водотоках определяются параметры водопропускных и водоотводных сооружений. Эти параметры зависят от расчетных значений максимальных расходов воды по действующим нормативным документам. При проведении таких расчетов во всех современных методиках в качестве основного условия принимается постоянство всех ландшафтных характеристик в течение расчетного периода эксплуатации проектируемого сооружения. В реальности параметры водосборов, водотоков и, как следствие, лимитирующих расходов воды заметно изменяются за период эксплуатации. Рассмотрены изменения основных морфологических характеристик малых рек – площади водосбора, длины водотока, густоты речной сети, залесенности, заболоченности и уклона. Ландшафтные параметры рассмотрены на примере ручьев и малых рек, протекающих по территории открытой в 2014 г. ведомственной лесной водно-балансовой станции «Междуречье». Территория станции находится в приводораздельной части междуречья р. Волги, Днепра и Западной Двины на границе Тверской и Смоленской областей в зоне смешанных лесов Европейской территории России. Для оценок использованы данные по картам 1938 г., 1952–1985 гг. и данные водно-балансовой станции «Междуречье» за 2016 г. Отмечено, что площади водосборов определяются по картам разных лет практически однозначно, в то же время резко увеличились длины водотоков, но их изменение не приводит к заметному уменьшению расчетных значений максимальных расходов воды. Относительные лесистость и заболоченность водосборов заметно возросли, что приводит иногда к значительному уменьшению расчетных коэффициентов, учитывающих влияние лесистости и заболоченности. В большинстве случаев уменьшились уклоны водотоков, что привело к падению расчетных максимальных расходов воды и заболоченности территории. Такие изменения максимальных расходов воды на основании существующих расчетных методик не могли быть предусмотрены заранее, при анализе данных картографических материалов прошлых лет. We define the parameters of culverts and drainage constructions when design road drainage in small forest streams. These parameters depend on the calculated values of maximum water flow. In the calculations of all modern methods as a basic condition is assumed permanence of landscape characteristics. In fact, the parameters of basins and streams are changed during the operation period. This article reviews the main changes of the morphological characteristics of small rivers: catchment area, length of the watercourse, the river network density, forest coverage, wetlands and biases of water surface. Landscape parameters considered by the example of streams and small rivers located on the territory of the forest water-balance station «MEZHDURECHYE». Station area is located between the rivers Volga, Dnieper and the Western Dvina. Data on the maps in 1938, 1952–1985 are used for assessments. Length streams increased during these years. Woodland and wetland basins have grown. Тhis leads to a significant reduction in the results of calculations. In most cases decreased biases of streams. This led to a drop in the calculated maximum water flow. These changes could not be provided in advance.

OpenForecast is the first openly available national-scale operational runoff forecasting system in Russia. Launched in March 2020, it routinely provides 7-day ahead predictions for 834 gauges across the country. Here, we provide an assessment of the OpenForecast performance on the long-term evaluation period from 14 March 2020 to 31 October 2021 (597 days) for 252 gauges for which operational data are available and quality-controlled. Results show that OpenForecast is a robust system based on reliable data and solid computational routines that secures efficient runoff forecasts for a diverse set of gauges.

<p>Would the river near my street stay in banks after the forecasted torrential rain? Will the spring flood fill the drinking water reservoirs of big cities? What should we expect from the changing climate? Hydrological modelling studies aim to solve these and other challenging questions providing solutions and guidelines for early warning and hazard risk mitigation. While traditional physically-based hydrological models proved as robust and reliable tools for streamflow prediction for decades, the emerging field of machine learning continues to deliver state-of-the-art modelling solutions in recent years. The power of these data-driven models is built on an explanatory power of underlying data – meteorological forcing and physiographic catchment attributes. While meteorological forcing is globally available and provided by global meteorological reanalysis datasets, catchment attributes datasets are usually region-specific and lacks consistency between different regions. Consequently, that limits the development of global machine learning models for streamflow prediction. Therefore, here we propose a framework for developing a global dataset of hydro-meteorological and landscape attributes that could be utilized for global, large-sample hydrological studies. Our framework is solely based on freely and openly available software and global environmental datasets, making it a reproducible and universal tool that could be further adapted for any region worldwide.</p>