Dmitriy Abramov

Mr. Dmitriy Abramov

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 January 2021 in Hydrology
Verified
Journal Article
Open access
PDF file
GAGeorgy Ayzel
Georgy Ayzel
LKLiubov Kurochkina
Liubov Kurochkina
DADmitriy Abramov
Dmitriy Abramov
SZSergei Zhuravlev
Sergei Zhuravlev
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.

29 October 2024
Verified
Conference Paper
Open access
DKDanil Kononykhin
Danil Kononykhin
MMMikhail Mozikov
Mikhail Mozikov
KMKirill Mishtal
Kirill Mishtal
PKPavel Kuznetsov
Pavel Kuznetsov
DADmitriy Abramov
Dmitriy Abramov
IMIlya Makarov
Ilya Makarov
As machine learning increasingly becomes a crucial tool for geospatial data analysis, finding and deploying a suitable model presents significant challenges, including the need for expertise in both programming and geospatial analysis, organizing data flow, and accurately assessing the results. To address these challenges, this paper introduces GlobeFlowGPT, a multimodal, chat-based framework designed to meet these demands by integrating domain-specific tools, machine learning models, Multimodal Large Language Models, and essential operational data. It leverages a Large Language Model orchestrator, facilitating complex geospatial tasks through a conversational interface. GlobeFlowGPT's flexible, containerized architecture allows for the rapid integration of cutting-edge models tailored for geospatial data, ensuring that the framework remains scalable and relevant amid ongoing technological advancements. We demonstrate the ability of our framework to streamline the analysis of geospatial data and expand the capabilities of modern MLLMs with complex geospatial machine learning models.

27 October 2025
Verified
Conference Paper
Open access
MMMikhail Mozikov
Mikhail Mozikov
DODaniil Orekhov
Daniil Orekhov
INIvan Nasonov
Ivan Nasonov
KBKonstantin Baltsat
Konstantin Baltsat
VPVladislav Pedashenko
Vladislav Pedashenko
IMIlya Makarov
Ilya Makarov

1 February 2022 in Geosciences
Verified
Journal Article
Open access
PDF file
GAGeorgy Ayzel
Georgy Ayzel
DADmitriy Abramov
Dmitriy Abramov
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.

27 March 2022
Verified
Conference Paper
Open access
DADmitriy Abramov
Dmitriy Abramov
GAGeorgy Ayzel
Georgy Ayzel
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.