LSTM-Based River Discharge Forecasting Using Spatially Gridded Input Data

Kamilla Rakhymbek, Balgaisha Mukanova (), Andrey Bondarovich, Dmitry Chernykh, Almas Alzhanov (), Dauren Nurekenov, Anatoliy Pavlenko and Aliya Nugumanova ()
Additional contact information
Kamilla Rakhymbek: Laboratory of Digital Technologies and Modeling, Sarsen Amanzholov East Kazakhstan University, Ust-Kamenogorsk 070000, Kazakhstan
Balgaisha Mukanova: Big Data and Blockchain Technologies Research Innovation Center, Astana IT University, Astana 010000, Kazakhstan
Andrey Bondarovich: Laboratory of Digital Technologies and Modeling, Sarsen Amanzholov East Kazakhstan University, Ust-Kamenogorsk 070000, Kazakhstan
Dmitry Chernykh: Laboratory of Digital Technologies and Modeling, Sarsen Amanzholov East Kazakhstan University, Ust-Kamenogorsk 070000, Kazakhstan
Almas Alzhanov: Big Data and Blockchain Technologies Research Innovation Center, Astana IT University, Astana 010000, Kazakhstan
Dauren Nurekenov: Laboratory of Digital Technologies and Modeling, Sarsen Amanzholov East Kazakhstan University, Ust-Kamenogorsk 070000, Kazakhstan
Anatoliy Pavlenko: Laboratory of Digital Technologies and Modeling, Sarsen Amanzholov East Kazakhstan University, Ust-Kamenogorsk 070000, Kazakhstan
Aliya Nugumanova: Big Data and Blockchain Technologies Research Innovation Center, Astana IT University, Astana 010000, Kazakhstan

Data, 2025, vol. 10, issue 8, 1-27

Abstract: Accurate river discharge forecasting remains a critical challenge in hydrology, particularly in data-scarce mountainous regions where in situ observations are limited. This study investigated the potential of long short-term memory (LSTM) networks to improve discharge prediction by leveraging spatially distributed reanalysis data. Using the ERA5-Land dataset, we developed an LSTM model that integrates grid-based meteorological inputs and assesses their relative importance. We conducted experiments on two snow-dominated basins with contrasting physiographic characteristics, the Uba River basin in Kazakhstan and the Flathead River basin in the USA, to answer three research questions: (1) whether full-grid input outperforms reduced configurations and models trained on Caravan, (2) the impact of spatial resolution on accuracy and efficiency, and (3) the effect of partial spatial coverage on prediction reliability. Specifically, we compared the full-grid LSTM with a single-cell LSTM, a basin-average LSTM, a Caravan-trained LSTM, and coarser cell aggregations. The results demonstrate that the full-grid LSTM consistently yields the highest forecasting performance, achieving a median Nash–Sutcliffe efficiency of 0.905 for Uba and 0.93 for Middle Fork Flathead, while using coarser grids and random subsets reduces performance. Our findings highlight the critical importance of spatial input richness and provide a reproducible framework for grid selection in flood-prone basins lacking dense observation networks.

Keywords: LSTM; river discharge; grid; ERA5-Land; Uba River basin; Middle Fork Flathead basin; Caravan; Nash–Sutcliffe efficiency (search for similar items in EconPapers)
JEL-codes: C8 C80 C81 C82 C83 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2306-5729/10/8/122/pdf (application/pdf)
https://www.mdpi.com/2306-5729/10/8/122/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jdataj:v:10:y:2025:i:8:p:122-:d:1711284

Access Statistics for this article

Data is currently edited by Ms. Cecilia Yang

More articles in Data from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().