A hybrid Kolmogorov–Arnold Networks-based model with attention for predicting Arctic river streamflow.
Saved in:
| Title: | A hybrid Kolmogorov–Arnold Networks-based model with attention for predicting Arctic river streamflow. |
|---|---|
| Authors: | Zhou, Renjie1 (AUTHOR) renjie.zhou@shsu.edu, Liu, Shiqi2 (AUTHOR) |
| Source: | Hydrology & Earth System Sciences. 2026, Vol. 30 Issue 10, p3165-3183. 19p. |
| Subject Terms: | *Streamflow, *Deep learning, *Hydrologic models, *Watersheds, *Encoding, *Tundras |
| Geographic Terms: | Arctic regions |
| Abstract: | Arctic rivers represent important components of the Arctic and global hydrological and climate systems, serving as dynamic conduits between terrestrial and marine environments in some rapidly changing regions. They transport freshwater, sediments, nutrients, and carbon from vast watersheds to the Arctic Ocean and affect ocean circulation patterns and regional climate dynamics. Despite their importance, modeling Arctic rivers remains challenging because of sparse data networks, unique cryospheric dynamics, and complex responses to hydrometeorological variables. In this study, a novel hybrid deep learning model is developed to address these challenges and predict Arctic river discharge by incorporating Kolmogorov–Arnold Networks (KAN), Long Short-Term Memory, and the attention mechanism with seasonal trigonometry encoding and physics-based constraints. It integrates several novel components: (1) A KAN-based deep learning component learns and captures intricate temporal patterns from nonlinear hydrometeorological data; (2) Explicit physical constraints designed for the characteristics of permafrost-dominated watersheds govern snow accumulation and melt processes through the architectural design and loss function; (3) Seasonal variations are accounted for using trigonometry functions to represent cyclical patterns; (4) A residual compensation structure allows the proposed model to revisit systematic errors in initial predictions and helps capture complex nonlinear processes that are not fully represented. The Kolyma River, which is dominated by permafrost, is adopted to test the performance of the newly developed model. It obtains more robust and accurate predictive performance compared to baseline models. The role of physical constraints, the residual compensated architecture, and the trigonometry encoding are assessed by ablation analysis. The results indicate that these components improve the predictive performance. This novel approach offers a new pathway for addressing key challenges of hydrological forecasting in cold, permafrost-dominated regions and provides a robust framework for improving Arctic river discharge prediction. [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: enr DbLabel: Energy & Power Source An: 194401726 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A hybrid Kolmogorov–Arnold Networks-based model with attention for predicting Arctic river streamflow. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Zhou%2C+Renjie%22">Zhou, Renjie</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> renjie.zhou@shsu.edu</i><br /><searchLink fieldCode="AR" term="%22Liu%2C+Shiqi%22">Liu, Shiqi</searchLink><relatesTo>2</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Hydrology+%26+Earth+System+Sciences%22">Hydrology & Earth System Sciences</searchLink>. 2026, Vol. 30 Issue 10, p3165-3183. 19p. – Name: Subject Label: Subject Terms Group: Su Data: *<searchLink fieldCode="DE" term="%22Streamflow%22">Streamflow</searchLink><br />*<searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Hydrologic+models%22">Hydrologic models</searchLink><br />*<searchLink fieldCode="DE" term="%22Watersheds%22">Watersheds</searchLink><br />*<searchLink fieldCode="DE" term="%22Encoding%22">Encoding</searchLink><br />*<searchLink fieldCode="DE" term="%22Tundras%22">Tundras</searchLink> – Name: SubjectGeographic Label: Geographic Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Arctic+regions%22">Arctic regions</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Arctic rivers represent important components of the Arctic and global hydrological and climate systems, serving as dynamic conduits between terrestrial and marine environments in some rapidly changing regions. They transport freshwater, sediments, nutrients, and carbon from vast watersheds to the Arctic Ocean and affect ocean circulation patterns and regional climate dynamics. Despite their importance, modeling Arctic rivers remains challenging because of sparse data networks, unique cryospheric dynamics, and complex responses to hydrometeorological variables. In this study, a novel hybrid deep learning model is developed to address these challenges and predict Arctic river discharge by incorporating Kolmogorov–Arnold Networks (KAN), Long Short-Term Memory, and the attention mechanism with seasonal trigonometry encoding and physics-based constraints. It integrates several novel components: (1) A KAN-based deep learning component learns and captures intricate temporal patterns from nonlinear hydrometeorological data; (2) Explicit physical constraints designed for the characteristics of permafrost-dominated watersheds govern snow accumulation and melt processes through the architectural design and loss function; (3) Seasonal variations are accounted for using trigonometry functions to represent cyclical patterns; (4) A residual compensation structure allows the proposed model to revisit systematic errors in initial predictions and helps capture complex nonlinear processes that are not fully represented. The Kolyma River, which is dominated by permafrost, is adopted to test the performance of the newly developed model. It obtains more robust and accurate predictive performance compared to baseline models. The role of physical constraints, the residual compensated architecture, and the trigonometry encoding are assessed by ablation analysis. The results indicate that these components improve the predictive performance. This novel approach offers a new pathway for addressing key challenges of hydrological forecasting in cold, permafrost-dominated regions and provides a robust framework for improving Arctic river discharge prediction. [ABSTRACT FROM AUTHOR] |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=194401726 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.5194/hess-30-3165-2026 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 19 StartPage: 3165 Subjects: – SubjectFull: Streamflow Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Hydrologic models Type: general – SubjectFull: Watersheds Type: general – SubjectFull: Encoding Type: general – SubjectFull: Tundras Type: general – SubjectFull: Arctic regions Type: general Titles: – TitleFull: A hybrid Kolmogorov–Arnold Networks-based model with attention for predicting Arctic river streamflow. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Zhou, Renjie – PersonEntity: Name: NameFull: Liu, Shiqi IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 05 Text: 2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 10275606 Numbering: – Type: volume Value: 30 – Type: issue Value: 10 Titles: – TitleFull: Hydrology & Earth System Sciences Type: main |
| ResultId | 1 |
