EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Spatiotemporal modeling of annual diffuse flow‐weighted total phosphorus concentrations in Danish headwater streams with machine learning

Brian Kronvang iD, Jørgen Windolf, Henrik Tornbjerg, Rasmus R Frederiksen iD, Søren E Larsen iD

Journal of Environmental Quality · 2026

DOI: 10.1002/jeq2.70141 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Environmental Quality, 2026. Verfasst von Brian Kronvang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ecoscience, Aarhus University, Aarhus, Denmark. Hauptthemen laut MEDLINE: Phosphorus, Rivers, Machine Learning, Environmental Monitoring. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Danish EPA, EU Horizon Project NORDBALT-ECOSAFE.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High total phosphorus (TP) concentrations in freshwater such as streams, rivers, and lakes remain a global issue, causing eutrophication and poor ecological conditions. We extracted annual flow‐weighted TP concentration data ( N = 3144) from 207 monitored Danish headwater streams (catchment area < 50 km 2 ) during the period 1990–2019 as the basis for developing a machine learning (ML) model for diffuse phosphorus in streams, using 22 potential predictor variables. We tested 70 different algorithms, applying an AI platform and a random split strategy with a holdout dataset (20%), a validation dataset (16%), and four training datasets (4 × 16%) in a fivefold cross‐validation procedure across a total of 207 stream stations. The ML algorithm “eXtreme Gradient Boosted trees regressor: XGBoost” was identified as the best‐performing model, based on 13 predictor variables, with a relatively high explanatory power for the training dataset ( R 2 = 0.68), the cross‐validation dataset ( R 2 = 0.71), and the holdout dataset ( R 2 = 0.66). The most important catchment characteristics of the 13 predictor variables were paved area, tile drained area, clay content in subsoil, farmed area, and TP loss from bank erosion. An external test of model transferability on a dataset, using an additional 142 stream stations ( N = 1261), revealed a somewhat lower predictive power of the final model ( R 2 = 0.41). The final model was applied to simulate annual diffuse flow‐weighted TP concentrations for 3200 unique headwater catchments (ca. 15 km 2 ) and this analysis now supports the calculation of annual TP loadings to surface waters from otherwise ungauged coast‐near areas in Denmark.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PhosphorusRiversMachine LearningEnvironmental MonitoringWater Pollutants, ChemicalDenmarkPredictive Learning ModelsBoosting Machine Learning Algorithms

Substanzen

PhosphorusWater Pollutants, Chemical

Autor:innen und Institutionen

  • Department of Ecoscience, Aarhus University, Aarhus, Denmark.

ORCID-Profile: Brian Kronvang, Rasmus R Frederiksen, Søren E Larsen

Förderung

  • Danish EPA
  • EU Horizon Project NORDBALT-ECOSAFE

Zitieren

APA

Kronvang, B., Windolf, J., Tornbjerg, H., Frederiksen, R. R., & Larsen, S. E. (2026). Spatiotemporal modeling of annual diffuse flow‐weighted total phosphorus concentrations in Danish headwater streams with machine learning. Journal of Environmental Quality. https://doi.org/10.1002/jeq2.70141

Vancouver

Kronvang B, Windolf J, Tornbjerg H, Frederiksen RR, Larsen SE. Spatiotemporal modeling of annual diffuse flow‐weighted total phosphorus concentrations in Danish headwater streams with machine learning. Journal of Environmental Quality. 2026. doi:10.1002/jeq2.70141

BibTeX
@article{Kronvang2026,
  author = {Kronvang, Brian and Windolf, Jørgen and Tornbjerg, Henrik and Frederiksen, Rasmus R and Larsen, Søren E},
  title = {Spatiotemporal modeling of annual diffuse flow‐weighted total phosphorus concentrations in Danish headwater streams with machine learning},
  journal = {Journal of Environmental Quality},
  year = {2026},
  doi = {10.1002/jeq2.70141}
}
Kostenlos starten →