Modeling Annual Total Organic Nitrogen Concentrations in Streams Using Machine Learning at National Scale

Abstract Understanding and quantifying total organic nitrogen (TON) concentrations in streams and their spatial variation is essential for accurately assessing their importance for total nitrogen (TN) loadings to coastal waters and the possible sources of TON in the landscape. Total organic nitrogen...

Full description

Saved in:
Bibliographic Details
Main Authors: Rasmus R. Frederiksen, Søren E. Larsen, Henrik Tornbjerg, Hans Thodsen, Brian Kronvang
Format: Article
Language:English
Published: Wiley 2025-06-01
Series:Water Resources Research
Subjects:
Online Access:https://doi.org/10.1029/2024WR039451
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850082823666401280
author Rasmus R. Frederiksen
Søren E. Larsen
Henrik Tornbjerg
Hans Thodsen
Brian Kronvang
author_facet Rasmus R. Frederiksen
Søren E. Larsen
Henrik Tornbjerg
Hans Thodsen
Brian Kronvang
author_sort Rasmus R. Frederiksen
collection DOAJ
description Abstract Understanding and quantifying total organic nitrogen (TON) concentrations in streams and their spatial variation is essential for accurately assessing their importance for total nitrogen (TN) loadings to coastal waters and the possible sources of TON in the landscape. Total organic nitrogen constitutes almost 20% of the TN riverine loadings to Danish coastal waters. We used environmental monitoring data from 390 stations across Denmark to calculate indirectly measured annual average TON concentrations using a wide range of predictor variables. We then trained a machine learning model to predict spatially distributed average annual TON concentrations in Danish streams, achieving a mean error of 0 mg L−1 and a root‐mean‐squared error of 0.20 mg L−1. The mean annual predicted (measured) TON concentrations in Danish streams were 0.84 (0.70) mg L−1, with a standard deviation of 0.36 (0.31) mg L−1. The model is primarily driven by mean elevation and the percentages of agricultural land, tile‐drained areas, lakes and carbon‐enriched soils in the catchment. The developed model contributes to our understanding of the spatial variation in annual TON concentrations in streams at a national scale, supporting our understanding of processes driving nitrogen cycling.
format Article
id doaj-art-3a46326acb504d9ca39a1792c4bd9bee
institution DOAJ
issn 0043-1397
1944-7973
language English
publishDate 2025-06-01
publisher Wiley
record_format Article
series Water Resources Research
spelling doaj-art-3a46326acb504d9ca39a1792c4bd9bee2025-08-20T02:44:24ZengWileyWater Resources Research0043-13971944-79732025-06-01616n/an/a10.1029/2024WR039451Modeling Annual Total Organic Nitrogen Concentrations in Streams Using Machine Learning at National ScaleRasmus R. Frederiksen0Søren E. Larsen1Henrik Tornbjerg2Hans Thodsen3Brian Kronvang4Department of Ecoscience Aarhus University Aarhus DenmarkDepartment of Ecoscience Aarhus University Aarhus DenmarkDepartment of Ecoscience Aarhus University Aarhus DenmarkDepartment of Ecoscience Aarhus University Aarhus DenmarkDepartment of Ecoscience Aarhus University Aarhus DenmarkAbstract Understanding and quantifying total organic nitrogen (TON) concentrations in streams and their spatial variation is essential for accurately assessing their importance for total nitrogen (TN) loadings to coastal waters and the possible sources of TON in the landscape. Total organic nitrogen constitutes almost 20% of the TN riverine loadings to Danish coastal waters. We used environmental monitoring data from 390 stations across Denmark to calculate indirectly measured annual average TON concentrations using a wide range of predictor variables. We then trained a machine learning model to predict spatially distributed average annual TON concentrations in Danish streams, achieving a mean error of 0 mg L−1 and a root‐mean‐squared error of 0.20 mg L−1. The mean annual predicted (measured) TON concentrations in Danish streams were 0.84 (0.70) mg L−1, with a standard deviation of 0.36 (0.31) mg L−1. The model is primarily driven by mean elevation and the percentages of agricultural land, tile‐drained areas, lakes and carbon‐enriched soils in the catchment. The developed model contributes to our understanding of the spatial variation in annual TON concentrations in streams at a national scale, supporting our understanding of processes driving nitrogen cycling.https://doi.org/10.1029/2024WR039451machine learningorganic nitrogenTONSHAPstream water qualityxgboost
spellingShingle Rasmus R. Frederiksen
Søren E. Larsen
Henrik Tornbjerg
Hans Thodsen
Brian Kronvang
Modeling Annual Total Organic Nitrogen Concentrations in Streams Using Machine Learning at National Scale
Water Resources Research
machine learning
organic nitrogen
TON
SHAP
stream water quality
xgboost
title Modeling Annual Total Organic Nitrogen Concentrations in Streams Using Machine Learning at National Scale
title_full Modeling Annual Total Organic Nitrogen Concentrations in Streams Using Machine Learning at National Scale
title_fullStr Modeling Annual Total Organic Nitrogen Concentrations in Streams Using Machine Learning at National Scale
title_full_unstemmed Modeling Annual Total Organic Nitrogen Concentrations in Streams Using Machine Learning at National Scale
title_short Modeling Annual Total Organic Nitrogen Concentrations in Streams Using Machine Learning at National Scale
title_sort modeling annual total organic nitrogen concentrations in streams using machine learning at national scale
topic machine learning
organic nitrogen
TON
SHAP
stream water quality
xgboost
url https://doi.org/10.1029/2024WR039451
work_keys_str_mv AT rasmusrfrederiksen modelingannualtotalorganicnitrogenconcentrationsinstreamsusingmachinelearningatnationalscale
AT sørenelarsen modelingannualtotalorganicnitrogenconcentrationsinstreamsusingmachinelearningatnationalscale
AT henriktornbjerg modelingannualtotalorganicnitrogenconcentrationsinstreamsusingmachinelearningatnationalscale
AT hansthodsen modelingannualtotalorganicnitrogenconcentrationsinstreamsusingmachinelearningatnationalscale
AT briankronvang modelingannualtotalorganicnitrogenconcentrationsinstreamsusingmachinelearningatnationalscale