EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Data-driven approach to estimate ambient ammonia concentrations

Amitabha Govande, Dick Heederik, Serigne Lô, Gerard Hoek, Kees de Hoogh, Ronald Hoogerbrugge, Albert Bleeker, Marten In 't Veld, Daniel Martins Figueiredo

Environmental Research · 2026-12 · 310 · 126009

DOI: 10.1016/j.envres.2026.126009 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Research, 2026-12. Verfasst von Amitabha Govande und 8 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Risk Assessment Sciences (IRAS), Utrecht University, the Netherlands. Electronic address: a.s.govande@uu.nl. Hauptthemen laut MEDLINE: Ammonia, Environmental Monitoring, Air Pollutants. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Netherlands experiences significant environmental impacts from reactive nitrogen, particularly ammonia (NH3), whose long-term deposition harms soil, water, and biodiversity. NH3 is emitted mainly from agriculture and its levels can be very high and variable in intensive livestock areas. Although monitoring stations are set up across multiple locations, data gaps may still arise due to issues with measurement instruments. Therefore, there is a need for models that can reliably fill in these missing observations. In this study, we first applied Linear Regression, Random Forest, and Gated Recurrent Unit (GRU) models to predict one day ahead NH3 concentrations at six sites (De Zilk, Valthermond, Vredepeel, Wekerom, Wieringerwerf, Zegveld) in the Netherlands. All models captured daily NH3 trends, with Random Forest initially performing best (R2 up to 0.59 at Valthermond). Predictions were strongly driven by lagged NH3 values, with wind speed and relative humidity contributing moderately. After correcting for prediction lag caused by autocorrelation, the linear regression performed best at most sites (with best performance observed at Zegveld with R2 of 0.84) and was used for gap filling. It maintained reasonable accuracy despite sparse observations (every 2-7 days), with most sites (De Zilk, Valthermond, Vredepeel, Wekerom, Zegveld) exhibiting a significant correlation of almost or more than 0.5 even at 7 days measurement gaps. Additionally, we noted that historical data from existing sites could be effectively used to fill gaps at newly established locations that exhibited similar distributions of NH3.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AmmoniaEnvironmental MonitoringAir PollutantsNetherlandsRandom ForestLinear Models

Stichwörter der Autor:innen

AmmoniaDaily predictionsData-driven modelsDeep learningMachine learningMissing values imputation

Substanzen

AmmoniaAir Pollutants

Autor:innen und Institutionen

  • Institute for Risk Assessment Sciences (IRAS), Utrecht University, the Netherlands. Electronic address: a.s.govande@uu.nl.
  • Institute for Risk Assessment Sciences (IRAS), Utrecht University, the Netherlands.
  • National Institute for Public Health and the Environment (RIVM), the Netherlands.

Zitieren

APA

Govande, A., Heederik, D., Lô, S., Hoek, G., de Hoogh, K., Hoogerbrugge, R., Bleeker, A., In 't Veld, M., & Figueiredo, D. M. (2026). Data-driven approach to estimate ambient ammonia concentrations. Environmental Research, 310, 126009. https://doi.org/10.1016/j.envres.2026.126009

Vancouver

Govande A, Heederik D, Lô S, Hoek G, de Hoogh K, Hoogerbrugge R, et al. Data-driven approach to estimate ambient ammonia concentrations. Environmental Research. 2026;310:126009. doi:10.1016/j.envres.2026.126009

BibTeX
@article{Govande2026,
  author = {Govande, Amitabha and Heederik, Dick and Lô, Serigne and Hoek, Gerard and de Hoogh, Kees and Hoogerbrugge, Ronald and Bleeker, Albert and In 't Veld, Marten and Figueiredo, Daniel Martins},
  title = {Data-driven approach to estimate ambient ammonia concentrations},
  journal = {Environmental Research},
  year = {2026},
  volume = {310},
  pages = {126009},
  doi = {10.1016/j.envres.2026.126009}
}
Kostenlos starten →