EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GLoN: A Global–Local Framework for Global Agricultural Nitrogen Loss Prediction

Baobao Pan, Kaibin Wang, Alex Kai Qin, Xiaoyu Xia, Di Liu, Deli Chen, Shu Kee Lam

Modern Agriculture · 2026-12 · 4 (2)

DOI: 10.1002/moda.70047 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Modern Agriculture, online erschienen am 28.07.2026. Verfasst von Baobao Pan und 6 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Nitrogen (N) is critical for global crop production, yet its transformations in agroecosystems drive losses via multiple pathways (e.g., NH 3 volatilisation, N 2 O emissions, and nitrate leaching/runoff) with major climate and environmental consequences. N loss modelling has advanced substantially over recent decades, ranging from simple emission‐factor inventories to process‐based simulations and machine learning. However, current modelling approaches for global N loss prediction are constrained by imbalanced and heterogeneous datasets and by the ‘one‐size‐fits‐all’ assumption that fails to account for region‐specific drivers across diverse soils, climates and management regimes. To bridge these gaps, we propose the Global–Local Nitrogen (GLoN) prediction framework. GLoN first develops region‐specific N loss prediction models using the input variables identified from each regional dataset. It then constructs an aggregated global model through the weighted synthesis of all regional models. For each region, the final N loss prediction is obtained by combining the regional model with the aggregated global model, so that data‐rich regions retain stronger local specificity while data‐sparse regions remain stabilised by cross‐region information. GLoN is valuable as it provides a structure for integrating heterogeneous regional evidence into globally coherent N loss prediction. It can retain regional specificity while supporting global estimation, mitigation assessment, and cross‐region comparison.

Förderung

  • Australian Research Council

Zitieren

APA

Pan, B., Wang, K., Qin, A. K., Xia, X., Liu, D., Chen, D., & Lam, S. K. (2026). GLoN: A Global–Local Framework for Global Agricultural Nitrogen Loss Prediction. Modern Agriculture, 4(2). https://doi.org/10.1002/moda.70047

Vancouver

Pan B, Wang K, Qin AK, Xia X, Liu D, Chen D, et al. GLoN: A Global–Local Framework for Global Agricultural Nitrogen Loss Prediction. Modern Agriculture. 2026;4(2). doi:10.1002/moda.70047

BibTeX
@article{Pan2026,
  author = {Pan, Baobao and Wang, Kaibin and Qin, Alex Kai and Xia, Xiaoyu and Liu, Di and Chen, Deli and Lam, Shu Kee},
  title = {GLoN: A Global–Local Framework for Global Agricultural Nitrogen Loss Prediction},
  journal = {Modern Agriculture},
  year = {2026},
  volume = {4},
  number = {2},
  doi = {10.1002/moda.70047}
}
Kostenlos starten →