Towards global estimates of reservoir nitrogen fixation: insights from machine learning
Journal of Environmental Management · 2026-07 · 413 · 130385
DOI: 10.1016/j.jenvman.2026.130385 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Environmental Management, 2026-07. Verfasst von Chunli Zheng und 2 weiteren Autor:innen. Beteiligte Einrichtung: The Key Laboratory of Environmental Pollution Monitoring and Disease Control, Ministry of Education, Department of Toxicology, School of Public Healt…. Hauptthemen laut MEDLINE: Machine Learning, Nitrogen Fixation. Die Arbeit nennt 74 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Reservoir construction is rapidly expanding worldwide, yet their role in the global nitrogen cycle remains poorly understood. Biological nitrogen fixation (BNF) in inland fresh waters is a major pathway of nitrogen fixation but continues to be overlooked for estimates of global BNF. Here, we use a dataset of BNF in 524 reservoirs with corresponding environmental predictor variables to train and test six machine learning based models. The support vector machine model exhibited the strong predictive performance (R2 = 0.71, RMSE = 0.41) and was used for further analyses. Using shapley additive explanations, we found that reservoir characteristics (volume, surface area) and climatic factors (precipitation seasonality, mean annual precipitation, and temperature seasonality) most influenced BNF rates. Notably, small reservoirs ( 1 km3) dominated the total nitrogen budget due to their vast storage capacity. Applying our model to 92,527 United States (U.S.) reservoirs, we estimated an annual fixation of approximately 1.5 Tg N. Given that inland and coastal waters contribute about 15% to global BNF, reservoirs are estimated to account for 3-5% of this aquatic contribution. Within the U.S, hotspots of reservoir N-fixations were identified to be in the southeast (Florida and along the Mississippi), but they also came with the largest model uncertainties. Our findings reposition reservoirs as critical for the global nitrogen cycle, that simultaneously act as large-scale nitrogen sinks and both localized nutrient sources. We also demonstrated how machine learning can advance biogeochemical assessments at national scale, with potential for broader application.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- The Key Laboratory of Environmental Pollution Monitoring and Disease Control, Ministry of Education, Department of Toxicology, School of Public Health, Guizhou Medical University, Guiyang, Guizhou, 550025, People's Repu…
- Guizhou Provincial Key Laboratory of Mountain Environment, Guizhou Normal University, Guiyang, 550001, People's Republic of China. Electronic address: liaohongkai66@163.com.
- Department of Fish, Wildlife & Conservation Ecology, New Mexico State University, Las Cruces, NM, 88003, USA.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zheng, C., Liao, H., & Boeing, W. J. (2026). Towards global estimates of reservoir nitrogen fixation: insights from machine learning. Journal of Environmental Management, 413, 130385. https://doi.org/10.1016/j.jenvman.2026.130385
Vancouver
Zheng C, Liao H, Boeing WJ. Towards global estimates of reservoir nitrogen fixation: insights from machine learning. Journal of Environmental Management. 2026;413:130385. doi:10.1016/j.jenvman.2026.130385
BibTeX
@article{Zheng2026,
author = {Zheng, Chunli and Liao, Hongkai and Boeing, Wiebke J},
title = {Towards global estimates of reservoir nitrogen fixation: insights from machine learning},
journal = {Journal of Environmental Management},
year = {2026},
volume = {413},
pages = {130385},
doi = {10.1016/j.jenvman.2026.130385}
}
EUVIMED