Predicting Dynamic Riverine Nitrogen Export in Unmonitored Watersheds: Leveraging Insights of AI from Data-Rich Regions

Xiong, Rui1,2; Zheng, Yi1,5; Chen, Nengwang3; Tian, Qing3; Liu, Wei1; Han, Feng1; Jiang, Shijie1,4; Lu, Mengqian2; Zheng, Yan1

2022-06-01

10.1021/acs.est.2c02232

ENVIRONMENTAL SCIENCE & TECHNOLOGY   Impact Factor & Quartile

0013-936X

1520-5851

Terrestrial export of nitrogen is a critical Earth system process, but its global dynamics remain difficult to predict at a high spatiotemporal resolution. Here, we use deep learning (DL) to model daily riverine nitrogen export in response to hydrometeorological and anthropogenic drivers. Long short-term memory (LSTM) models for the daily concentration and flux of dissolved inorganic nitrogen (DIN) were built in a coastal watershed in southeastern China with a typical subtropical monsoon climate. The DL models exhibited excellent accuracy for both DIN concentration and flux, with Nash-Sutcliffe efficiency coefficients (NSEs) up to 0.67 and 0.92, respectively, a performance unlikely to be achieved by generic process-based models with comparable data quality. The flux model ensemble, without retraining, performed well (mean NSE = 0.32-0.84) in seven distinct watersheds in Asia, Europe, and North America, and retraining with multi-watershed data further improved the lowest NSE from 0.32 to 0.68. DL interpretation confirmed that interbasin consistency of riverine nitrogen export exists across different continents, which stems from the similarities in rainfall-runoff relationships. The multi-watershed flux model projects 0.60-12.4% increases in the nitrogen export to oceans from the studied watersheds under a 20% increase in fertilizer consumption, which rises to 6.7-20.1% with a 10% increase in runoff, indicating the synergistic effect of human activities and climate change. The DL-based method represents a successful case of explainable artificial intelligence in environmental science, providing a potential shortcut to a consistent understanding of the global daily-resolution dynamics of riverine nitrogen export under the currently limited data conditions.

nitrogen riverine export nonpoint sources deep learning LSTM transfer learning artificial intelligence

SCI ; EI

English

NI Journal Papers

First ; Corresponding

National Natural Science Foundation of China["51961125203","92047302"] ; Shenzhen Science and Technology Innovation Commission[KCXFZ202002011006491]

Engineering ; Environmental Sciences & Ecology

Engineering, Environmental ; Environmental Sciences

WOS:000826222100001

AMER CHEMICAL SOC

20223012418256

Climate change ; Climate models ; Earth system models ; Learning systems ; Runoff ; Watersheds

Flood Control:442.1 ; Meteorology:443 ; Atmospheric Properties:443.1 ; Surface Water:444.1 ; Maintenance:913.5 ; Mathematics:921

ENVIRONMENT/ECOLOGY

Web of Science

1.Southern Univ Sci & Technol, Sch Environm Sci & Engn, Shenzhen, 518055, Peoples R China
2.Hong Kong Univ Sci & Technol, Dept Civil & Environm Engn, Hong Kong 999077, Peoples R China
3.Xiamen Univ, Coll Environm & Ecol, Fujian Prov Key Lab Coastal Ecol & Environm Studie, Xiamen, 361102, Peoples R China
4.Helmholtz Ctr Environm Res, Dept Computat Hydrosyst, D-04318 Leipzig, Germany
5.Southern Univ Sci & Technol, Shenzhen Municipal Engn Lab Environm IoT Technol, Shenzhen 518055, Guangdong Provi, Peoples R China

Xiong, Rui,Zheng, Yi,Chen, Nengwang,et al. Predicting Dynamic Riverine Nitrogen Export in Unmonitored Watersheds: Leveraging Insights of AI from Data-Rich Regions[J]. ENVIRONMENTAL SCIENCE & TECHNOLOGY,2022,56:10530-10542.

Xiong, Rui.,Zheng, Yi.,Chen, Nengwang.,Tian, Qing.,Liu, Wei.,...&Zheng, Yan.(2022).Predicting Dynamic Riverine Nitrogen Export in Unmonitored Watersheds: Leveraging Insights of AI from Data-Rich Regions.ENVIRONMENTAL SCIENCE & TECHNOLOGY,56,10530-10542.

Xiong, Rui,et al."Predicting Dynamic Riverine Nitrogen Export in Unmonitored Watersheds: Leveraging Insights of AI from Data-Rich Regions".ENVIRONMENTAL SCIENCE & TECHNOLOGY 56(2022):10530-10542.