Deoxygenation is commonly observed in oceans and lakes but less expected in shallower, flowing rivers. Here we reconstructed daily water temperature and dissolved oxygen in 580 rivers across the United States and 216 rivers in Central Europe by training a deep learning model using temporal weather and water quality data and static watershed attributes (for example, hydro-climate, topography, land use, soil). Results revealed persistent warming in 87% and deoxygenation in 70% of the rivers. Urban rivers demonstrated the most rapid warming, whereas agricultural rivers experienced the slowest warming but fastest deoxygenation. Mean deoxygenation rates (−0.038 ± 0.026 mg l−1 decade−1) were higher than those in oceans but lower than those in temperate lakes. These rates, however, may be underestimated, as training data are from grab samples collected during the day when photosynthesis peaks. Projected future rates are between 1.6 and 2.5 times higher than historical rates, indicating significant ramifications for water quality and aquatic ecosystems.
Discharge and water quality data in the United States were downloaded from the USGS National Water Information System (NWIS) at https://waterdata.usgs.gov/nwis. The historical meteorological datasets in the United States are available from the NLDAS-2 (https://ldas.gsfc.nasa.gov/nldas/v2/forcing) and DAYMET (https://daymet.ornl.gov). Basin characteristics in the United States are from GAGES-II archived at https://water.usgs.gov/GIS/metadata/usgswrd/XML/gagesII_Sept2011.xml. The LamaH-CE paper and dataset including meteorological forcing, discharge and basin attributes is available at https://doi.org/10.5194/essd-13-4529-2021. Due to limits in sharing raw water quality data from providers in the CE region, we recommend accessing data directly from their websites: Water quality data for Austria were obtained from the Federal Ministry of Agriculture, Regions and Tourism at https://wasser.umweltbundesamt.at/h2odb/fivestep/abfrageQdPublic.xhtml. Water quality data in Switzerland were obtained from the Swiss Federal Institute of Aquatic Science and Technology (EAWAG) and Federal Office for the Environment (FOEN) at https://doi.org/10.25678/0004AV. Water quality data for Germany were obtained from the State Agency for the Environment Baden-Württemberg at https://udo.lubw.baden-wuerttemberg.de/public/index.xhtml, and the Bavarian State Office for the Environment at https://www.gkd.bayern.de/en/rivers/chemistry. Supporting data are deposited at https://github.com/LiReactiveWater/WT-DO-US-CE-dataset. The projected downscaled forcing data from the NEX-GDDP-CMIP6 database19 can be found at https://doi.org/10.7917/OFSG3345.