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