Spatiotemporal Patterns of Methane and Nitrous Oxide Emissions in China’s Inland Waters Identified by Machine Learning Technique

The fugitive emissions of greenhouse gases, primarily
methane (CH4) and nitrous oxide (N2O), from
water environments
have aroused global concern. However, there are currently limited
information about national-scale data of CH4 and N2O emissions from inland waters, such as lakes, rivers, and
reservoirs, particularly in developing countries. This study employed
machine learning techniques, based on the literature data and national
water quality monitoring data, to reveal the CH4 and N2O emission patterns of China’s inland waters at the
third-level basin and daily resolution. Our results show significant
seasonal variations in CH4 emissions, which were influenced
by total nitrogen and chemical oxygen demand concentrations. Northern
watersheds were identified as hotspots of CH4 emissions,
with 57% higher CH4 flux than the other watersheds. In
contrast, N2O had a relatively lower contribution to total
carbon emissions and showed smaller temporal and spatial variations.
The estimated total emissions of CH4 and N2O
in China’s inland waters in 2021 amounted to 80.22 Tg of carbon
dioxide equivalent, accounting for 9–11% of China’s
terrestrial carbon sinks. This research provides valuable insights
to guide the counting and control of greenhouse gas emissions from
environmental water bodies.