Machine learning modeling study reveals hydropower reservoirs will generate 87% of energy-sector emissions globally by 2050, indicating major climate trade-offs in dam expansion.
Hydropower reservoirs are recognised as significant sources of greenhouse gases. In this study, we employed machine learning models trained on published datasets to assess reservoir emissions over time, explicitly accounting for changing climatic conditions. Here we show that, under a net-zero emissions scenario, total greenhouse gas emissions from both installed and planned hydropower projects are projected to exceed those from conventional energy sources, representing 87% of total energy-sector emissions by 2050, with 44.6% from planned projects. Within this scenario, planned reservoirs and constructed reservoirs are expected to emit approximately 2509 and 2360 megatonnes of carbon dioxide equivalent per year, respectively. Globally, hydropower GHG emissions are projected to surge during the 2060s, primarily driven by methane ebullition. In North America, Africa, and Europe, emissions are expected to reach a peak in the 2060s, after which they decline due to drier climatic conditions, whereas emissions in South America and Central and South Asia are projected to stabilise by the 2090s. Hydropower reservoirs representing 87% of total energy-sector emissions by 2050 under a net-zero scenario; according to machine learning models trained on published datasets accounting for evolving climatic conditions.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: