Waste-water treatment plants (WWTPs) emit large amounts of nitrous oxide (N2O), a potent greenhouse gas with a global-warming potential 265 times stronger than that of carbon dioxide. A study now applies a ‘deep learning’ approach to model, understand and forecast WWTP emissions – a method that uses artificial intelligence (AI) to identify the complex dynamics behind N2O concentrations, based on data collected over one year from a WWTP in Denmark.