The frequency and severity of heatwaves is expected to increase as the global climate warms. We apply crossing theory for the first time to determine heatwave properties solely from the distribution of daily observations without time-correlation information. We use Central England Temperature time series to quantify how the simple increased occurrence of higher temperatures makes heatwaves (consecutive summer days with temperatures exceeding a threshold) more frequent and intense. We find an overall twofold to threefold increase in heatwave activity since the late 1800's. Week-long heatwaves that on average return every 5 years were typically below similar to 28 degrees C and now typically exceed it. Our analysis takes as inputs average user-specific heat wave properties. Its output pinpoints the range of temperatures for which changes in the distribution must be well resolved statistically in order to track how these heatwave properties are changing. This provides a quantitative benchmark for models used for the attribution of heat waves.
Plain Language Summary As the climate changes, we can expect to see changes in the frequency and severity of heatwaves. Heatwaves are defined here as successive days during which the surface temperature is above a threshold value. A heatwave threshold value that is important for planning will vary depending on circumstances or geographical location, for the United Kingdom we consider the building overheating threshold of 28 degrees C, but higher thresholds may be relevant in more equatorial regions. The Central England Temperature time series is one of the longest continuous records of daily surface temperature measurements and we use this data to estimate how U.K. heatwaves have changed from 1878 to the present. We find an overall twofold to threefold increase in heatwave activity since the late 1800' s. Week-long heatwaves that occur on average every 5 years were typically below about 28 degrees C but now typically exceed it. Our analysis relies solely on the observations and does not involve large-scale numerical models. It provides a quantitative verification for models that are used to attribute heatwave activity.