气候变化领域集成服务门户

5. Droughts and floods are complicated: The picture on droughts and floods is more complicated than most people think. First, there is a great deal of regional variation, second the historical metrics we use to assess drought (such as the Palmer Drought Severity Index) don t perform very well in a changing climate, and third the attribution of meteorological or agricultural or ecological drought varies as well. Analyses that average over too wide an area, or that look at the wrong metrics, will come to erroneous conclusions. The IPCC authors went to a lot of trouble to disentangle this and the assessment in Fig. SPM3 of evidence for observed drought changes focuses specifically on agricultural and ecological drought (based on soil moisture), as opposed to hydrological drought (runoff) or meteorological drought (based on rainfall). This is because we don t see strong attribution in total rainfall amounts, but we do in evaporative demand (which depends on temperature). Thus when we have a longterm precipitation anomaly (such as in the American South West (WNA in the hexagon plot above)), we can t (yet) attribute the rainfall change, but we can attribute the soil moisture change. Floods are also complicated because they too don t solely depend on a single factor (such as intense precipitation) but instead are a function of prior state of soil moisture, water management practices and other hyper-local effects. Work here will continue to advance, but the picture is clear only in a few regions so far.