摘要：Climate change models predict reduced summer precipitations for most European countries, including more frequent and extreme summer droughts. Rainout-shelters which intercept part of the natural precipitation provide an effective tool to investigate effects of different precipitation levels on biodiversity and ecosystem functioning. In this study, we evaluate and describe in detail a fixed-location rainout-shelter (2.5 x 2.5m) with partial interception of natural rainfall. We provide a complete parts list, a construction manual and detailed CAD drawings allowing to rebuild and use these shelters for rainfall manipulation studies. In addition, we describe a rainout-shelter control treatment giving the possibility to quantify and account for potential shelter artefacts. To test the rainout-shelters, we established the following three treatments each in eight winter wheat plots of the agricultural long-term farming system comparison trial DOK in Therwil (Switzerland): (1) A rainout-shelter with 65 % interception of rainfall, (2) a rainout-shelter control without interception of rainfall and (3) an ambient control. The rainout-shelter effectively excluded 64.9 % of the ambient rainfall, which is very close to the a priori calculated exclusion of 65.1 %. In comparison to the ambient control plots, gravimetric soil moisture decreased under the rainout-shelter by a maximum of 11.1 percentage points. Air temperature under the rainout-shelter differed little from the ambient control (-0.55°C in 1.2 m height and +0.19°C in 0.1 m height), whereas soil temperatures were slightly higher in periods of high ambient temperature (+1.02°C), but remained basically unaffected in periods of low ambient temperature (+0.14°C). A maximum edge effect of 0.75 m defined a sampling area of 1 x 1 m under the rainout-shelter. The rainout-shelters presented here, proved to sustain under heavy weather and they were well suited to be used in agricultural fields where management operations require the removal of the rainout-shelters for management operations. Overall, the results confirmed the good performance of the presented rainout-shelters regarding rainout-shelter artefacts, predictable rain exclusion, and feasibility for experimental studies in agricultural fields.
