Use of experimental disturbances to assess resilience along a known stress gradient

We sought to determine the effectiveness of experimental disturbances for assessing resilience and stability in a Spartina alterniflora salt marsh. To do this, we applied disturbances of different intensities along a gradient of sediment deposition that doubled as a gradient of known stress, being associated in previous studies with numerous measures of plant vigor and soil condition. Using this gradient as a standard, we postulated a priori that areas receiving sediment were less stressed than areas which received no sediment, and therefore would be more stable and recover more rapidly after experimental disturbances. For the vegetation, we found that our estimates of resilience and stability were strongly and positively affected by sediment deposition, and therefore agreed with our a priori estimates. After lethal disturbance (herbicide application), vegetation in plots not receiving sediment failed to recover, and the affected marsh turned into a mudflat and remained so during the period of observation (>2 years). In contrast, plots receiving high and moderate amounts of sediment recovered rapidly after lethal disturbance (8-11% recovery month(-1) to 50% of control levels [dependent variable was a composite variable describing vegetation]). After non-lethal disturbance (trimming at the soil surface) all study plots recovered, with rate of vegetative recovery being directly associated with degree of sediment deposition. For edaphic parameters, there no was effect of disturbance, and thus these parameters appeared to be resistant to vegetation removal. These parameters appeared to be more powerfully affected by other factors, such as water level fluctuations and sediment addition. We conclude that experimental disturbances accurately assessed stress along a known stress-gradient. They also provided additional information about the underlying stress in the system. In particular, it was intriguing that in stressed areas S. alterniflora grew in elevated "hummocks" which appeared unable to send rhizomes into denuded areas or to recover after root death. Because recovery after experimental disturbances depends on a variety of plant-soil processes, we suggest that this recovery can be used as a bio-indicator of ecosystem condition that provides insight into important underlying determinants of structure and function. (c) 2007 Elsevier Ltd. All rights reserved.