摘要：Monitoring is a key step for achieving restoration success. Despite increasing advances for selecting ecological indicators, monitoring sampling designs are not always available. We investigated how tree richness and the most used forest structure indicators vary spatially in restoration sites, aiming to provide evidence-based guidance for future monitoring protocols. We collected data from eight forest restoration sites covering overall 1,000 ha in four Brazilian Atlantic Forest regions. Canopy cover, tree density, vegetation height, and species richness were assessed in 18.2 ha of plots ranging from 60 to 300 m2 in size, in restoration sites aged 1 to 5 years old. Using resampling techniques, we calculated the sampling error for the indicators and compared them with original sampling results, and then estimated the number of plots needed to reach a 20% sampling error. The ecological indicators assessed showed high variability among restoration sites. Canopy cover and height required less plots to reach the targeted sampling error than density of trees. The number of species does not stabilize even when more than 90% of the total number of plots was resampled, indicating high spatial variation. The use of the sampling error approach for defining how much to monitor, associated to appropriate sampling methods, could increase the reliability of monitoring. In addition, they will reduce operational costs, thus providing a key contribution to the effectiveness of large-scale restoration programs expected to be implemented globally in the coming years. Thus, we recommend the incorporation of this in the forest restoration monitoring protocols being discussed worldwide.
