Ranking matrices as operational tools for the environmental risk assessment of genetically modified crops on non-target organisms

For the operationalization of the structured, stepwise selection procedure for non-target testing organisms integrated into the new EFSA guidelines for environmental risk assessment of GM plants practical tools - i.e. ranking matrices - were developed. These tools - some of them are new and some are refined from older ones - were tested using the GM case crop of TC 1507 maize. The selection procedure consists of six steps. The strategy builds on identifying the important ecological functions for the particular cropping system and compiling a species lists according to their ecological functions and presence in the specific receiving environments. Subsequently, the species numbers are reduced in a systematic, stepwise fashion to a relevant and practical number of testing organisms and/or processes. Four ecological functional categories were selected: herbivory, pollination, natural enemies and soil organisms/processes. Based on these categories, the relevant species were chosen and subjected to the selection steps. Out of a total of 33 herbivores, 73 pollinators/pollen feeders, 48 natural enemies and 77 soil organisms/processes we started with in Step 1, 15 herbivores, 10 pollinators 17 natural enemy species and 9 soil organisms/processes were selected as relevant and suited for a testing program at the end of the selection procedure in Step 4. Although the ranking tools will continue to need further refinement, we could demonstrate that this procedure allows to swiftly select the most important suite of species and processes from a large number of organisms. This expert-driven process increases ecological realism and transparency in risk assessment and tailors it to the particular receiving environment, thus, overcoming important deficiencies of the current approach that has attracted persistent criticism. We recommend balancing ecological requirements with practicability criteria and realism in the test strategy. At present, the ranking is abundance-oriented and, thus, excludes rare and/or endangered species that are sensitive to disturbances. We suggest additional selection criteria to strengthen nature conservation and off-field aspects. (C) 2013 Elsevier Ltd. All rights reserved.