Natural history collections recapitulate 200 years of faunal change

Abstract

Changing species assemblages represent major challenges to ecosystems around the world. Retracing these changes is limited by our knowledge of past biodiversity. Natural history collections represent archives of biodiversity and are therefore an unparalleled source to study biodiversity changes. In the present study, we tested the value of natural history collections for reconstructing changes in the abundance and presence of species over time. In total, we scrutinized 17 080 quality-checked records for 242 epibenthic invertebrate species from the North and Baltic Seas collected throughout the last 200 years. Our approaches identified eight previously reported species introductions, 10 range expansions, six of which are new to science, as well as the long-term decline of 51 marine invertebrate species. The cross-validation of our results with published accounts of endangered species and neozoa of the area confirmed the results for two of the approaches for 49 to 55% of the identified species, and contradicted our results for 9 to 10%. The results based on relative record trends were less validated. We conclude that, with the proper approaches, natural history collections are an unmatched resource for recovering early species introductions and declines.

Keywords: Crustacea; Echinodermata; Mollusca; biodiversity; collections; marine invertebrates.

Figure 1.

Workflow that led to the investigated collection database. (a) Sampling of specimens, for example by hand-sampling in coastal areas, or by dredging aboard research vessels. (b) Deposition of specimens that are preserved and identified ideally to the species level. If and which specimens are discarded depends on the sampling design, the individual researchers' preferences and the available space in the collections. Collection records reflect the fact that all specimens of the same species and sampling event are stored together as a single lot. (c) Digitized collection records allow the analysis of century-old natural history collections.

Figure 2.

Spatio-temporal distribution of investigated collection records. (a) Spatial distribution of records before and after 1912. The polygons denote the investigated area, notably the North Sea without the British coast, the German part of the Baltic Sea and the transition area between the two seas. (b) Accumulative number of deposited collection lots and species that were new to the collections. Grey areas highlight the major collecting efforts detailed under ‘Data curation’ in the Results section, responsible for the largest increases in species and collection lots.

Figure 3.

Relationship between the relative abundances as reported in the German Red List for benthic marine invertebrates [39] and the number of collection records for these species in the investigated collection database. Relative abundances are sorted from least abundant (extinct) to most abundant (very abundant). Colours denote supraspecific taxa: Crustacea (blue), Echinodermata (red) and Mollusca (green).

Figure 4.

Temporal distribution of collections records for potential neozoa. Temporal distribution of records for species appearing after 1912 in the investigated collection database, excluding species identified as rare. The years 1912 and 1991 (the end of two intense collecting efforts) are indicated by grey vertical lines. Underlined species names indicate previously known neozoa for the North or Baltic Sea. Names of known endangered species [39] are bolded, and names of spatio-temporal sampling artefacts are shown in grey. Arrows indicate species that were significantly increasing or declining based on the GBIF Relative Observations Tool. Colours denote supraspecific taxa: Crustacea (blue) and Mollusca (green). Our analysis did not identify any neozoan Echinodermata to the North or Baltic Sea. The Venn diagram in the upper corner summarizes the cross-validation results from the GBIF Relative Observations Tool (arrows), German Red List (bold number) and known neozoa (underlined number) as per cent species.

Figure 5.

Potentially declining species with relatively few records after 1912. The proportion of records after 1912 is shown by the bold line (top axis). Bar plot of the number of records available before and after 1912 as coloured and grey bars, respectively. Colours denote the supraspecific taxon: Crustacea (blue), Echinodermata (red) and Mollusca (green). Names of known endangered species [39] are bolded. Arrows indicate species that were significantly increasing or declining based on the GBIF Relative Observations Tool. The Venn diagram in the upper corner summarizes the cross-validation results from the GBIF Relative Observations Tool (arrows) and German Red List (bold number) as per cent species.

Figure 6.

Regression slope values of species with significant record trends. (a) Species with significantly negative slopes, (b) species with significantly positive slopes. Depicted is the slope in relation to the class for the complete dataset. Colours denote intraspecific taxa: Crustacea (blue), Echinodermata (red) and Mollusca (green). Names of known endangered species [39] are bolded. Underlined species are independently identified neozoa to the North or Baltic Sea (see text for references). Arrows indicate species that were significantly increasing or declining based on the GBIF Relative Observations Tool. The Venn diagrams in each corner summarize the cross-validation results from the GBIF Relative Observations Tool (arrows), German Red List (bold percentage) and known neozoa (underlined percentage) as per cent of species.

Figure 7.

Intersecting results between approaches. Each filled circle represents one species. The colours denote intraspecific taxa: Crustacea (blue), Echinodermata (red) and Mollusca (green).