Search

Three species of invasive carp—Grass Carp Ctenopharyngodon idella, Silver Carp Hypophthalmichthys molitrix, and Bighead Carp H. nobilis—are rapidly spreading throughout North America. Monitoring their reproduction can help to determine establishment in new areas but is difficult due to challenges associated with identifying fish eggs. Recently, random forest models provided accurate identification of eggs based on morphological traits, but the models have not been validated using independent data. Our objective was to evaluate the predictive performance of egg identification models developed by Camacho et al. (2019) for classifying invasive carp eggs by using an independent data set. When invasive carp were grouped as one category, predictive accuracy was high at the following levels: family (89%), genus (90%), species (91%), and species with reduced predictor variables (94%). Invasive carp predictive accuracy decreased when we only considered observations from newly sampled locations (family: 9%; genus: 22%; species: 30%; species with reduced predictor variables: 70%), suggesting potential differences in egg characteristics among locations. Random forest models using a combination of previous and new data resulted in high predictive accuracy for invasive carp (96–98%) when invasive carp were grouped as one class for all models at the family, genus, and species levels. The two most influential predictor variables were average membrane diameter and average embryo diameter; the probability of predicting an invasive carp egg increased with these metrics. High predictive accuracy metrics suggest that these trained and validated random forest models can be used to identify invasive carp eggs based on morphometric variables. However, decreased performance at new locations suggests that more research would be beneficial to determine the models' applicability to a larger spatial region. [ABSTRACT FROM AUTHOR]

Within the Great Plains region of North America, oxbow wetlands were lost as streams were channelized and straightened to allow for agricultural use of the landscape. Topeka Shiner, which rely on these oxbow wetlands, have declined in abundance, currently occupy 20% of their historical geographic range, and are now an endangered species. A large emphasis has been placed on restoring oxbow wetlands to recover Topeka Shiner populations. As the number of oxbow restorations has increased, so has the number of monitoring projects focused on these habitats. Currently, conservation practitioners rely on the presence of Topeka Shiner to determine the success of an oxbow restoration. Given the rarity of the species, this method is likely ineffective. Within this study we attempt to create a model that can be used to determine the success of an oxbow restoration that will benefit the Topeka Shiner without relying on the presence of the species in the wetland. We used multiple fish community metrics and modelling strategies to determine the best model for predicting Topeka Shiner CPUE and presence/absence within oxbows. We determined that the top models were ineffective at predicting Topeka Shiner CPUE and presence/absence. Our findings illustrate the random nature by which fish communities become established within oxbows, and the island-like nature of oxbows in terms of how fish communities may become established and change over time. These findings indicate that the success of oxbow restoration for Topeka Shiner needs to be defined at a larger scale than for individual oxbows. Furthermore, our findings corroborate the inability of previous studies to determine reproducible associations of Topeka Shiner with various fish community metrics. [ABSTRACT FROM AUTHOR]