JSJoseph M. Szewczak

Joseph M. Szewczak

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Joseph M. Szewczak has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Bat Use of Hollows in California’s Old-Growth Redwood Forests: From DNA to Ecology

    by Amon J. Armstrong, Faith M. Walker, Colin J. Sobek, Cheri J. Sanville, Stephanie L. Martin, Joseph M. Szewczak

    The loss of roosting resources, either through disturbance or removal, negatively affects bats. Identifying sensitive species and determining roost requirements are critical components in conserving their habitat. Cavity-roosting bats on the North Coast of California are known to use hollows in large redwood trees. In this study, we examined the factors determining the use of basal tree hollows by different bat species at eight redwood forest sites in Del Norte, Humboldt, and Mendocino Counties, California. Bat guano was collected from 179 basal hollow roosts from 2017 to 2018, and guano mass was used as an index of roosting activity. Nine bat species and one species group were identified by analysis of DNA in guano. We made a total of 253 identifications from 83 hollows into the 10 species categories. The most prevalent species were Myotis californicus (California myotis; 28.5% of all identifications), the Myotis evotis-Myotis thysanodes group (17.4%), Corynorhinus townsendii (17.0%), and Myotis volans (15.0%). We evaluated the extent to which habitat variables at the scales of the hollow, vicinity, and site influenced the level of roost use. The correlations between guano mass and habitat variables were examined using generalized additive mixed models. At the hollow scale, guano mass increased with ceiling height above the opening. At the vicinity scale, guano mass increased with less cover of small trees. At the site scale, there was no association between guano mass and distance to foraging areas, elevation, or the number of nearby hollows. These tree hollow roost preferences can inform land managers when planning the management and conservation of redwood forests.


  • Open Access

    Classification of Echolocation Calls from 14 Species of Bat by Support Vector Machines and Ensembles of Neural Networks

    by Robert D. Redgwell, Joseph M. Szewczak, Gareth Jones, Stuart Parsons

    Calls from 14 species of bat were classified to genus and species using discriminant function analysis (DFA), support vector machines (SVM) and ensembles of neural networks (ENN). Both SVMs and ENNs outperformed DFA for every species while ENNs (mean identification rate – 97%) consistently outperformed SVMs (mean identification rate – 87%). Correct classification rates produced by the ENNs varied from 91% to 100%; calls from six species were correctly identified with 100% accuracy. Calls from the five species of Myotis, a genus whose species are considered difficult to distinguish acoustically, had correct identification rates that varied from 91 – 100%. Five parameters were most important for classifying calls correctly while seven others contributed little to classification performance.